{"as_of":"2026-08-19T23:33:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:f10aa3073d35ec0d198f6c5e0b20d09cf77dd7daea4bc07ff444c70f98b84053","coverage":[{"denominator":68,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":68,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T22:45:34.291934Z","state":"measured"},{"denominator":68,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":68,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-19T06:32:44.657259+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2505.06477/citation-record","integrity":"/paper/2505.06477/integrity","json":"/paper/2505.06477/citation-record.json","paper":"/paper/2505.06477"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:45:35.281947Z","title":"Using machine learning for healthcare challenges and opportunities","venue":null,"work_id":"a04b8c88-01be-4a98-870b-e2733c1ff70f","year":2022},"citing_paper":{"arxiv_id":"2505.06477","last_updated":"2025-05-10T00:33:15Z","snapshot_observed_at":"2026-08-19T20:55:22.611592Z","submitted_at":"2025-05-10T00:33:15Z","title":"Learning from the Good Ones: Risk Profiling-Based Defenses Against Evasion Attacks on DNNs","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-15T22:45:34.039728Z"},"links":{"citing_paper":"/paper/2505.06477"},"observation_digest":"sha256:8a20219ba62c825e9fa23375d81de811396916be7ffbf6586bef9299cb5f440d","observation_id":"562a430a-1c93-445b-9c6b-8790e528b4c5","resolution":{"observed_at":"2026-08-15T22:45:35.285672Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:45:35.270575Z","title":"Machine learning in healthcare","venue":null,"work_id":"ce16c474-f156-4cc6-8c2d-e20532c1ad4a","year":2021},"citing_paper":{"arxiv_id":"2505.06477","last_updated":"2025-05-10T00:33:15Z","snapshot_observed_at":"2026-08-19T20:55:22.611592Z","submitted_at":"2025-05-10T00:33:15Z","title":"Learning from the Good Ones: Risk Profiling-Based Defenses Against Evasion Attacks on DNNs","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-15T22:45:34.043949Z"},"links":{"citing_paper":"/paper/2505.06477"},"observation_digest":"sha256:76f145423657715c58247067502871621182f4e8f0c99e9044b69d23ad8cd074","observation_id":"2ca97029-8716-4346-afa2-cc3c956c9532","resolution":{"observed_at":"2026-08-15T22:45:35.274557Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:45:35.259072Z","title":"Machine learning for healthcare: on the verge of a major shift in healthcare epidemiology","venue":null,"work_id":"dd69e34f-743b-4613-8ae7-8c6d492e57d2","year":2018},"citing_paper":{"arxiv_id":"2505.06477","last_updated":"2025-05-10T00:33:15Z","snapshot_observed_at":"2026-08-19T20:55:22.611592Z","submitted_at":"2025-05-10T00:33:15Z","title":"Learning from the Good Ones: Risk Profiling-Based Defenses Against Evasion Attacks on DNNs","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-15T22:45:34.048159Z"},"links":{"citing_paper":"/paper/2505.06477"},"observation_digest":"sha256:cf830d853e332197ceae76a683be0abb9bf45c86d7b9db07d90b12fa5b541ead","observation_id":"745e26ab-db2c-45be-9665-1d16f76adb72","resolution":{"observed_at":"2026-08-15T22:45:35.263236Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:45:35.246880Z","title":"Deep neural networks in healthcare systems","venue":null,"work_id":"5c5d5269-5a15-44c3-8413-f70621e99ad7","year":2022},"citing_paper":{"arxiv_id":"2505.06477","last_updated":"2025-05-10T00:33:15Z","snapshot_observed_at":"2026-08-19T20:55:22.611592Z","submitted_at":"2025-05-10T00:33:15Z","title":"Learning from the Good Ones: Risk Profiling-Based Defenses Against Evasion Attacks on DNNs","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-15T22:45:34.052431Z"},"links":{"citing_paper":"/paper/2505.06477"},"observation_digest":"sha256:748e861e6e602e6b9ffe8f9bbacf86130385afbce5db6c57d9b3fb687b4335ce","observation_id":"2b6c21c7-ffd5-483c-9176-e58d62639092","resolution":{"observed_at":"2026-08-15T22:45:35.251018Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:45:35.235360Z","title":null,"venue":null,"work_id":"45f42dcc-3b39-4773-acc0-2ac0d8f59875","year":2023},"citing_paper":{"arxiv_id":"2505.06477","last_updated":"2025-05-10T00:33:15Z","snapshot_observed_at":"2026-08-19T20:55:22.611592Z","submitted_at":"2025-05-10T00:33:15Z","title":"Learning from the Good Ones: Risk Profiling-Based Defenses Against Evasion Attacks on DNNs","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-15T22:45:34.056051Z"},"links":{"citing_paper":"/paper/2505.06477"},"observation_digest":"sha256:a7a6716bf2ee4d27cb651eb786b8a949daaa29f76d37e1876778dcaa92a56c5f","observation_id":"578e5c5d-11ac-4a7c-a3ca-22b67a586e3a","resolution":{"observed_at":"2026-08-15T22:45:35.239369Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:45:35.222641Z","title":"Autonomous driving ar- chitectures: insights of machine learning and deep learning algorithms","venue":null,"work_id":"85704695-6319-4b6d-8de4-e0d4817a9d9b","year":2021},"citing_paper":{"arxiv_id":"2505.06477","last_updated":"2025-05-10T00:33:15Z","snapshot_observed_at":"2026-08-19T20:55:22.611592Z","submitted_at":"2025-05-10T00:33:15Z","title":"Learning from the Good Ones: Risk Profiling-Based Defenses Against Evasion Attacks on DNNs","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-15T22:45:34.059928Z"},"links":{"citing_paper":"/paper/2505.06477"},"observation_digest":"sha256:a90a0048ad81c0071ab5cef2e25d615e6d478158f3578c878805b5c5b6f69d31","observation_id":"6a43a2d6-b125-4db1-8026-1cff3bbe938d","resolution":{"observed_at":"2026-08-15T22:45:35.226708Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:45:35.209327Z","title":"Exploring the mechanism of crashes with autonomous vehi- cles using machine learning","venue":null,"work_id":"7408883b-f28f-4386-98bb-65a3f11d71c1","year":2021},"citing_paper":{"arxiv_id":"2505.06477","last_updated":"2025-05-10T00:33:15Z","snapshot_observed_at":"2026-08-19T20:55:22.611592Z","submitted_at":"2025-05-10T00:33:15Z","title":"Learning from the Good Ones: Risk Profiling-Based Defenses Against Evasion Attacks on DNNs","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-15T22:45:34.064401Z"},"links":{"citing_paper":"/paper/2505.06477"},"observation_digest":"sha256:76b57d3d559d051a77f30b97b8b61231d8c4e9e499571eb080c05d97b29aa746","observation_id":"466b6d25-3e1b-4aae-a473-a9d8314fa7e8","resolution":{"observed_at":"2026-08-15T22:45:35.214303Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:45:35.197309Z","title":"Deep neural networks with koopman operators for modeling and control of autonomous vehicles","venue":null,"work_id":"3a6cb1e5-f361-45db-973e-45c0a9f3d145","year":2022},"citing_paper":{"arxiv_id":"2505.06477","last_updated":"2025-05-10T00:33:15Z","snapshot_observed_at":"2026-08-19T20:55:22.611592Z","submitted_at":"2025-05-10T00:33:15Z","title":"Learning from the Good Ones: Risk Profiling-Based Defenses Against Evasion Attacks on DNNs","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-15T22:45:34.067942Z"},"links":{"citing_paper":"/paper/2505.06477"},"observation_digest":"sha256:8c640d1ece7371fa9b44d57952818a99c5f3330dc07a94839754a9392b731059","observation_id":"ccec83ed-5e30-417d-a989-2504f811fe4c","resolution":{"observed_at":"2026-08-15T22:45:35.201389Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:45:35.185806Z","title":"Simple black- box adversarial attacks on deep neural networks","venue":null,"work_id":"ed7e2d5d-07ae-4405-96d8-3d03af042898","year":2017},"citing_paper":{"arxiv_id":"2505.06477","last_updated":"2025-05-10T00:33:15Z","snapshot_observed_at":"2026-08-19T20:55:22.611592Z","submitted_at":"2025-05-10T00:33:15Z","title":"Learning from the Good Ones: Risk Profiling-Based Defenses Against Evasion Attacks on DNNs","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-15T22:45:34.071512Z"},"links":{"citing_paper":"/paper/2505.06477"},"observation_digest":"sha256:fc64f79a27052f5ecb28d0e7e7712a9b5c8cc8dfea78d5dd162ef7d52167b27b","observation_id":"1d99bed3-4132-48f6-a2da-50542104cc38","resolution":{"observed_at":"2026-08-15T22:45:35.189975Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:45:35.174548Z","title":"Adversarial attacks on deep neural networks for time series classification","venue":null,"work_id":"21e9f73c-218f-4169-aecb-f27857333bfb","year":2019},"citing_paper":{"arxiv_id":"2505.06477","last_updated":"2025-05-10T00:33:15Z","snapshot_observed_at":"2026-08-19T20:55:22.611592Z","submitted_at":"2025-05-10T00:33:15Z","title":"Learning from the Good Ones: Risk Profiling-Based Defenses Against Evasion Attacks on DNNs","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-15T22:45:34.075090Z"},"links":{"citing_paper":"/paper/2505.06477"},"observation_digest":"sha256:7492927b4f6eef584f783a20556038f7c1fe8463a665d59f2b7a247582f4091e","observation_id":"80d40de5-57d6-4c3f-9282-6b38da5612ac","resolution":{"observed_at":"2026-08-15T22:45:35.178551Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:45:35.163523Z","title":"Fast adversarial attacks to deep neural networks through gradual sparsifica- tion","venue":null,"work_id":"2e18d484-1b60-45f6-a5d2-edbfc38b193f","year":2024},"citing_paper":{"arxiv_id":"2505.06477","last_updated":"2025-05-10T00:33:15Z","snapshot_observed_at":"2026-08-19T20:55:22.611592Z","submitted_at":"2025-05-10T00:33:15Z","title":"Learning from the Good Ones: Risk Profiling-Based Defenses Against Evasion Attacks on DNNs","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-15T22:45:34.078731Z"},"links":{"citing_paper":"/paper/2505.06477"},"observation_digest":"sha256:68c86e8be1277f8f7c91d450dcf83555d3aeeb5dd547e89842ea9268f7f6d5b3","observation_id":"69dff1ac-4229-4e0b-9d1f-696edf4de24b","resolution":{"observed_at":"2026-08-15T22:45:35.167216Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1611.01236","last_updated":"2017-02-11T00:15:46Z","snapshot_observed_at":"2026-08-17T02:26:19.835254Z","submitted_at":"2016-11-04T01:11:02Z","title":"Adversarial Machine Learning at Scale","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1611.01236","snapshot_observed_at":"2026-08-15T22:45:34.082825Z","title":"Goodfellow, and Samy Bengio","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2505.06477","last_updated":"2025-05-10T00:33:15Z","snapshot_observed_at":"2026-08-19T20:55:22.611592Z","submitted_at":"2025-05-10T00:33:15Z","title":"Learning from the Good Ones: Risk Profiling-Based Defenses Against Evasion Attacks on DNNs","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-15T22:45:34.082825Z"},"links":{"cited_paper":"/paper/1611.01236","citing_paper":"/paper/2505.06477"},"observation_digest":"sha256:f9939603fb551a0ffb3630d561f2c53e503c5661cdc463b249150f84b9159c5f","observation_id":"2413acd9-57c8-49a5-9c68-68a0be8c2cd6","resolution":{"observed_at":"2026-08-15T22:45:34.082825Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:45:35.152464Z","title":"Are self-driving cars secure? evasion attacks against deep neural networks for steering angle prediction","venue":null,"work_id":"0559f429-4e5e-4b4b-8741-52b80f6b0640","year":2019},"citing_paper":{"arxiv_id":"2505.06477","last_updated":"2025-05-10T00:33:15Z","snapshot_observed_at":"2026-08-19T20:55:22.611592Z","submitted_at":"2025-05-10T00:33:15Z","title":"Learning from the Good Ones: Risk Profiling-Based Defenses Against Evasion Attacks on DNNs","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-15T22:45:34.086831Z"},"links":{"citing_paper":"/paper/2505.06477"},"observation_digest":"sha256:37f818589491bb4e2952a70175aeba375b6a378c41b8c02311ab70170ff02931","observation_id":"f17eefd5-eb0f-43ec-9e85-9dcf06df45d9","resolution":{"observed_at":"2026-08-15T22:45:35.156410Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:45:35.141896Z","title":"Real-time evasion attacks against deep learning-based anomaly detection from distributed system logs","venue":null,"work_id":"53e85ea6-2905-4a6f-895a-d1de8ec96803","year":2021},"citing_paper":{"arxiv_id":"2505.06477","last_updated":"2025-05-10T00:33:15Z","snapshot_observed_at":"2026-08-19T20:55:22.611592Z","submitted_at":"2025-05-10T00:33:15Z","title":"Learning from the Good Ones: Risk Profiling-Based Defenses Against Evasion Attacks on DNNs","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-15T22:45:34.090777Z"},"links":{"citing_paper":"/paper/2505.06477"},"observation_digest":"sha256:fac548546962b39c6fccae236923ada2a7476f49c6106d5fd3b2ba6474c7fc13","observation_id":"c98dc576-5395-4402-91c0-b4b0cbd4abf1","resolution":{"observed_at":"2026-08-15T22:45:35.145651Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:45:35.130677Z","title":"What is adversarial machine learning? attack methods in 2024, June 2024","venue":null,"work_id":"11e1879a-c3b8-43a7-bed0-b925b6d67721","year":2024},"citing_paper":{"arxiv_id":"2505.06477","last_updated":"2025-05-10T00:33:15Z","snapshot_observed_at":"2026-08-19T20:55:22.611592Z","submitted_at":"2025-05-10T00:33:15Z","title":"Learning from the Good Ones: Risk Profiling-Based Defenses Against Evasion Attacks on DNNs","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-15T22:45:34.094422Z"},"links":{"citing_paper":"/paper/2505.06477"},"observation_digest":"sha256:bcbcad845f759421bc6296fdfa98b1f257c9db012eee889073bb8dcce929462c","observation_id":"a8d59a2a-aa00-4b76-a7c9-4c3beff7cc21","resolution":{"observed_at":"2026-08-15T22:45:35.134653Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:45:35.118407Z","title":"Evasion attacks against machine-learning based behavioral authentication","venue":null,"work_id":"9a780b5d-3eba-4067-8ef2-507084b6c631","year":2018},"citing_paper":{"arxiv_id":"2505.06477","last_updated":"2025-05-10T00:33:15Z","snapshot_observed_at":"2026-08-19T20:55:22.611592Z","submitted_at":"2025-05-10T00:33:15Z","title":"Learning from the Good Ones: Risk Profiling-Based Defenses Against Evasion Attacks on DNNs","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-15T22:45:34.097981Z"},"links":{"citing_paper":"/paper/2505.06477"},"observation_digest":"sha256:ef8fcb9a1a31827069eb98b6dc815b867cb2b755a5346df7297a0d609b8f7dfa","observation_id":"0255f7fd-44e4-4996-a393-16d961c227b8","resolution":{"observed_at":"2026-08-15T22:45:35.122327Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1312.6199","last_updated":"2014-02-19T16:33:14Z","snapshot_observed_at":"2026-08-15T16:41:15.505782Z","submitted_at":"2013-12-21T03:36:08Z","title":"Intriguing properties of neural networks","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1312.6199","snapshot_observed_at":"2026-08-15T22:45:34.102776Z","title":"Intriguing properties of neural networks","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2505.06477","last_updated":"2025-05-10T00:33:15Z","snapshot_observed_at":"2026-08-19T20:55:22.611592Z","submitted_at":"2025-05-10T00:33:15Z","title":"Learning from the Good Ones: Risk Profiling-Based Defenses Against Evasion Attacks on DNNs","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-15T22:45:34.102776Z"},"links":{"cited_paper":"/paper/1312.6199","citing_paper":"/paper/2505.06477"},"observation_digest":"sha256:06ae309e48aebee2f8a9b1f613e7579c0a49b68ba6819d762668a05f181ad73b","observation_id":"ed8f5ceb-2f2f-4275-bd25-19fc9a3535a7","resolution":{"observed_at":"2026-08-15T22:45:34.102776Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1412.6572","last_updated":"2015-03-20T20:19:16Z","snapshot_observed_at":"2026-08-19T07:17:20.004918Z","submitted_at":"2014-12-20T01:17:12Z","title":"Explaining and Harnessing Adversarial Examples","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1412.6572","snapshot_observed_at":"2026-08-15T22:45:34.106974Z","title":"Explaining and harnessing adversarial examples","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2505.06477","last_updated":"2025-05-10T00:33:15Z","snapshot_observed_at":"2026-08-19T20:55:22.611592Z","submitted_at":"2025-05-10T00:33:15Z","title":"Learning from the Good Ones: Risk Profiling-Based Defenses Against Evasion Attacks on DNNs","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-15T22:45:34.106974Z"},"links":{"cited_paper":"/paper/1412.6572","citing_paper":"/paper/2505.06477"},"observation_digest":"sha256:e9d7f7f64e3afa3f029a79893e57237e28c412c71d507a58007a58d0f03887fa","observation_id":"d2ab5b26-f7ae-4f94-b0b5-652aeaab44b3","resolution":{"observed_at":"2026-08-15T22:45:34.106974Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:45:35.104623Z","title":"Personalized insulin dose manipulation attack and its detection using interval-based temporal patterns and machine learning algorithms","venue":null,"work_id":"1ec06d4f-6e98-4f4a-a275-d8478767e4f4","year":2022},"citing_paper":{"arxiv_id":"2505.06477","last_updated":"2025-05-10T00:33:15Z","snapshot_observed_at":"2026-08-19T20:55:22.611592Z","submitted_at":"2025-05-10T00:33:15Z","title":"Learning from the Good Ones: Risk Profiling-Based Defenses Against Evasion Attacks on DNNs","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-15T22:45:34.111056Z"},"links":{"citing_paper":"/paper/2505.06477"},"observation_digest":"sha256:6e1b401fb11810a578205b2d525c7a757342512b7b2343d993b6d64c07b35f24","observation_id":"b712e835-c816-4418-beea-8dd739e03f82","resolution":{"observed_at":"2026-08-15T22:45:35.109794Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:45:35.093204Z","title":"Adversarial training against adversarial attacks for machine learning-based intrusion detection systems","venue":null,"work_id":"7e95c3b1-ea89-4871-a0dc-d1b5dc8cded1","year":2022},"citing_paper":{"arxiv_id":"2505.06477","last_updated":"2025-05-10T00:33:15Z","snapshot_observed_at":"2026-08-19T20:55:22.611592Z","submitted_at":"2025-05-10T00:33:15Z","title":"Learning from the Good Ones: Risk Profiling-Based Defenses Against Evasion Attacks on DNNs","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-15T22:45:34.115298Z"},"links":{"citing_paper":"/paper/2505.06477"},"observation_digest":"sha256:597452df29dd1587c53f648de5ce606b1abd662466b608e75fd2d7236ecd671e","observation_id":"666e1a2d-308f-4d36-8e42-d22ad0a322fe","resolution":{"observed_at":"2026-08-15T22:45:35.097283Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:45:35.081484Z","title":"Defending evasion attacks via adversarially adaptive training","venue":null,"work_id":"40d6b380-7860-42db-9b3f-9390c8cde3e7","year":2022},"citing_paper":{"arxiv_id":"2505.06477","last_updated":"2025-05-10T00:33:15Z","snapshot_observed_at":"2026-08-19T20:55:22.611592Z","submitted_at":"2025-05-10T00:33:15Z","title":"Learning from the Good Ones: Risk Profiling-Based Defenses Against Evasion Attacks on DNNs","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-15T22:45:34.118959Z"},"links":{"citing_paper":"/paper/2505.06477"},"observation_digest":"sha256:5d0e2c8955a9ecf76c9142626b7eb0eefaf044ea6158720a7190e5f99d9531f2","observation_id":"aca55bf3-ddb5-4a48-9bd0-0612c87a31a0","resolution":{"observed_at":"2026-08-15T22:45:35.085830Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:45:35.069662Z","title":"Adversarial training methods for deep learning: A systematic review","venue":null,"work_id":"f98728b9-e29c-4fcc-9bc0-df1df210cb6f","year":2022},"citing_paper":{"arxiv_id":"2505.06477","last_updated":"2025-05-10T00:33:15Z","snapshot_observed_at":"2026-08-19T20:55:22.611592Z","submitted_at":"2025-05-10T00:33:15Z","title":"Learning from the Good Ones: Risk Profiling-Based Defenses Against Evasion Attacks on DNNs","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-15T22:45:34.122641Z"},"links":{"citing_paper":"/paper/2505.06477"},"observation_digest":"sha256:44a03ea52f45a1bcb0156e067931e9ffe05c5c340c5082527ae7b6fa7eae6629","observation_id":"a1b07922-8c8e-455d-8b91-86c00afb9a9f","resolution":{"observed_at":"2026-08-15T22:45:35.073786Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:45:35.057873Z","title":"Feature denoising for improving adversarial robustness","venue":null,"work_id":"c2577175-b58f-4f1e-bc5d-3cce2557e5af","year":2019},"citing_paper":{"arxiv_id":"2505.06477","last_updated":"2025-05-10T00:33:15Z","snapshot_observed_at":"2026-08-19T20:55:22.611592Z","submitted_at":"2025-05-10T00:33:15Z","title":"Learning from the Good Ones: Risk Profiling-Based Defenses Against Evasion Attacks on DNNs","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-15T22:45:34.126147Z"},"links":{"citing_paper":"/paper/2505.06477"},"observation_digest":"sha256:a2a6c0b6a3a0c6c1d9365f75181e8e17e25c1c01ea60cfa9969164199a71b817","observation_id":"cfdb93f5-ea43-49a5-9c02-8b0c0c6618d1","resolution":{"observed_at":"2026-08-15T22:45:35.061916Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:45:35.045820Z","title":"Evaluating and improving ad- versarial robustness of machine learning-based network intrusion detec- tors","venue":null,"work_id":"4000ab21-dbec-4bef-9e81-55df1176a8a5","year":2021},"citing_paper":{"arxiv_id":"2505.06477","last_updated":"2025-05-10T00:33:15Z","snapshot_observed_at":"2026-08-19T20:55:22.611592Z","submitted_at":"2025-05-10T00:33:15Z","title":"Learning from the Good Ones: Risk Profiling-Based Defenses Against Evasion Attacks on DNNs","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-15T22:45:34.129788Z"},"links":{"citing_paper":"/paper/2505.06477"},"observation_digest":"sha256:80e54fa3d3d40caad9bffb7acd1b609afdb2ffa8fb7ee9223ceb746aa4356eb3","observation_id":"8851fc79-8885-4731-a5f2-4a4783763012","resolution":{"observed_at":"2026-08-15T22:45:35.049844Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:45:35.034751Z","title":"Adversarial feature alignment: Balancing robustness and accuracy in deep learning via adversarial training, 2024","venue":null,"work_id":"29777d0d-de17-4301-9411-da89e9bfb0e7","year":2024},"citing_paper":{"arxiv_id":"2505.06477","last_updated":"2025-05-10T00:33:15Z","snapshot_observed_at":"2026-08-19T20:55:22.611592Z","submitted_at":"2025-05-10T00:33:15Z","title":"Learning from the Good Ones: Risk Profiling-Based Defenses Against Evasion Attacks on DNNs","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-15T22:45:34.133424Z"},"links":{"citing_paper":"/paper/2505.06477"},"observation_digest":"sha256:871ea697dd0a13e597f0e66d9baeac4f183d50fcf67e18649f5137a119723484","observation_id":"321cea04-1323-4b8a-80ac-839a24850116","resolution":{"observed_at":"2026-08-15T22:45:35.038656Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:45:35.023030Z","title":"The more the merrier: adding hidden measurements to secure industrial control systems","venue":null,"work_id":"ce3e3025-00f7-4bec-ba25-86a2e6515228","year":2020},"citing_paper":{"arxiv_id":"2505.06477","last_updated":"2025-05-10T00:33:15Z","snapshot_observed_at":"2026-08-19T20:55:22.611592Z","submitted_at":"2025-05-10T00:33:15Z","title":"Learning from the Good Ones: Risk Profiling-Based Defenses Against Evasion Attacks on DNNs","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-15T22:45:34.137030Z"},"links":{"citing_paper":"/paper/2505.06477"},"observation_digest":"sha256:8bcdb9d6ca73a5de3505724c303cb1e0c636d576b3c23561edd84e53d9a03d05","observation_id":"3e8cf17a-1493-426d-9e05-c363de3e0d79","resolution":{"observed_at":"2026-08-15T22:45:35.027024Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1804.11022","last_updated":"2018-04-30T02:09:25Z","snapshot_observed_at":"2026-08-14T19:20:43.109272Z","submitted_at":"2018-04-30T02:09:25Z","title":"Adversarial Regression for Detecting Attacks in Cyber-Physical Systems","version":1},"cited_work":{"arxiv_id":"1804.11022","doi":null,"metadata_source":"pith","pith_arxiv_id":"1804.11022","snapshot_observed_at":"2026-08-15T22:45:34.545008Z","title":"Adversarial Regression for Detecting Attacks in Cyber-Physical Systems","venue":"cs.AI","work_id":"a4134a98-c754-4dbf-b4c5-c454e8c8776d","year":2018},"citing_paper":{"arxiv_id":"2505.06477","last_updated":"2025-05-10T00:33:15Z","snapshot_observed_at":"2026-08-19T20:55:22.611592Z","submitted_at":"2025-05-10T00:33:15Z","title":"Learning from the Good Ones: Risk Profiling-Based Defenses Against Evasion Attacks on DNNs","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-15T22:45:34.140635Z"},"links":{"cited_paper":"/paper/1804.11022","citing_paper":"/paper/2505.06477"},"observation_digest":"sha256:15b1faa1561eb9ce43aba3841f7aefc1121b9244ea1ad3872ee78c0819f1a778","observation_id":"c52272f9-ad63-4f06-89a6-6b4938ec4570","resolution":{"observed_at":"2026-08-15T22:45:34.549447Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:45:35.008433Z","title":"Lunar: Unifying local outlier detection methods via graph neural networks","venue":null,"work_id":"80ed5fed-1542-42ea-aab7-7c4794e072cc","year":2022},"citing_paper":{"arxiv_id":"2505.06477","last_updated":"2025-05-10T00:33:15Z","snapshot_observed_at":"2026-08-19T20:55:22.611592Z","submitted_at":"2025-05-10T00:33:15Z","title":"Learning from the Good Ones: Risk Profiling-Based Defenses Against Evasion Attacks on DNNs","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-15T22:45:34.144945Z"},"links":{"citing_paper":"/paper/2505.06477"},"observation_digest":"sha256:dd071686edf459598971f7f9a60c6bf2d34ca182d60eec5fb96a84d784b764ea","observation_id":"300073f6-0b7c-49b9-958e-80efdd963ca3","resolution":{"observed_at":"2026-08-15T22:45:35.014066Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:45:34.994111Z","title":"Robustness test- ing of data and knowledge driven anomaly detection in cyber-physical systems","venue":null,"work_id":"9c6b48fa-a06f-4441-8fa9-575f0f42564c","year":2022},"citing_paper":{"arxiv_id":"2505.06477","last_updated":"2025-05-10T00:33:15Z","snapshot_observed_at":"2026-08-19T20:55:22.611592Z","submitted_at":"2025-05-10T00:33:15Z","title":"Learning from the Good Ones: Risk Profiling-Based Defenses Against Evasion Attacks on DNNs","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-15T22:45:34.148436Z"},"links":{"citing_paper":"/paper/2505.06477"},"observation_digest":"sha256:23e0b97cfc2fbb8556a2eb5973f87c69329bc249f8cc600955296bd850207fdd","observation_id":"6d11a67c-1918-42ff-8846-5c10196e963b","resolution":{"observed_at":"2026-08-15T22:45:34.999211Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:45:34.982605Z","title":"Adversarial attack mitigation strategy for machine learning-based network attack detection model in power system","venue":null,"work_id":"acad500d-d5a5-483d-a88e-5a472005a489","year":2022},"citing_paper":{"arxiv_id":"2505.06477","last_updated":"2025-05-10T00:33:15Z","snapshot_observed_at":"2026-08-19T20:55:22.611592Z","submitted_at":"2025-05-10T00:33:15Z","title":"Learning from the Good Ones: Risk Profiling-Based Defenses Against Evasion Attacks on DNNs","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-15T22:45:34.151916Z"},"links":{"citing_paper":"/paper/2505.06477"},"observation_digest":"sha256:369d333c866a92c4183e9656411071bc95df3aef4295db87db6c9db919d4a02e","observation_id":"8a630f11-fddf-48af-b2f9-ed13de8e5d42","resolution":{"observed_at":"2026-08-15T22:45:34.986575Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:45:34.971901Z","title":"Mad-gan: Multivariate anomaly detection for time series data with generative adversarial networks","venue":null,"work_id":"cabd1fab-7240-4130-9449-1a284192df1c","year":2019},"citing_paper":{"arxiv_id":"2505.06477","last_updated":"2025-05-10T00:33:15Z","snapshot_observed_at":"2026-08-19T20:55:22.611592Z","submitted_at":"2025-05-10T00:33:15Z","title":"Learning from the Good Ones: Risk Profiling-Based Defenses Against Evasion Attacks on DNNs","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-15T22:45:34.155401Z"},"links":{"citing_paper":"/paper/2505.06477"},"observation_digest":"sha256:3f3e8b352d0552a6f529b576a8d7e09c1a4874a6e718bd1f7aec317781d95e0c","observation_id":"998f4dd0-95f9-4072-8b0c-60ad643e089e","resolution":{"observed_at":"2026-08-15T22:45:34.975610Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:45:34.960374Z","title":"Deep reinforcement learning based evasion generative adversarial network for botnet detection.Future Generation Computer Systems , 150:294–302, 2024","venue":null,"work_id":"78a4043f-956f-43af-ae18-28dd93e074fd","year":2024},"citing_paper":{"arxiv_id":"2505.06477","last_updated":"2025-05-10T00:33:15Z","snapshot_observed_at":"2026-08-19T20:55:22.611592Z","submitted_at":"2025-05-10T00:33:15Z","title":"Learning from the Good Ones: Risk Profiling-Based Defenses Against Evasion Attacks on DNNs","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-15T22:45:34.158812Z"},"links":{"citing_paper":"/paper/2505.06477"},"observation_digest":"sha256:b20de7ba6dad8b96fc4ea87d49cfe7b48194eb2af86f6539a922eb0dabd94fc0","observation_id":"04e9e98a-8a22-44b9-99b2-a0ae878bba09","resolution":{"observed_at":"2026-08-15T22:45:34.964549Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:45:34.948542Z","title":"Strengthening ids against evasion attacks with gan-based adversarial samples in sdn-enabled network","venue":null,"work_id":"13b3327f-0dc7-4aa8-b099-58c27a327c21","year":2021},"citing_paper":{"arxiv_id":"2505.06477","last_updated":"2025-05-10T00:33:15Z","snapshot_observed_at":"2026-08-19T20:55:22.611592Z","submitted_at":"2025-05-10T00:33:15Z","title":"Learning from the Good Ones: Risk Profiling-Based Defenses Against Evasion Attacks on DNNs","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-15T22:45:34.163172Z"},"links":{"citing_paper":"/paper/2505.06477"},"observation_digest":"sha256:bdf866a8d33e10f11fb9ce1b93386dac69eaec3c08039c6c907da8a44fd9447f","observation_id":"454a602e-ef79-41c8-9948-280db67d3027","resolution":{"observed_at":"2026-08-15T22:45:34.952459Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:45:34.937136Z","title":"Omni: Au- tomated ensemble with unexpected models against adversarial evasion attack","venue":null,"work_id":"c9107a6a-dd36-4648-8131-7856aa5bb7e6","year":2022},"citing_paper":{"arxiv_id":"2505.06477","last_updated":"2025-05-10T00:33:15Z","snapshot_observed_at":"2026-08-19T20:55:22.611592Z","submitted_at":"2025-05-10T00:33:15Z","title":"Learning from the Good Ones: Risk Profiling-Based Defenses Against Evasion Attacks on DNNs","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-15T22:45:34.166829Z"},"links":{"citing_paper":"/paper/2505.06477"},"observation_digest":"sha256:9a783af7f0449b262500cb7d22e22111859fa32f6891d393f40b300fb7ae6625","observation_id":"6903c398-ff97-4eb1-a463-cd1c9fe33357","resolution":{"observed_at":"2026-08-15T22:45:34.941074Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:45:34.925765Z","title":"Clustering and ensemble based approach for securing electricity theft detectors against evasion attacks","venue":null,"work_id":"c6c003ee-2ec9-4591-aee7-b0fbaf2ce455","year":2023},"citing_paper":{"arxiv_id":"2505.06477","last_updated":"2025-05-10T00:33:15Z","snapshot_observed_at":"2026-08-19T20:55:22.611592Z","submitted_at":"2025-05-10T00:33:15Z","title":"Learning from the Good Ones: Risk Profiling-Based Defenses Against Evasion Attacks on DNNs","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-15T22:45:34.170300Z"},"links":{"citing_paper":"/paper/2505.06477"},"observation_digest":"sha256:1825197e2cffe2c6d22dda5c26bba428c7ed93280026066924b9667677702355","observation_id":"1bd25fce-bf90-46ca-a8a6-b2bfe04259c1","resolution":{"observed_at":"2026-08-15T22:45:34.929475Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:45:34.914560Z","title":"Mitigating adversarial evasion attacks of ransomware using ensemble learning","venue":null,"work_id":"cdad401d-5af5-417d-b1ae-4e24b00c167b","year":2022},"citing_paper":{"arxiv_id":"2505.06477","last_updated":"2025-05-10T00:33:15Z","snapshot_observed_at":"2026-08-19T20:55:22.611592Z","submitted_at":"2025-05-10T00:33:15Z","title":"Learning from the Good Ones: Risk Profiling-Based Defenses Against Evasion Attacks on DNNs","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-15T22:45:34.174419Z"},"links":{"citing_paper":"/paper/2505.06477"},"observation_digest":"sha256:5ff5a93163bd904b44afd7b3bdfa93903eed816205023f44d4cc38b98b6f2100","observation_id":"fe6b9039-4d7b-4b1d-b25f-46cc0cfebed8","resolution":{"observed_at":"2026-08-15T22:45:34.918180Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:45:34.902484Z","title":"Evasion attack and defense on machine learn- ing models in cyber-physical systems: A survey","venue":null,"work_id":"47e8972e-add4-44c1-8299-9bc610df1eb4","year":2023},"citing_paper":{"arxiv_id":"2505.06477","last_updated":"2025-05-10T00:33:15Z","snapshot_observed_at":"2026-08-19T20:55:22.611592Z","submitted_at":"2025-05-10T00:33:15Z","title":"Learning from the Good Ones: Risk Profiling-Based Defenses Against Evasion Attacks on DNNs","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-15T22:45:34.178015Z"},"links":{"citing_paper":"/paper/2505.06477"},"observation_digest":"sha256:551745c89e58004cff4635dd0fa0851e1f5ea3cf49a39e6f659e27f910f20c64","observation_id":"dd73cc38-0e90-44ba-8cb7-f204c9a75179","resolution":{"observed_at":"2026-08-15T22:45:34.906939Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2303.06302","last_updated":"2023-03-11T04:19:31Z","snapshot_observed_at":"2026-08-16T15:49:04.806658Z","submitted_at":"2023-03-11T04:19:31Z","title":"Adversarial Attacks and Defenses in Machine Learning-Powered Networks: A Contemporary Survey","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.06302","snapshot_observed_at":"2026-08-15T22:45:34.181672Z","title":"Adversarial attacks and defenses in machine learning-powered networks: A contemporary survey","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.06477","last_updated":"2025-05-10T00:33:15Z","snapshot_observed_at":"2026-08-19T20:55:22.611592Z","submitted_at":"2025-05-10T00:33:15Z","title":"Learning from the Good Ones: Risk Profiling-Based Defenses Against Evasion Attacks on DNNs","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-15T22:45:34.181672Z"},"links":{"cited_paper":"/paper/2303.06302","citing_paper":"/paper/2505.06477"},"observation_digest":"sha256:e2a40b155437e679f55b498439cab832c906dbfa7429e93386d3a9b6ea2a952e","observation_id":"2146dcd4-c8c5-412a-a863-211e5f393f3a","resolution":{"observed_at":"2026-08-15T22:45:34.181672Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:45:34.185814Z","title":"Evaluating the adversarial robustness of adaptive test-time defenses","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.06477","last_updated":"2025-05-10T00:33:15Z","snapshot_observed_at":"2026-08-19T20:55:22.611592Z","submitted_at":"2025-05-10T00:33:15Z","title":"Learning from the Good Ones: Risk Profiling-Based Defenses Against Evasion Attacks on DNNs","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-15T22:45:34.185814Z"},"links":{"citing_paper":"/paper/2505.06477"},"observation_digest":"sha256:72c1ec964c4181c63c510db4877577db3ca75a9fa4c31d93139df7a18000d1f9","observation_id":"80a63ff6-a492-4c65-94d5-91957f96ca58","resolution":{"observed_at":"2026-08-15T22:45:34.185814Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:45:34.882892Z","title":"Adversarial attacks to machine learning-based smart healthcare systems","venue":null,"work_id":"f625b488-91d5-496a-a71b-0aa852b65458","year":2020},"citing_paper":{"arxiv_id":"2505.06477","last_updated":"2025-05-10T00:33:15Z","snapshot_observed_at":"2026-08-19T20:55:22.611592Z","submitted_at":"2025-05-10T00:33:15Z","title":"Learning from the Good Ones: Risk Profiling-Based Defenses Against Evasion Attacks on DNNs","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-15T22:45:34.189645Z"},"links":{"citing_paper":"/paper/2505.06477"},"observation_digest":"sha256:5d0c2ab997bad325dfefc6694cbb0c04e3c3dfdcdfeb0ecf2f5c3e899281d861","observation_id":"a7d1128a-534c-4fbf-ae6d-6115ed0385d2","resolution":{"observed_at":"2026-08-15T22:45:34.887898Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:45:34.871168Z","title":null,"venue":null,"work_id":"84a2e7c1-c17c-4014-a727-00174e587fb0","year":2021},"citing_paper":{"arxiv_id":"2505.06477","last_updated":"2025-05-10T00:33:15Z","snapshot_observed_at":"2026-08-19T20:55:22.611592Z","submitted_at":"2025-05-10T00:33:15Z","title":"Learning from the Good Ones: Risk Profiling-Based Defenses Against Evasion Attacks on DNNs","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-15T22:45:34.193145Z"},"links":{"citing_paper":"/paper/2505.06477"},"observation_digest":"sha256:1a5a121f6030a08960d99d4365a1699b7cca09d26560057228026708dadc6442","observation_id":"e5ab6420-aeca-469d-8fe1-7e0db74f54e5","resolution":{"observed_at":"2026-08-15T22:45:34.874865Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2106.07925","last_updated":"2021-06-15T07:27:39Z","snapshot_observed_at":"2026-08-16T18:17:06.574057Z","submitted_at":"2021-06-15T07:27:39Z","title":"Machine Learning with Electronic Health Records is vulnerable to Backdoor Trigger Attacks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2106.07925","snapshot_observed_at":"2026-08-15T22:45:34.196559Z","title":"Machine learning with electronic health records is vulnerable to backdoor trigger attacks","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.06477","last_updated":"2025-05-10T00:33:15Z","snapshot_observed_at":"2026-08-19T20:55:22.611592Z","submitted_at":"2025-05-10T00:33:15Z","title":"Learning from the Good Ones: Risk Profiling-Based Defenses Against Evasion Attacks on DNNs","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-15T22:45:34.196559Z"},"links":{"cited_paper":"/paper/2106.07925","citing_paper":"/paper/2505.06477"},"observation_digest":"sha256:672dc4bd81319a63b5f89531633ba61aaa0e13a76ca2816d6a5c509bb7388a4b","observation_id":"7e49f74c-f71d-4677-af6b-539d2aada85c","resolution":{"observed_at":"2026-08-15T22:45:34.196559Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:45:34.858742Z","title":"Dealing with noise problem in machine learning data-sets: A systematic review","venue":null,"work_id":"eeb90786-1c54-4017-a882-c2d5e6470890","year":2019},"citing_paper":{"arxiv_id":"2505.06477","last_updated":"2025-05-10T00:33:15Z","snapshot_observed_at":"2026-08-19T20:55:22.611592Z","submitted_at":"2025-05-10T00:33:15Z","title":"Learning from the Good Ones: Risk Profiling-Based Defenses Against Evasion Attacks on DNNs","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-15T22:45:34.200533Z"},"links":{"citing_paper":"/paper/2505.06477"},"observation_digest":"sha256:20a45ae72e46720401b8c280dae72b2c930f948bd5b559ccce1a0d0d1eb28789","observation_id":"15babfb5-d3cf-4e0b-aa9c-4b50361709fb","resolution":{"observed_at":"2026-08-15T22:45:34.863217Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:45:34.846725Z","title":"Adversarial learning with cost-sensitive classes","venue":null,"work_id":"37107210-d7c4-4fd0-83a6-71d4a379012c","year":2022},"citing_paper":{"arxiv_id":"2505.06477","last_updated":"2025-05-10T00:33:15Z","snapshot_observed_at":"2026-08-19T20:55:22.611592Z","submitted_at":"2025-05-10T00:33:15Z","title":"Learning from the Good Ones: Risk Profiling-Based Defenses Against Evasion Attacks on DNNs","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-15T22:45:34.203868Z"},"links":{"citing_paper":"/paper/2505.06477"},"observation_digest":"sha256:f3bb248f4a868eb6fb8e297aca0b48eaacdeece4d78c6eda1a17bb5a75c61daf","observation_id":"b8a8ef91-61bd-4848-ac6b-83e0d9daf66c","resolution":{"observed_at":"2026-08-15T22:45:34.851089Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:45:34.834762Z","title":"Adversarial training for privacy-preserving deep learning model distribution","venue":null,"work_id":"46d54dbf-2315-4b06-8c0b-4bb0d8a73980","year":2019},"citing_paper":{"arxiv_id":"2505.06477","last_updated":"2025-05-10T00:33:15Z","snapshot_observed_at":"2026-08-19T20:55:22.611592Z","submitted_at":"2025-05-10T00:33:15Z","title":"Learning from the Good Ones: Risk Profiling-Based Defenses Against Evasion Attacks on DNNs","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-15T22:45:34.207236Z"},"links":{"citing_paper":"/paper/2505.06477"},"observation_digest":"sha256:33ae4e4d113d430cf6ae5136f0559a52ab2284552dfb4468aefb3f5d8a2fe466","observation_id":"0383ee49-fff2-481a-aba1-4fc0768c2120","resolution":{"observed_at":"2026-08-15T22:45:34.838727Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2012.13573","last_updated":"2020-12-25T13:35:02Z","snapshot_observed_at":"2026-08-16T18:56:01.679944Z","submitted_at":"2020-12-25T13:35:02Z","title":"Robustness, Privacy, and Generalization of Adversarial Training","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2012.13573","snapshot_observed_at":"2026-08-15T22:45:34.210789Z","title":"Robust- ness, privacy, and generalization of adversarial training","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2505.06477","last_updated":"2025-05-10T00:33:15Z","snapshot_observed_at":"2026-08-19T20:55:22.611592Z","submitted_at":"2025-05-10T00:33:15Z","title":"Learning from the Good Ones: Risk Profiling-Based Defenses Against Evasion Attacks on DNNs","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-15T22:45:34.210789Z"},"links":{"cited_paper":"/paper/2012.13573","citing_paper":"/paper/2505.06477"},"observation_digest":"sha256:46a510eccca1a897e1c36fbbdc6769af344fe76d73e3779590b65c1fb3fff52d","observation_id":"579ab869-79db-4238-b200-ce4bb8a178f7","resolution":{"observed_at":"2026-08-15T22:45:34.210789Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:45:34.823292Z","title":"The ohiot1dm dataset for blood glucose level prediction: Update 2020","venue":null,"work_id":"ac5ab3a6-273a-4354-907f-4aaa6f1b6bb7","year":2020},"citing_paper":{"arxiv_id":"2505.06477","last_updated":"2025-05-10T00:33:15Z","snapshot_observed_at":"2026-08-19T20:55:22.611592Z","submitted_at":"2025-05-10T00:33:15Z","title":"Learning from the Good Ones: Risk Profiling-Based Defenses Against Evasion Attacks on DNNs","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-15T22:45:34.214758Z"},"links":{"citing_paper":"/paper/2505.06477"},"observation_digest":"sha256:ac10bb7d3f1192c0e64b570414265de66c67aeeedc36564e4f4da12b12d8c6a8","observation_id":"40b225da-0308-447d-80b0-780eb0746bac","resolution":{"observed_at":"2026-08-15T22:45:34.827270Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:45:34.811293Z","title":"Deep Residual Time- Series Forecasting: Application to Blood Glucose Prediction","venue":null,"work_id":"b02460af-ce04-4131-bfe5-5c0ee898fa8a","year":2020},"citing_paper":{"arxiv_id":"2505.06477","last_updated":"2025-05-10T00:33:15Z","snapshot_observed_at":"2026-08-19T20:55:22.611592Z","submitted_at":"2025-05-10T00:33:15Z","title":"Learning from the Good Ones: Risk Profiling-Based Defenses Against Evasion Attacks on DNNs","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-15T22:45:34.218255Z"},"links":{"citing_paper":"/paper/2505.06477"},"observation_digest":"sha256:e0dd7b9ac1ef7a0f9bc8328b3a47800ecc0e35519989078d0c21442798ae68f3","observation_id":"8969911f-0d21-46ac-bc58-fd3a99065fa8","resolution":{"observed_at":"2026-08-15T22:45:34.815993Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2401.17136","last_updated":"2024-04-12T00:33:58Z","snapshot_observed_at":"2026-08-16T14:23:11.620450Z","submitted_at":"2024-01-30T16:15:55Z","title":"Systematically Assessing the Security Risks of AI/ML-enabled Connected Healthcare Systems","version":2},"cited_work":{"arxiv_id":"2401.17136","doi":null,"metadata_source":"pith","pith_arxiv_id":"2401.17136","snapshot_observed_at":"2026-08-15T22:45:34.483865Z","title":"Systematically Assessing the Security Risks of AI/ML-enabled Connected Healthcare Systems","venue":"cs.CR","work_id":"bce7a5dc-151d-441b-b3b2-fbdaa55be391","year":2024},"citing_paper":{"arxiv_id":"2505.06477","last_updated":"2025-05-10T00:33:15Z","snapshot_observed_at":"2026-08-19T20:55:22.611592Z","submitted_at":"2025-05-10T00:33:15Z","title":"Learning from the Good Ones: Risk Profiling-Based Defenses Against Evasion Attacks on DNNs","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-15T22:45:34.222150Z"},"links":{"cited_paper":"/paper/2401.17136","citing_paper":"/paper/2505.06477"},"observation_digest":"sha256:91a2237cd2ce0a83213bb620b9f1e3d0c43810f76234b0074d3809853d1ac437","observation_id":"73c5c0c9-fae2-4fba-ab12-d0e35c4676fa","resolution":{"observed_at":"2026-08-15T22:45:34.490471Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:45:34.799671Z","title":"BLURtooth: Exploiting Cross- Transport Key Derivation in Bluetooth Classic and Bluetooth Low Energy","venue":null,"work_id":"f82b7287-fc66-4570-b959-a3fd9ae80b5a","year":2022},"citing_paper":{"arxiv_id":"2505.06477","last_updated":"2025-05-10T00:33:15Z","snapshot_observed_at":"2026-08-19T20:55:22.611592Z","submitted_at":"2025-05-10T00:33:15Z","title":"Learning from the Good Ones: Risk Profiling-Based Defenses Against Evasion Attacks on DNNs","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-15T22:45:34.225791Z"},"links":{"citing_paper":"/paper/2505.06477"},"observation_digest":"sha256:3d65d8b944374037ee9de2e24249da7c5853d0bb995408acbc11393f318f574a","observation_id":"720dedac-1241-4c09-984a-04951caea913","resolution":{"observed_at":"2026-08-15T22:45:34.803438Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:45:34.788257Z","title":"Medtronic MyCareLink Smart Vulnerability","venue":null,"work_id":"0c32ee76-e35b-482b-8e17-9ffb68b3a36b","year":2020},"citing_paper":{"arxiv_id":"2505.06477","last_updated":"2025-05-10T00:33:15Z","snapshot_observed_at":"2026-08-19T20:55:22.611592Z","submitted_at":"2025-05-10T00:33:15Z","title":"Learning from the Good Ones: Risk Profiling-Based Defenses Against Evasion Attacks on DNNs","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-15T22:45:34.229205Z"},"links":{"citing_paper":"/paper/2505.06477"},"observation_digest":"sha256:7c248474eda536f55ad95ae3e22ca7fc0e4d0ba8a74e3c30ed5e592e8e7cb83d","observation_id":"aa0a9bbf-48af-40bc-89f7-0f4085c9f524","resolution":{"observed_at":"2026-08-15T22:45:34.792082Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:45:34.232957Z","title":"Securing automated insulin delivery systems: A review of security threats and protectives strategies","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2505.06477","last_updated":"2025-05-10T00:33:15Z","snapshot_observed_at":"2026-08-19T20:55:22.611592Z","submitted_at":"2025-05-10T00:33:15Z","title":"Learning from the Good Ones: Risk Profiling-Based Defenses Against Evasion Attacks on DNNs","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-15T22:45:34.232957Z"},"links":{"citing_paper":"/paper/2505.06477"},"observation_digest":"sha256:39254f047cb9b55c1e11b012d80e1f31a64504860770d30036ec4aabb5150d55","observation_id":"74403d03-6778-4812-a2a9-593b7b6a5047","resolution":{"observed_at":"2026-08-15T22:45:34.232957Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:45:34.776791Z","title":"Com- partmentation policies for android apps: A combinatorial optimization approach","venue":null,"work_id":"7858864a-0f5c-452f-8e2e-efe2d7fb49a7","year":2015},"citing_paper":{"arxiv_id":"2505.06477","last_updated":"2025-05-10T00:33:15Z","snapshot_observed_at":"2026-08-19T20:55:22.611592Z","submitted_at":"2025-05-10T00:33:15Z","title":"Learning from the Good Ones: Risk Profiling-Based Defenses Against Evasion Attacks on DNNs","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-15T22:45:34.236438Z"},"links":{"citing_paper":"/paper/2505.06477"},"observation_digest":"sha256:782dedba1e844eb93d2ee46b3078cd1e22ea4eb86c7b48342e2bed2f57dd78d7","observation_id":"996737a9-418a-4593-aa97-ecc90dec1b17","resolution":{"observed_at":"2026-08-15T22:45:34.780854Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:45:34.766378Z","title":null,"venue":null,"work_id":"3878b36c-6f85-481c-9b14-f28a50cd3fad","year":2023},"citing_paper":{"arxiv_id":"2505.06477","last_updated":"2025-05-10T00:33:15Z","snapshot_observed_at":"2026-08-19T20:55:22.611592Z","submitted_at":"2025-05-10T00:33:15Z","title":"Learning from the Good Ones: Risk Profiling-Based Defenses Against Evasion Attacks on DNNs","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-15T22:45:34.240027Z"},"links":{"citing_paper":"/paper/2505.06477"},"observation_digest":"sha256:8fb7f6639f73f09b96e652bca55917a535d8950b5c972b10b22c2e7a0973e5ae","observation_id":"8ea88c53-489b-4216-8084-454c501f6e71","resolution":{"observed_at":"2026-08-15T22:45:34.769852Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:45:34.754627Z","title":"URET: Universal Robustness Evaluation Toolkit (for Evasion)","venue":null,"work_id":"7960c41f-7302-4f02-9111-6649d4a5b4fd","year":2023},"citing_paper":{"arxiv_id":"2505.06477","last_updated":"2025-05-10T00:33:15Z","snapshot_observed_at":"2026-08-19T20:55:22.611592Z","submitted_at":"2025-05-10T00:33:15Z","title":"Learning from the Good Ones: Risk Profiling-Based Defenses Against Evasion Attacks on DNNs","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-15T22:45:34.243405Z"},"links":{"citing_paper":"/paper/2505.06477"},"observation_digest":"sha256:3326c2a460de6be61bdb93eec0c73f35931d4d825719fe424d91ff1c53789c6c","observation_id":"60068f3a-fa61-40a5-aa0c-41301ca8dd01","resolution":{"observed_at":"2026-08-15T22:45:34.759034Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:45:34.743413Z","title":"A review of anomaly detection techniques based on nearest neighbor","venue":null,"work_id":"52aab547-dc20-41fc-8813-e4c234c8f69b","year":2018},"citing_paper":{"arxiv_id":"2505.06477","last_updated":"2025-05-10T00:33:15Z","snapshot_observed_at":"2026-08-19T20:55:22.611592Z","submitted_at":"2025-05-10T00:33:15Z","title":"Learning from the Good Ones: Risk Profiling-Based Defenses Against Evasion Attacks on DNNs","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-15T22:45:34.246899Z"},"links":{"citing_paper":"/paper/2505.06477"},"observation_digest":"sha256:ab1c821521c94639ad81279d6ffc8d593322417b3992b7e69b0576e421a97245","observation_id":"bb472c50-6ee6-4712-891f-93bc0809935d","resolution":{"observed_at":"2026-08-15T22:45:34.747280Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:45:34.732314Z","title":"Sparse coding with anomaly detection","venue":null,"work_id":"ebe41e88-1e5d-474c-ab6f-b1b0e438f366","year":2015},"citing_paper":{"arxiv_id":"2505.06477","last_updated":"2025-05-10T00:33:15Z","snapshot_observed_at":"2026-08-19T20:55:22.611592Z","submitted_at":"2025-05-10T00:33:15Z","title":"Learning from the Good Ones: Risk Profiling-Based Defenses Against Evasion Attacks on DNNs","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-15T22:45:34.250380Z"},"links":{"citing_paper":"/paper/2505.06477"},"observation_digest":"sha256:7511dc90029de71750c3eb4763a1f5d4cc905f456d8fd420195ab74ff1ab907f","observation_id":"267f2dce-a048-4b73-b7c3-950ac86f2c53","resolution":{"observed_at":"2026-08-15T22:45:34.736134Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:45:34.720586Z","title":"Detection and explanation of anomalies in healthcare data","venue":null,"work_id":"cf8dacd9-6a89-4a4c-8c4a-0f7bef1f665e","year":2023},"citing_paper":{"arxiv_id":"2505.06477","last_updated":"2025-05-10T00:33:15Z","snapshot_observed_at":"2026-08-19T20:55:22.611592Z","submitted_at":"2025-05-10T00:33:15Z","title":"Learning from the Good Ones: Risk Profiling-Based Defenses Against Evasion Attacks on DNNs","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-15T22:45:34.254403Z"},"links":{"citing_paper":"/paper/2505.06477"},"observation_digest":"sha256:5cc469e81a39e1546d4d45d472c43d9adfc038f16828a8d8a6076279723bcbd4","observation_id":"8324c582-7983-47fa-a8b3-b04bb2564616","resolution":{"observed_at":"2026-08-15T22:45:34.724436Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:45:34.708918Z","title":"Sparsity techniques in medical imaging","venue":null,"work_id":"e476d7be-d88b-4898-9c6c-70d93a5562cf","year":2015},"citing_paper":{"arxiv_id":"2505.06477","last_updated":"2025-05-10T00:33:15Z","snapshot_observed_at":"2026-08-19T20:55:22.611592Z","submitted_at":"2025-05-10T00:33:15Z","title":"Learning from the Good Ones: Risk Profiling-Based Defenses Against Evasion Attacks on DNNs","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-15T22:45:34.258001Z"},"links":{"citing_paper":"/paper/2505.06477"},"observation_digest":"sha256:e67c32de962bb235b02a30c11138779ccce928a9ea1c564490047c68d817d9e7","observation_id":"21d78e3d-0606-45f2-9664-197a0c821d59","resolution":{"observed_at":"2026-08-15T22:45:34.712698Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:45:34.696794Z","title":"Improv- ing one-class svm for anomaly detection","venue":null,"work_id":"ed28a48b-35fd-4520-b007-fecb3670e8f5","year":2003},"citing_paper":{"arxiv_id":"2505.06477","last_updated":"2025-05-10T00:33:15Z","snapshot_observed_at":"2026-08-19T20:55:22.611592Z","submitted_at":"2025-05-10T00:33:15Z","title":"Learning from the Good Ones: Risk Profiling-Based Defenses Against Evasion Attacks on DNNs","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-15T22:45:34.261990Z"},"links":{"citing_paper":"/paper/2505.06477"},"observation_digest":"sha256:c3090f5b8132165201ef538ce86ed0a80030c41606b6be7ca57dad27568888f1","observation_id":"1e8b7bb8-9f27-4afe-8650-290888ebe519","resolution":{"observed_at":"2026-08-15T22:45:34.701662Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:45:34.684360Z","title":"Analyzing the non-linear relationship between fasting blood glucose levels and gensini score in patients with stemi","venue":null,"work_id":"32ebda7b-f5da-4f91-97c7-4fb9d8c01cb9","year":2024},"citing_paper":{"arxiv_id":"2505.06477","last_updated":"2025-05-10T00:33:15Z","snapshot_observed_at":"2026-08-19T20:55:22.611592Z","submitted_at":"2025-05-10T00:33:15Z","title":"Learning from the Good Ones: Risk Profiling-Based Defenses Against Evasion Attacks on DNNs","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-15T22:45:34.265870Z"},"links":{"citing_paper":"/paper/2505.06477"},"observation_digest":"sha256:6932c84191e7317c8e01f37800979ab9674f6a7f17a451e461f2a68d6c126ae2","observation_id":"c478788b-b3a6-472f-acbe-9f358e8478f6","resolution":{"observed_at":"2026-08-15T22:45:34.688816Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:45:34.672158Z","title":"Nonlinear metabolic effect of insulin across the blood glucose range in patients with type 1 diabetes mellitus","venue":null,"work_id":"023a9c0e-118e-419b-bbef-2ef4d78f9ff0","year":2010},"citing_paper":{"arxiv_id":"2505.06477","last_updated":"2025-05-10T00:33:15Z","snapshot_observed_at":"2026-08-19T20:55:22.611592Z","submitted_at":"2025-05-10T00:33:15Z","title":"Learning from the Good Ones: Risk Profiling-Based Defenses Against Evasion Attacks on DNNs","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-15T22:45:34.269509Z"},"links":{"citing_paper":"/paper/2505.06477"},"observation_digest":"sha256:19dbd172a586e91839aba50663ebc991d9a7d6f1fe954b153e76b35f78d80555","observation_id":"9c81e759-7354-4293-9fc5-6be01e196045","resolution":{"observed_at":"2026-08-15T22:45:34.676409Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:45:34.660308Z","title":"Somogyi effect: What it is, causes, symp- toms & treatment","venue":null,"work_id":"647f8120-cec5-4b10-80c9-ad16feaa43f3","year":2023},"citing_paper":{"arxiv_id":"2505.06477","last_updated":"2025-05-10T00:33:15Z","snapshot_observed_at":"2026-08-19T20:55:22.611592Z","submitted_at":"2025-05-10T00:33:15Z","title":"Learning from the Good Ones: Risk Profiling-Based Defenses Against Evasion Attacks on DNNs","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-15T22:45:34.273305Z"},"links":{"citing_paper":"/paper/2505.06477"},"observation_digest":"sha256:41c842879e1957c3bfbb2d72003b6e3a133b7dd2633833b283bde2bc1f75e75d","observation_id":"013cbeb9-48bc-4381-8c5b-b59c7c5b600f","resolution":{"observed_at":"2026-08-15T22:45:34.664515Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:45:34.647703Z","title":"Hypoglycemia","venue":null,"work_id":"3cd05837-fd05-4e90-a651-cc49c48f6621","year":2018},"citing_paper":{"arxiv_id":"2505.06477","last_updated":"2025-05-10T00:33:15Z","snapshot_observed_at":"2026-08-19T20:55:22.611592Z","submitted_at":"2025-05-10T00:33:15Z","title":"Learning from the Good Ones: Risk Profiling-Based Defenses Against Evasion Attacks on DNNs","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-15T22:45:34.277417Z"},"links":{"citing_paper":"/paper/2505.06477"},"observation_digest":"sha256:d7f5057aab41babc5828f99bffb5e59a575d5fd3599db1185e01144c9c308fae","observation_id":"927e152d-4f89-4d82-8a3a-8c8441fe398c","resolution":{"observed_at":"2026-08-15T22:45:34.652044Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:45:34.634659Z","title":null,"venue":null,"work_id":"822d922d-b235-443d-b234-d21eb44f265c","year":null},"citing_paper":{"arxiv_id":"2505.06477","last_updated":"2025-05-10T00:33:15Z","snapshot_observed_at":"2026-08-19T20:55:22.611592Z","submitted_at":"2025-05-10T00:33:15Z","title":"Learning from the Good Ones: Risk Profiling-Based Defenses Against Evasion Attacks on DNNs","version":1},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-15T22:45:34.280995Z"},"links":{"citing_paper":"/paper/2505.06477"},"observation_digest":"sha256:f7b518173f116911c13ecc0b1c7b6bb71edc5f6e4b83b43a074b2458ec45e5cc","observation_id":"cb10025c-3b41-411b-b3d3-1cd8f4ea487c","resolution":{"observed_at":"2026-08-15T22:45:34.638383Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:45:34.621980Z","title":"Hypoglycemia (low blood sugar), February 2024","venue":null,"work_id":"6b464c3b-1eef-40cb-a251-7ba4e8ed4158","year":2024},"citing_paper":{"arxiv_id":"2505.06477","last_updated":"2025-05-10T00:33:15Z","snapshot_observed_at":"2026-08-19T20:55:22.611592Z","submitted_at":"2025-05-10T00:33:15Z","title":"Learning from the Good Ones: Risk Profiling-Based Defenses Against Evasion Attacks on DNNs","version":1},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-15T22:45:34.284512Z"},"links":{"citing_paper":"/paper/2505.06477"},"observation_digest":"sha256:68bf545ce50fe75958f898887ecb34689fc9f742ae389afc56c516145104aca3","observation_id":"e16dcb51-3e1d-45e7-ad53-fc4c07a3b53e","resolution":{"observed_at":"2026-08-15T22:45:34.626052Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:45:34.609135Z","title":"What is hierarchical clustering?, August 2024","venue":null,"work_id":"6430565d-763c-4f74-839d-6bdbb2e91057","year":2024},"citing_paper":{"arxiv_id":"2505.06477","last_updated":"2025-05-10T00:33:15Z","snapshot_observed_at":"2026-08-19T20:55:22.611592Z","submitted_at":"2025-05-10T00:33:15Z","title":"Learning from the Good Ones: Risk Profiling-Based Defenses Against Evasion Attacks on DNNs","version":1},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-15T22:45:34.287923Z"},"links":{"citing_paper":"/paper/2505.06477"},"observation_digest":"sha256:a0f46cbe0da22202cb8dc397a59ce139f5dd2aaa5b765901b083b326cfb743b1","observation_id":"149b552c-bf11-4b92-8d38-c94a94684021","resolution":{"observed_at":"2026-08-15T22:45:34.613530Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:45:34.596589Z","title":"Patient i","venue":null,"work_id":"8bfff3d8-d3a1-452f-9512-34017baf97e2","year":2022},"citing_paper":{"arxiv_id":"2505.06477","last_updated":"2025-05-10T00:33:15Z","snapshot_observed_at":"2026-08-19T20:55:22.611592Z","submitted_at":"2025-05-10T00:33:15Z","title":"Learning from the Good Ones: Risk Profiling-Based Defenses Against Evasion Attacks on DNNs","version":1},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-15T22:45:34.291934Z"},"links":{"citing_paper":"/paper/2505.06477"},"observation_digest":"sha256:f8ec6296cea0df3c608e124753152c2ef0fd8fe9f7eb2cc16a1fccc79c2b4f76","observation_id":"777d55d9-563f-4b22-b09d-3b41ac72d596","resolution":{"observed_at":"2026-08-15T22:45:34.601008Z","resolver_source":"raw_fallback","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2505.06477","last_updated":"2025-05-10T00:33:15Z","latest_version":1,"primary_category":"cs.CR","snapshot_observed_at":"2026-08-19T20:55:22.611592Z","submitted_at":"2025-05-10T00:33:15Z","title":"Learning from the Good Ones: Risk Profiling-Based Defenses Against Evasion Attacks on DNNs"},"reference_resolution":{"displayed":68,"state_counts":{"malformed_identifier":1,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":12,"verified_exact":2,"verified_fuzzy":53},"total_outbound_references":68},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"thesis":"As of 19 August 2026, this Paper Citation Record lists 68 of 68 outbound references and 0 inbound Pith citation observations for arXiv:2505.06477."}