{"as_of":"2026-08-23T01:28:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:370c2c1c7613b98d7ab16efaff62056731b8eadd526a3e40709c2d3c5f169aa3","coverage":[{"denominator":47,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":47,"source":"paper_references, paper_reference_links","source_observed_at":"2026-06-25T21:09:23.769302Z","state":"measured"},{"denominator":47,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":47,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-22T06:32:14.747728+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/2606.25589/citation-record","integrity":"/paper/2606.25589/integrity","json":"/paper/2606.25589/citation-record.json","paper":"/paper/2606.25589"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-25T21:09:23.769302Z","title":"Graph convolutional networks: a comprehensive review,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2606.25589","last_updated":"2026-06-24T08:59:28Z","snapshot_observed_at":"2026-08-16T20:59:57.458007Z","submitted_at":"2026-06-24T08:59:28Z","title":"Leaking Circuit Secrets: Gradient Leakage Attacks on Graph Neural Networks","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-06-25T21:09:23.769302Z"},"links":{"citing_paper":"/paper/2606.25589"},"observation_digest":"sha256:babeb5dfe27c7120018fc289b483624b60e26a1a14a8798240e61cf74ca5bd2a","observation_id":"277b31e0-b03a-42fc-b821-cebd104110fa","resolution":{"observed_at":"2026-06-25T21:09:23.769302Z","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":"2026-06-25T21:09:23.769302Z","title":"Benchmarking backdoor attacks on graph convolution neural networks: A comprehensive analysis of poisoning techniques,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2606.25589","last_updated":"2026-06-24T08:59:28Z","snapshot_observed_at":"2026-08-16T20:59:57.458007Z","submitted_at":"2026-06-24T08:59:28Z","title":"Leaking Circuit Secrets: Gradient Leakage Attacks on Graph Neural Networks","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-06-25T21:09:23.769302Z"},"links":{"citing_paper":"/paper/2606.25589"},"observation_digest":"sha256:d85dfa2b52432ae42592864c452186ac6c6411509877ba5ce0d0eebaa46559c0","observation_id":"be10a78d-8a51-4313-8e7c-c7e2ecf83854","resolution":{"observed_at":"2026-06-25T21:09:23.769302Z","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":"2026-06-25T21:09:23.769302Z","title":"Circuit-gnn: Graph neural networks for distributed circuit design,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2606.25589","last_updated":"2026-06-24T08:59:28Z","snapshot_observed_at":"2026-08-16T20:59:57.458007Z","submitted_at":"2026-06-24T08:59:28Z","title":"Leaking Circuit Secrets: Gradient Leakage Attacks on Graph Neural Networks","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-06-25T21:09:23.769302Z"},"links":{"citing_paper":"/paper/2606.25589"},"observation_digest":"sha256:3b1744b7038e6262b7bd5eb85e28f0abb0d1fc2e31f9af33887920b2604e3629","observation_id":"e130cf96-ff80-4828-bddb-9f35be1bf7c6","resolution":{"observed_at":"2026-06-25T21:09:23.769302Z","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":"2026-06-25T21:09:23.769302Z","title":"Gnn-based hierarchical annotation for analog circuits,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2606.25589","last_updated":"2026-06-24T08:59:28Z","snapshot_observed_at":"2026-08-16T20:59:57.458007Z","submitted_at":"2026-06-24T08:59:28Z","title":"Leaking Circuit Secrets: Gradient Leakage Attacks on Graph Neural Networks","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-06-25T21:09:23.769302Z"},"links":{"citing_paper":"/paper/2606.25589"},"observation_digest":"sha256:6f16ac479824caed119967aaf5301239caa1cc3c64472f04475a5da16130e41d","observation_id":"4571ee0d-4f5a-4d73-bb72-29db448d3c71","resolution":{"observed_at":"2026-06-25T21:09:23.769302Z","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":"2026-06-25T21:09:23.769302Z","title":"Graph of circuits with gnn for exploring the optimal design space,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2606.25589","last_updated":"2026-06-24T08:59:28Z","snapshot_observed_at":"2026-08-16T20:59:57.458007Z","submitted_at":"2026-06-24T08:59:28Z","title":"Leaking Circuit Secrets: Gradient Leakage Attacks on Graph Neural Networks","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-06-25T21:09:23.769302Z"},"links":{"citing_paper":"/paper/2606.25589"},"observation_digest":"sha256:d575f662fef900c535641a20c57a19ab4dee074b52513584c7545a3a13186553","observation_id":"367eeaf0-bb57-4299-8605-487891b7fca5","resolution":{"observed_at":"2026-06-25T21:09:23.769302Z","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":"2026-06-25T21:09:23.769302Z","title":"Trustworthy graph neural networks: Aspects, methods, and trends,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2606.25589","last_updated":"2026-06-24T08:59:28Z","snapshot_observed_at":"2026-08-16T20:59:57.458007Z","submitted_at":"2026-06-24T08:59:28Z","title":"Leaking Circuit Secrets: Gradient Leakage Attacks on Graph Neural Networks","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-06-25T21:09:23.769302Z"},"links":{"citing_paper":"/paper/2606.25589"},"observation_digest":"sha256:3cb661e5f865f4b70562c91b455bf0db01856022949908693d7937e2276f4da3","observation_id":"9b8e114b-8761-4935-b1f3-2bd4cca1900f","resolution":{"observed_at":"2026-06-25T21:09:23.769302Z","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":"2026-06-25T21:09:23.769302Z","title":"Poisonedgnn: Backdoor attack on graph neural networks-based hardware security systems,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2606.25589","last_updated":"2026-06-24T08:59:28Z","snapshot_observed_at":"2026-08-16T20:59:57.458007Z","submitted_at":"2026-06-24T08:59:28Z","title":"Leaking Circuit Secrets: Gradient Leakage Attacks on Graph Neural Networks","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-06-25T21:09:23.769302Z"},"links":{"citing_paper":"/paper/2606.25589"},"observation_digest":"sha256:1f7495284d1db5e89af8faa37ba0dc8b65ca1ccb89f2e0334cd975c547d4af40","observation_id":"158662fc-3b55-4576-b97a-1bb924e5e06e","resolution":{"observed_at":"2026-06-25T21:09:23.769302Z","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":"2026-06-25T21:09:23.769302Z","title":"Graph neural networks: a survey on the links between privacy and security,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2606.25589","last_updated":"2026-06-24T08:59:28Z","snapshot_observed_at":"2026-08-16T20:59:57.458007Z","submitted_at":"2026-06-24T08:59:28Z","title":"Leaking Circuit Secrets: Gradient Leakage Attacks on Graph Neural Networks","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-06-25T21:09:23.769302Z"},"links":{"citing_paper":"/paper/2606.25589"},"observation_digest":"sha256:3c74ac8bc799afc660550399a0ea66ea42ccc22dc4f68e22c29ba85d4996828a","observation_id":"5447d833-185f-4bf6-bb31-c50abdb4f0db","resolution":{"observed_at":"2026-06-25T21:09:23.769302Z","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":"2026-06-25T21:09:23.769302Z","title":"Deep leakage from gradients,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2606.25589","last_updated":"2026-06-24T08:59:28Z","snapshot_observed_at":"2026-08-16T20:59:57.458007Z","submitted_at":"2026-06-24T08:59:28Z","title":"Leaking Circuit Secrets: Gradient Leakage Attacks on Graph Neural Networks","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-06-25T21:09:23.769302Z"},"links":{"citing_paper":"/paper/2606.25589"},"observation_digest":"sha256:c7c183d0a6c3aff3b240a4ea5e4df930780c6918a88bccef466f2c1c97f34ac0","observation_id":"4479ea99-2f46-418e-82f9-87cefe809d6d","resolution":{"observed_at":"2026-06-25T21:09:23.769302Z","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":"2026-06-25T21:09:23.769302Z","title":"Gradient leakage attacks in federated learning,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2606.25589","last_updated":"2026-06-24T08:59:28Z","snapshot_observed_at":"2026-08-16T20:59:57.458007Z","submitted_at":"2026-06-24T08:59:28Z","title":"Leaking Circuit Secrets: Gradient Leakage Attacks on Graph Neural Networks","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-06-25T21:09:23.769302Z"},"links":{"citing_paper":"/paper/2606.25589"},"observation_digest":"sha256:2b291c41cfe795a8dc764beb3da8d1a5a3b714d8adb30b86fe96c81406e2e743","observation_id":"5d68786a-fc9c-4c22-ad48-4f71296ab7c0","resolution":{"observed_at":"2026-06-25T21:09:23.769302Z","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":"2026-06-25T21:09:23.769302Z","title":"Dropout is not all you need to prevent gradient leakage,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2606.25589","last_updated":"2026-06-24T08:59:28Z","snapshot_observed_at":"2026-08-16T20:59:57.458007Z","submitted_at":"2026-06-24T08:59:28Z","title":"Leaking Circuit Secrets: Gradient Leakage Attacks on Graph Neural Networks","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-06-25T21:09:23.769302Z"},"links":{"citing_paper":"/paper/2606.25589"},"observation_digest":"sha256:f6ab16b44107bc8bdaab8ca55c21fbaaa5187aac2400ce4e9a573949a5f007fc","observation_id":"f7e1be83-292d-4aa7-b758-0dfa57294d5b","resolution":{"observed_at":"2026-06-25T21:09:23.769302Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.04013","last_updated":"2024-09-11T01:09:07Z","snapshot_observed_at":"2026-08-16T14:21:00.628189Z","submitted_at":"2024-02-06T14:06:23Z","title":"Privacy Leakage on DNNs: A Survey of Model Inversion Attacks and Defenses","version":2},"cited_work":{"arxiv_id":"2402.04013","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2402.04013","snapshot_observed_at":"2026-07-04T19:40:06.648411Z","title":"Privacy leakage on dnns: A survey of model inversion attacks and defenses","venue":null,"work_id":"cf22a4ad-a59a-4d3b-bcef-afb905dbdc42","year":2024},"citing_paper":{"arxiv_id":"2606.25589","last_updated":"2026-06-24T08:59:28Z","snapshot_observed_at":"2026-08-16T20:59:57.458007Z","submitted_at":"2026-06-24T08:59:28Z","title":"Leaking Circuit Secrets: Gradient Leakage Attacks on Graph Neural Networks","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-06-25T21:09:23.769302Z"},"links":{"cited_paper":"/paper/2402.04013","citing_paper":"/paper/2606.25589"},"observation_digest":"sha256:0a539198808f03204177e35ad1ff7e240a507b2f40c86876ba7b70386dde969c","observation_id":"7eda2f04-5d04-44a4-b405-a7d9b9af63f6","resolution":{"observed_at":"2026-07-04T19:40:06.667431Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-06-25T21:09:23.769302Z","title":"Graphsage-based multi-path reliable routing algorithm for wireless mesh networks,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2606.25589","last_updated":"2026-06-24T08:59:28Z","snapshot_observed_at":"2026-08-16T20:59:57.458007Z","submitted_at":"2026-06-24T08:59:28Z","title":"Leaking Circuit Secrets: Gradient Leakage Attacks on Graph Neural Networks","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-06-25T21:09:23.769302Z"},"links":{"citing_paper":"/paper/2606.25589"},"observation_digest":"sha256:ecf4f2f9d552f04accc7dba55f0c1fd54d98a6a1151346486aed59d128e245c7","observation_id":"28737a1d-6a0b-4b63-a635-34ecae9c7f73","resolution":{"observed_at":"2026-06-25T21:09:23.769302Z","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":"2026-06-25T21:09:23.769302Z","title":"Omla: An oracle- less machine learning-based attack on logic locking,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2606.25589","last_updated":"2026-06-24T08:59:28Z","snapshot_observed_at":"2026-08-16T20:59:57.458007Z","submitted_at":"2026-06-24T08:59:28Z","title":"Leaking Circuit Secrets: Gradient Leakage Attacks on Graph Neural Networks","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-06-25T21:09:23.769302Z"},"links":{"citing_paper":"/paper/2606.25589"},"observation_digest":"sha256:ef1771f7fa21618015c96a76728cd53ee0d3b5dfcb14b1ffbc33b4b2c42d96d8","observation_id":"47c099bd-9013-4ab8-bba1-4987cdbd9840","resolution":{"observed_at":"2026-06-25T21:09:23.769302Z","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":"2026-06-25T21:09:23.769302Z","title":"Parsing netlists of integrated circuits from images via graph attention network,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2606.25589","last_updated":"2026-06-24T08:59:28Z","snapshot_observed_at":"2026-08-16T20:59:57.458007Z","submitted_at":"2026-06-24T08:59:28Z","title":"Leaking Circuit Secrets: Gradient Leakage Attacks on Graph Neural Networks","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-06-25T21:09:23.769302Z"},"links":{"citing_paper":"/paper/2606.25589"},"observation_digest":"sha256:323c5ede3671d0a80bde36ca7763e6f8cfd748955112bf442796da881d54d460","observation_id":"5411455f-5b20-47bb-990b-18d2bd42fce4","resolution":{"observed_at":"2026-06-25T21:09:23.769302Z","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":"2026-06-25T21:09:23.769302Z","title":"Trojansaint: Gate-level netlist sampling-based inductive learning for hardware trojan detection,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2606.25589","last_updated":"2026-06-24T08:59:28Z","snapshot_observed_at":"2026-08-16T20:59:57.458007Z","submitted_at":"2026-06-24T08:59:28Z","title":"Leaking Circuit Secrets: Gradient Leakage Attacks on Graph Neural Networks","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-06-25T21:09:23.769302Z"},"links":{"citing_paper":"/paper/2606.25589"},"observation_digest":"sha256:6ae82bd6a70fd04e4adb409521befead95c846c589b6ac985b99fc3a70c89861","observation_id":"2089d78e-a11a-44e6-b074-16d1b8571e55","resolution":{"observed_at":"2026-06-25T21:09:23.769302Z","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":"2026-06-25T21:09:23.769302Z","title":"Defense against adversarial attacks via controlling gradient leaking on embedded manifolds,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2606.25589","last_updated":"2026-06-24T08:59:28Z","snapshot_observed_at":"2026-08-16T20:59:57.458007Z","submitted_at":"2026-06-24T08:59:28Z","title":"Leaking Circuit Secrets: Gradient Leakage Attacks on Graph Neural Networks","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-06-25T21:09:23.769302Z"},"links":{"citing_paper":"/paper/2606.25589"},"observation_digest":"sha256:838dfd93ba70f625d0c766a9338df0105abda80c810f7cf8cb313a001997abea","observation_id":"f80d426a-9f28-4daf-86bf-9afb64723f85","resolution":{"observed_at":"2026-06-25T21:09:23.769302Z","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":"2026-06-25T21:09:23.769302Z","title":"Gradient leakage attack resilient deep learning,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2606.25589","last_updated":"2026-06-24T08:59:28Z","snapshot_observed_at":"2026-08-16T20:59:57.458007Z","submitted_at":"2026-06-24T08:59:28Z","title":"Leaking Circuit Secrets: Gradient Leakage Attacks on Graph Neural Networks","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-06-25T21:09:23.769302Z"},"links":{"citing_paper":"/paper/2606.25589"},"observation_digest":"sha256:4bcab2280ccf509dd7af1f710196da12efafeff8371b4ca2dbf0f84a80aa3690","observation_id":"1332fb63-c26a-4b10-9d3f-aeef8f22c438","resolution":{"observed_at":"2026-06-25T21:09:23.769302Z","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":"2026-06-25T21:09:23.769302Z","title":"Breaking secure aggregation: Label leakage from aggregated gradients in federated learning,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2606.25589","last_updated":"2026-06-24T08:59:28Z","snapshot_observed_at":"2026-08-16T20:59:57.458007Z","submitted_at":"2026-06-24T08:59:28Z","title":"Leaking Circuit Secrets: Gradient Leakage Attacks on Graph Neural Networks","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-06-25T21:09:23.769302Z"},"links":{"citing_paper":"/paper/2606.25589"},"observation_digest":"sha256:b735a338edc839e016bb7bc4ebae34020c0af235919d0a04bbe05598111cc3e2","observation_id":"98edb0ab-f168-49d0-9c10-83b73392ee39","resolution":{"observed_at":"2026-06-25T21:09:23.769302Z","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":"2026-06-25T21:09:23.769302Z","title":"Model compression hardens deep neural networks: A new perspective to prevent adversarial attacks,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2606.25589","last_updated":"2026-06-24T08:59:28Z","snapshot_observed_at":"2026-08-16T20:59:57.458007Z","submitted_at":"2026-06-24T08:59:28Z","title":"Leaking Circuit Secrets: Gradient Leakage Attacks on Graph Neural Networks","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-06-25T21:09:23.769302Z"},"links":{"citing_paper":"/paper/2606.25589"},"observation_digest":"sha256:7c01c35c68ac6c657a86ae510f42e8bde616747c101ecc8efe30df6394e32b6d","observation_id":"ee2f5692-ea17-4cff-a708-e4f8a6f9f550","resolution":{"observed_at":"2026-06-25T21:09:23.769302Z","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":"2026-06-25T21:09:23.769302Z","title":"Deep models under the gan: information leakage from collaborative deep learning,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2606.25589","last_updated":"2026-06-24T08:59:28Z","snapshot_observed_at":"2026-08-16T20:59:57.458007Z","submitted_at":"2026-06-24T08:59:28Z","title":"Leaking Circuit Secrets: Gradient Leakage Attacks on Graph Neural Networks","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-06-25T21:09:23.769302Z"},"links":{"citing_paper":"/paper/2606.25589"},"observation_digest":"sha256:d13aaa7e5207737c12307fa4a5781ba3b33d933eb15d105e4bfd0c3c2d5ba521","observation_id":"53ce6e63-3aad-46ae-9710-faef7ed6018b","resolution":{"observed_at":"2026-06-25T21:09:23.769302Z","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":"2026-06-25T21:09:23.769302Z","title":"Inverting gradients-how easy is it to break privacy in federated learning?","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2606.25589","last_updated":"2026-06-24T08:59:28Z","snapshot_observed_at":"2026-08-16T20:59:57.458007Z","submitted_at":"2026-06-24T08:59:28Z","title":"Leaking Circuit Secrets: Gradient Leakage Attacks on Graph Neural Networks","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-06-25T21:09:23.769302Z"},"links":{"citing_paper":"/paper/2606.25589"},"observation_digest":"sha256:90b69b303a59b599e82f6f52915d6becfaaac726cae4001f3a88d14caf3dc88f","observation_id":"1a2e637c-b6bb-4fa8-915d-1c0828c246e4","resolution":{"observed_at":"2026-06-25T21:09:23.769302Z","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":"2026-06-25T21:09:23.769302Z","title":"Exploiting unintended feature leakage in collaborative learning,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2606.25589","last_updated":"2026-06-24T08:59:28Z","snapshot_observed_at":"2026-08-16T20:59:57.458007Z","submitted_at":"2026-06-24T08:59:28Z","title":"Leaking Circuit Secrets: Gradient Leakage Attacks on Graph Neural Networks","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-06-25T21:09:23.769302Z"},"links":{"citing_paper":"/paper/2606.25589"},"observation_digest":"sha256:185d8f0ef257eb95b9935eb6a794f2fc726ecee1433b129e0389f79edd2394ed","observation_id":"3ba7094e-8052-4aa7-9500-b9afa273b086","resolution":{"observed_at":"2026-06-25T21:09:23.769302Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2206.07284","last_updated":"2022-06-15T03:52:51Z","snapshot_observed_at":"2026-08-16T16:52:55.257846Z","submitted_at":"2022-06-15T03:52:51Z","title":"A Survey on Gradient Inversion: Attacks, Defenses and Future Directions","version":1},"cited_work":{"arxiv_id":"2206.07284","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2206.07284","snapshot_observed_at":"2026-07-04T19:40:06.645522Z","title":"A survey on gradient inversion: Attacks, defenses and future directions,","venue":null,"work_id":"a0354b6b-bfde-4396-a3ea-3aa5348ba02e","year":2022},"citing_paper":{"arxiv_id":"2606.25589","last_updated":"2026-06-24T08:59:28Z","snapshot_observed_at":"2026-08-16T20:59:57.458007Z","submitted_at":"2026-06-24T08:59:28Z","title":"Leaking Circuit Secrets: Gradient Leakage Attacks on Graph Neural Networks","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-06-25T21:09:23.769302Z"},"links":{"cited_paper":"/paper/2206.07284","citing_paper":"/paper/2606.25589"},"observation_digest":"sha256:f4fbff639a2ecb55e5486cb87dbb707d521f69752e08433200e9a19cd310655f","observation_id":"10ba6641-0fb0-4d4b-92cc-3e5ec307d4cc","resolution":{"observed_at":"2026-07-04T19:40:06.647094Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2411.19440","last_updated":"2025-08-03T01:05:31Z","snapshot_observed_at":"2026-08-22T02:35:16.218011Z","submitted_at":"2024-11-29T02:42:17Z","title":"Gradient Inversion Attack on Graph Neural Networks","version":2},"cited_work":{"arxiv_id":"2411.19440","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2411.19440","snapshot_observed_at":"2026-07-04T19:40:06.640010Z","title":"Gradient inver- sion attack on graph neural networks,","venue":null,"work_id":"84ec71b6-2ff8-4471-984d-5b4263774024","year":2024},"citing_paper":{"arxiv_id":"2606.25589","last_updated":"2026-06-24T08:59:28Z","snapshot_observed_at":"2026-08-16T20:59:57.458007Z","submitted_at":"2026-06-24T08:59:28Z","title":"Leaking Circuit Secrets: Gradient Leakage Attacks on Graph Neural Networks","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-06-25T21:09:23.769302Z"},"links":{"cited_paper":"/paper/2411.19440","citing_paper":"/paper/2606.25589"},"observation_digest":"sha256:4ba1913c7f493fbcaf193ebfaf4e199d598bb28d61e142282f922acf089e95d0","observation_id":"b0ff1376-5a89-4fb8-8519-e121b38b7278","resolution":{"observed_at":"2026-07-04T19:40:06.641515Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-06-25T21:09:23.769302Z","title":"Everything is connected: Graph neural networks,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2606.25589","last_updated":"2026-06-24T08:59:28Z","snapshot_observed_at":"2026-08-16T20:59:57.458007Z","submitted_at":"2026-06-24T08:59:28Z","title":"Leaking Circuit Secrets: Gradient Leakage Attacks on Graph Neural Networks","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-06-25T21:09:23.769302Z"},"links":{"citing_paper":"/paper/2606.25589"},"observation_digest":"sha256:add715576fdb004cf781bf057d0dea2d0bf5027055ac2aee60263990535ced87","observation_id":"88160741-b376-4f2d-a10f-463eeae98075","resolution":{"observed_at":"2026-06-25T21:09:23.769302Z","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":"2026-06-25T21:09:23.769302Z","title":"Mathematical expres- siveness of graph neural networks,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2606.25589","last_updated":"2026-06-24T08:59:28Z","snapshot_observed_at":"2026-08-16T20:59:57.458007Z","submitted_at":"2026-06-24T08:59:28Z","title":"Leaking Circuit Secrets: Gradient Leakage Attacks on Graph Neural Networks","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-06-25T21:09:23.769302Z"},"links":{"citing_paper":"/paper/2606.25589"},"observation_digest":"sha256:5080619c44cdd32e25316b2c0598eee07f8d3bfb1c8a640d7c50b9edd55012e5","observation_id":"4686c5f9-6f57-4adb-ab55-e6d0a0765975","resolution":{"observed_at":"2026-06-25T21:09:23.769302Z","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":"2026-06-25T21:09:23.769302Z","title":"Vision gnn: An image is worth graph of nodes,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2606.25589","last_updated":"2026-06-24T08:59:28Z","snapshot_observed_at":"2026-08-16T20:59:57.458007Z","submitted_at":"2026-06-24T08:59:28Z","title":"Leaking Circuit Secrets: Gradient Leakage Attacks on Graph Neural Networks","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-06-25T21:09:23.769302Z"},"links":{"citing_paper":"/paper/2606.25589"},"observation_digest":"sha256:7885ec8d9d59bafbf7e1fc0d78edcfc5d24123d09a5685bf6eb6c6035995264e","observation_id":"eb1e78df-a0fe-4c7d-929c-bc282465f879","resolution":{"observed_at":"2026-06-25T21:09:23.769302Z","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":"2026-06-25T21:09:23.769302Z","title":"Graph neural network via edge convolution for hyperspectral image classification,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2606.25589","last_updated":"2026-06-24T08:59:28Z","snapshot_observed_at":"2026-08-16T20:59:57.458007Z","submitted_at":"2026-06-24T08:59:28Z","title":"Leaking Circuit Secrets: Gradient Leakage Attacks on Graph Neural Networks","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-06-25T21:09:23.769302Z"},"links":{"citing_paper":"/paper/2606.25589"},"observation_digest":"sha256:17149ddc1a02314b102b3070fe155d19193e178c895afaaae9224e63451ea03b","observation_id":"8dadb388-fb71-43d8-bd8f-4ce7e4b5c316","resolution":{"observed_at":"2026-06-25T21:09:23.769302Z","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":"2026-06-25T21:09:23.769302Z","title":"Graphs, convolutions, and neural networks: From graph filters to graph neural networks,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2606.25589","last_updated":"2026-06-24T08:59:28Z","snapshot_observed_at":"2026-08-16T20:59:57.458007Z","submitted_at":"2026-06-24T08:59:28Z","title":"Leaking Circuit Secrets: Gradient Leakage Attacks on Graph Neural Networks","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-06-25T21:09:23.769302Z"},"links":{"citing_paper":"/paper/2606.25589"},"observation_digest":"sha256:9912e81712047fedff3fb51d47f530674a9f7676f29b8086a691a2b8bb49e723","observation_id":"8012095c-299b-4d6a-a613-951167cbd324","resolution":{"observed_at":"2026-06-25T21:09:23.769302Z","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":"2026-06-25T21:09:23.769302Z","title":"Membership inference attacks on machine learning: A survey,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2606.25589","last_updated":"2026-06-24T08:59:28Z","snapshot_observed_at":"2026-08-16T20:59:57.458007Z","submitted_at":"2026-06-24T08:59:28Z","title":"Leaking Circuit Secrets: Gradient Leakage Attacks on Graph Neural Networks","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-06-25T21:09:23.769302Z"},"links":{"citing_paper":"/paper/2606.25589"},"observation_digest":"sha256:825776aaa294f71965ca41dd0d2a92b3494f93b6dde371c4f9af6dabfb6f4471","observation_id":"02fc3fe2-44b2-4172-aa5d-356ce23159fa","resolution":{"observed_at":"2026-06-25T21:09:23.769302Z","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":"2026-06-25T21:09:23.769302Z","title":"Advances in logic locking: Past, present, and prospects,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2606.25589","last_updated":"2026-06-24T08:59:28Z","snapshot_observed_at":"2026-08-16T20:59:57.458007Z","submitted_at":"2026-06-24T08:59:28Z","title":"Leaking Circuit Secrets: Gradient Leakage Attacks on Graph Neural Networks","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-06-25T21:09:23.769302Z"},"links":{"citing_paper":"/paper/2606.25589"},"observation_digest":"sha256:af363de458df05d038036adb87b48ee44933e1e5ee355d430abd0646e0999e69","observation_id":"c07dd80d-cfe9-467d-9b9d-ee945d8fe1e0","resolution":{"observed_at":"2026-06-25T21:09:23.769302Z","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":"2026-06-25T21:09:23.769302Z","title":"A survey of the implementations of model inversion attacks,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2606.25589","last_updated":"2026-06-24T08:59:28Z","snapshot_observed_at":"2026-08-16T20:59:57.458007Z","submitted_at":"2026-06-24T08:59:28Z","title":"Leaking Circuit Secrets: Gradient Leakage Attacks on Graph Neural Networks","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-06-25T21:09:23.769302Z"},"links":{"citing_paper":"/paper/2606.25589"},"observation_digest":"sha256:b19982fc09f43647122c18cbf49f86282576afce3f50fbd2360d27b92bbf191b","observation_id":"d681bf70-2dab-4c62-b12f-df3ff2e0cc05","resolution":{"observed_at":"2026-06-25T21:09:23.769302Z","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":"2026-06-25T21:09:23.769302Z","title":"An automated framework for board-level trojan benchmarking,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2606.25589","last_updated":"2026-06-24T08:59:28Z","snapshot_observed_at":"2026-08-16T20:59:57.458007Z","submitted_at":"2026-06-24T08:59:28Z","title":"Leaking Circuit Secrets: Gradient Leakage Attacks on Graph Neural Networks","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-06-25T21:09:23.769302Z"},"links":{"citing_paper":"/paper/2606.25589"},"observation_digest":"sha256:52c8d6d18c8ae53bfaa89a4c840ea45551fe5ca73092bd5ea04a250ecc19d218","observation_id":"9ceeb7cb-8d61-4400-ab8a-a078d40382e2","resolution":{"observed_at":"2026-06-25T21:09:23.769302Z","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":"2026-06-25T21:09:23.769302Z","title":"The state-of-the-art in ic reverse engineering,","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2606.25589","last_updated":"2026-06-24T08:59:28Z","snapshot_observed_at":"2026-08-16T20:59:57.458007Z","submitted_at":"2026-06-24T08:59:28Z","title":"Leaking Circuit Secrets: Gradient Leakage Attacks on Graph Neural Networks","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-06-25T21:09:23.769302Z"},"links":{"citing_paper":"/paper/2606.25589"},"observation_digest":"sha256:b25b20c09feee90db7faad0dae63bbbd4abf50f61f9d0bbfc6a69f3b5f9b7045","observation_id":"5001f264-59a1-4b41-81ee-d740145dc349","resolution":{"observed_at":"2026-06-25T21:09:23.769302Z","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":"2026-06-25T21:09:23.769302Z","title":"Netlist reverse engineering for high- level functionality reconstruction,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2606.25589","last_updated":"2026-06-24T08:59:28Z","snapshot_observed_at":"2026-08-16T20:59:57.458007Z","submitted_at":"2026-06-24T08:59:28Z","title":"Leaking Circuit Secrets: Gradient Leakage Attacks on Graph Neural Networks","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-06-25T21:09:23.769302Z"},"links":{"citing_paper":"/paper/2606.25589"},"observation_digest":"sha256:fe113e7927e75aa716cd095602607e4520bfc3d4e15ab760d76500d9a630418b","observation_id":"d4a3ccf0-f221-4627-9964-9e1664703d07","resolution":{"observed_at":"2026-06-25T21:09:23.769302Z","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":"2026-06-25T21:09:23.769302Z","title":"Adaptivenet: Post-deployment neural architecture adaptation for diverse edge environments,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2606.25589","last_updated":"2026-06-24T08:59:28Z","snapshot_observed_at":"2026-08-16T20:59:57.458007Z","submitted_at":"2026-06-24T08:59:28Z","title":"Leaking Circuit Secrets: Gradient Leakage Attacks on Graph Neural Networks","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-06-25T21:09:23.769302Z"},"links":{"citing_paper":"/paper/2606.25589"},"observation_digest":"sha256:814f8d0dc82ac58cd580e2f226c1248f1f581371d3b8fe3a3afe7a56ff44676e","observation_id":"823f1d5b-d474-4ed6-aea2-cda2f4cd3e67","resolution":{"observed_at":"2026-06-25T21:09:23.769302Z","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":"2026-06-25T21:09:23.769302Z","title":"Side channel attacks for architecture extraction of neural networks,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2606.25589","last_updated":"2026-06-24T08:59:28Z","snapshot_observed_at":"2026-08-16T20:59:57.458007Z","submitted_at":"2026-06-24T08:59:28Z","title":"Leaking Circuit Secrets: Gradient Leakage Attacks on Graph Neural Networks","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-06-25T21:09:23.769302Z"},"links":{"citing_paper":"/paper/2606.25589"},"observation_digest":"sha256:8367589d6eb01bc7054614a1aec15f2a114516bc98588cd3ee84031dad5d7f8d","observation_id":"df4833af-b1da-48d9-bc28-9aad39e0a47b","resolution":{"observed_at":"2026-06-25T21:09:23.769302Z","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":"2026-06-25T21:09:23.769302Z","title":"Deep learning with differential privacy,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2606.25589","last_updated":"2026-06-24T08:59:28Z","snapshot_observed_at":"2026-08-16T20:59:57.458007Z","submitted_at":"2026-06-24T08:59:28Z","title":"Leaking Circuit Secrets: Gradient Leakage Attacks on Graph Neural Networks","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-06-25T21:09:23.769302Z"},"links":{"citing_paper":"/paper/2606.25589"},"observation_digest":"sha256:696ec2401289bc9ae66b4bba7c4cbb8d62794dc00b78d49dded0903d6b6bf210","observation_id":"26b0bc29-4b56-47d9-94b6-3bec6c672d58","resolution":{"observed_at":"2026-06-25T21:09:23.769302Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1909.01315","last_updated":"2020-08-25T15:46:13Z","snapshot_observed_at":"2026-08-18T10:54:34.717319Z","submitted_at":"2019-09-03T17:10:28Z","title":"Deep Graph Library: A Graph-Centric, Highly-Performant Package for Graph Neural Networks","version":2},"cited_work":{"arxiv_id":"1909.01315","doi":"10.1109/jproc.2015.2494218","metadata_source":"pith","pith_arxiv_id":"1909.01315","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Deep Graph Library: A Graph-Centric, Highly-Performant Package for Graph Neural Networks","venue":"cs.LG","work_id":"cda59fa8-5a85-49bd-97eb-af4eb18ec95a","year":2019},"citing_paper":{"arxiv_id":"2606.25589","last_updated":"2026-06-24T08:59:28Z","snapshot_observed_at":"2026-08-16T20:59:57.458007Z","submitted_at":"2026-06-24T08:59:28Z","title":"Leaking Circuit Secrets: Gradient Leakage Attacks on Graph Neural Networks","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-06-25T21:09:23.769302Z"},"links":{"cited_paper":"/paper/1909.01315","citing_paper":"/paper/2606.25589"},"observation_digest":"sha256:078f10d793c06c7f9c915a3dbf97a3cca16fc9179180fbe9c99991503a28b3a3","observation_id":"e1b17dbe-0081-4803-b75b-8dabb4dc0224","resolution":{"observed_at":"2026-07-04T19:40:06.644302Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-07-12T04:50:27.149977+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-12T04:50:27.149977+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-06-25T21:09:23.769302Z","title":"A survey of handwritten character recognition with mnist and emnist,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2606.25589","last_updated":"2026-06-24T08:59:28Z","snapshot_observed_at":"2026-08-16T20:59:57.458007Z","submitted_at":"2026-06-24T08:59:28Z","title":"Leaking Circuit Secrets: Gradient Leakage Attacks on Graph Neural Networks","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-06-25T21:09:23.769302Z"},"links":{"citing_paper":"/paper/2606.25589"},"observation_digest":"sha256:60aadafa34af242f3469cbb68742cd6bb0e5abe94251397c99f51cf622ebb407","observation_id":"1d82e810-a7b1-45ce-afa0-debbb6f08327","resolution":{"observed_at":"2026-06-25T21:09:23.769302Z","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":"2026-06-25T21:09:23.769302Z","title":"Unveiling the iscas-85 benchmarks: A case study in reverse engineering,","venue":null,"work_id":null,"year":1999},"citing_paper":{"arxiv_id":"2606.25589","last_updated":"2026-06-24T08:59:28Z","snapshot_observed_at":"2026-08-16T20:59:57.458007Z","submitted_at":"2026-06-24T08:59:28Z","title":"Leaking Circuit Secrets: Gradient Leakage Attacks on Graph Neural Networks","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-06-25T21:09:23.769302Z"},"links":{"citing_paper":"/paper/2606.25589"},"observation_digest":"sha256:2b27f30fddc151cb002bb76f6e52592b68604b7c479d99910ba8ecf30c830a5d","observation_id":"2985c089-6951-4427-a8d3-13bdd66533ec","resolution":{"observed_at":"2026-06-25T21:09:23.769302Z","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":"2026-06-25T21:09:23.769302Z","title":"The epfl combinational benchmark suite,","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2606.25589","last_updated":"2026-06-24T08:59:28Z","snapshot_observed_at":"2026-08-16T20:59:57.458007Z","submitted_at":"2026-06-24T08:59:28Z","title":"Leaking Circuit Secrets: Gradient Leakage Attacks on Graph Neural Networks","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-06-25T21:09:23.769302Z"},"links":{"citing_paper":"/paper/2606.25589"},"observation_digest":"sha256:25922eba4b44e589839e0a0eacb0bf288b75bc15652505c1511e8cbb5bc1083d","observation_id":"6deeccde-4527-4650-a55d-19591a996d82","resolution":{"observed_at":"2026-06-25T21:09:23.769302Z","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":"2026-06-25T21:09:23.769302Z","title":"This transformation limits the granularity of feature updates, reducing inversion fidelity","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.25589","last_updated":"2026-06-24T08:59:28Z","snapshot_observed_at":"2026-08-16T20:59:57.458007Z","submitted_at":"2026-06-24T08:59:28Z","title":"Leaking Circuit Secrets: Gradient Leakage Attacks on Graph Neural Networks","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-06-25T21:09:23.769302Z"},"links":{"citing_paper":"/paper/2606.25589"},"observation_digest":"sha256:e2652ac2fe431b9d898626bdad47cef1c4f193b2330f5ae71bfd1b475951d360","observation_id":"5184d251-c7ce-4024-8856-afe13dad92a2","resolution":{"observed_at":"2026-06-25T21:09:23.769302Z","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":"2026-06-25T21:09:23.769302Z","title":"This process eliminates weak connections in the NN, making gradient inversion less effective","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.25589","last_updated":"2026-06-24T08:59:28Z","snapshot_observed_at":"2026-08-16T20:59:57.458007Z","submitted_at":"2026-06-24T08:59:28Z","title":"Leaking Circuit Secrets: Gradient Leakage Attacks on Graph Neural Networks","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-06-25T21:09:23.769302Z"},"links":{"citing_paper":"/paper/2606.25589"},"observation_digest":"sha256:ea0897c6ef8c9bf6b4e79965c6978a5aa8538ee50e69ba8d13ea11250224e7f6","observation_id":"3d8c2e4f-4980-43ac-8de9-94c9251ab3f5","resolution":{"observed_at":"2026-06-25T21:09:23.769302Z","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":"2026-06-25T21:09:23.769302Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.25589","last_updated":"2026-06-24T08:59:28Z","snapshot_observed_at":"2026-08-16T20:59:57.458007Z","submitted_at":"2026-06-24T08:59:28Z","title":"Leaking Circuit Secrets: Gradient Leakage Attacks on Graph Neural Networks","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-06-25T21:09:23.769302Z"},"links":{"citing_paper":"/paper/2606.25589"},"observation_digest":"sha256:35dcee292e1bb52caf791e8b8178ca6c6e547b9d8d282deeffa59c5cc8a03851","observation_id":"549f82ed-0c67-4af5-9e92-51b40b15a4f9","resolution":{"observed_at":"2026-06-25T21:09:23.769302Z","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":"2026-06-25T21:09:23.769302Z","title":"This forces the model to optimize for robustness rather than merely fitting the clean training data","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.25589","last_updated":"2026-06-24T08:59:28Z","snapshot_observed_at":"2026-08-16T20:59:57.458007Z","submitted_at":"2026-06-24T08:59:28Z","title":"Leaking Circuit Secrets: Gradient Leakage Attacks on Graph Neural Networks","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-06-25T21:09:23.769302Z"},"links":{"citing_paper":"/paper/2606.25589"},"observation_digest":"sha256:b778a93de7ee048a6427daead4118ab3e4def2582aaf601e82d509d5bf5fc6da","observation_id":"21555831-d35b-4a7c-a036-a6986d696955","resolution":{"observed_at":"2026-06-25T21:09:23.769302Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2606.25589","last_updated":"2026-06-24T08:59:28Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-16T20:59:57.458007Z","submitted_at":"2026-06-24T08:59:28Z","title":"Leaking Circuit Secrets: Gradient Leakage Attacks on Graph Neural Networks"},"reference_resolution":{"displayed":47,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":43,"verified_exact":4,"verified_fuzzy":0},"total_outbound_references":47},"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":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"thesis":"As of 23 August 2026, this Paper Citation Record lists 47 of 47 outbound references and 0 inbound Pith citation observations for arXiv:2606.25589."}