{"as_of":"2026-08-11T17:39:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:4af64fb76f15b2a5c5a48ffcf84bb3a6fab12fdcfd283ea555bd108c16cbfd50","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":"2026-08-10T21:02:02.035875Z","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":"2026-08-11T06:34:44.6726+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/2501.06650/citation-record","integrity":"/paper/2501.06650/integrity","json":"/paper/2501.06650/citation-record.json","paper":"/paper/2501.06650"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T21:02:03.389825Z","title":"https://www.govinfo.gov/content/pkg/PLAW-104publ191/pdf/ PLAW-104publ191.pdf","venue":null,"work_id":"21befb42-2019-4f73-95aa-2f4e54631dbf","year":1996},"citing_paper":{"arxiv_id":"2501.06650","last_updated":"2025-02-24T05:31:25Z","snapshot_observed_at":"2026-08-10T21:15:29.368518Z","submitted_at":"2025-01-11T22:20:20Z","title":"SafeSplit: A Novel Defense Against Client-Side Backdoor Attacks in Split Learning (Full Version)","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-10T21:02:01.681186Z"},"links":{"citing_paper":"/paper/2501.06650"},"observation_digest":"sha256:58316a96a3217d12cf940f0ab336fbdbfcc04adc4bd517da8195acf3c68024e2","observation_id":"424d776a-b5a0-49b5-b3f4-b7c64e99a77a","resolution":{"observed_at":"2026-08-10T21:02:03.394622Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T21:02:03.370642Z","title":"https://eur-lex.europa.eu/eli/ reg/2016/679/oj","venue":null,"work_id":"17186d62-c486-4d93-8deb-0a65da55a754","year":2018},"citing_paper":{"arxiv_id":"2501.06650","last_updated":"2025-02-24T05:31:25Z","snapshot_observed_at":"2026-08-10T21:15:29.368518Z","submitted_at":"2025-01-11T22:20:20Z","title":"SafeSplit: A Novel Defense Against Client-Side Backdoor Attacks in Split Learning (Full Version)","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-10T21:02:01.687331Z"},"links":{"citing_paper":"/paper/2501.06650"},"observation_digest":"sha256:8f69a13c86091cefde5f88d8f5d10211a60c79cc17ed4a71e25dd90251162b15","observation_id":"a94b5e5c-45e5-4dd8-874d-525644b74fba","resolution":{"observed_at":"2026-08-10T21:02:03.376154Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T21:02:03.350886Z","title":"https://pytorch.org","venue":null,"work_id":"978867c0-0300-4d68-8df1-21b7a6bfcd69","year":2022},"citing_paper":{"arxiv_id":"2501.06650","last_updated":"2025-02-24T05:31:25Z","snapshot_observed_at":"2026-08-10T21:15:29.368518Z","submitted_at":"2025-01-11T22:20:20Z","title":"SafeSplit: A Novel Defense Against Client-Side Backdoor Attacks in Split Learning (Full Version)","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-10T21:02:01.693589Z"},"links":{"citing_paper":"/paper/2501.06650"},"observation_digest":"sha256:8e4171e7a3b386b0755ced6bfe10a63d33e341bb344c73122ce65d58410aa6ce","observation_id":"136c5455-fbd7-4bab-9a0e-87567f4d2946","resolution":{"observed_at":"2026-08-10T21:02:03.357860Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T21:02:03.330596Z","title":"Discrete cosine transform","venue":null,"work_id":"8ab04dc4-cd1d-4f51-9102-086b3386ce50","year":1974},"citing_paper":{"arxiv_id":"2501.06650","last_updated":"2025-02-24T05:31:25Z","snapshot_observed_at":"2026-08-10T21:15:29.368518Z","submitted_at":"2025-01-11T22:20:20Z","title":"SafeSplit: A Novel Defense Against Client-Side Backdoor Attacks in Split Learning (Full Version)","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-10T21:02:01.699237Z"},"links":{"citing_paper":"/paper/2501.06650"},"observation_digest":"sha256:25af350b855f1d7984353d35ff124e6e3f93ad4a4066292ab8b939eeb545d7c1","observation_id":"55554eaf-62ec-4ef5-9413-295e22c70b78","resolution":{"observed_at":"2026-08-10T21:02:03.335850Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T21:02:03.314926Z","title":"How To Backdoor Federated Learning","venue":null,"work_id":"7d8a89ae-22fb-46a2-babd-f9d71211f3ed","year":2020},"citing_paper":{"arxiv_id":"2501.06650","last_updated":"2025-02-24T05:31:25Z","snapshot_observed_at":"2026-08-10T21:15:29.368518Z","submitted_at":"2025-01-11T22:20:20Z","title":"SafeSplit: A Novel Defense Against Client-Side Backdoor Attacks in Split Learning (Full Version)","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-10T21:02:01.704562Z"},"links":{"citing_paper":"/paper/2501.06650"},"observation_digest":"sha256:2ddb02758ae6245b052b94a51bb8832e4c7d6ed0e969ec2720a6cfaa5c760d44","observation_id":"f63041c7-b4e7-47f0-9424-0c256be2fcd7","resolution":{"observed_at":"2026-08-10T21:02:03.319501Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T21:02:03.298079Z","title":"VILLAIN: Backdoor attacks against vertical split learning","venue":null,"work_id":"c4609652-bae3-457c-bec3-5c8cb1017f06","year":2023},"citing_paper":{"arxiv_id":"2501.06650","last_updated":"2025-02-24T05:31:25Z","snapshot_observed_at":"2026-08-10T21:15:29.368518Z","submitted_at":"2025-01-11T22:20:20Z","title":"SafeSplit: A Novel Defense Against Client-Side Backdoor Attacks in Split Learning (Full Version)","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-10T21:02:01.710637Z"},"links":{"citing_paper":"/paper/2501.06650"},"observation_digest":"sha256:8ff3525d4fa48d4b67cc10e7c97b749403b2dd854669a0bfeb350a7345a798ae","observation_id":"8f65bdac-27ab-48cd-8be1-eec261cd831d","resolution":{"observed_at":"2026-08-10T21:02:03.303122Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T21:02:03.275552Z","title":"Analyzing federated learning through an adversarial lens","venue":null,"work_id":"65751842-7684-4a2e-a854-8b8b1239c865","year":2019},"citing_paper":{"arxiv_id":"2501.06650","last_updated":"2025-02-24T05:31:25Z","snapshot_observed_at":"2026-08-10T21:15:29.368518Z","submitted_at":"2025-01-11T22:20:20Z","title":"SafeSplit: A Novel Defense Against Client-Side Backdoor Attacks in Split Learning (Full Version)","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-10T21:02:01.716366Z"},"links":{"citing_paper":"/paper/2501.06650"},"observation_digest":"sha256:170946a2aee382a65e16d372585c56b56594b008f7f31872412702ea755c5f16","observation_id":"95169507-4de8-412a-af39-09882f07677e","resolution":{"observed_at":"2026-08-10T21:02:03.284961Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T21:02:03.257362Z","title":"Machine Learning with Adversaries: Byzantine Tolerant Gradi- ent Descent","venue":null,"work_id":"20665782-8055-4916-8b51-bcf9d625236e","year":2017},"citing_paper":{"arxiv_id":"2501.06650","last_updated":"2025-02-24T05:31:25Z","snapshot_observed_at":"2026-08-10T21:15:29.368518Z","submitted_at":"2025-01-11T22:20:20Z","title":"SafeSplit: A Novel Defense Against Client-Side Backdoor Attacks in Split Learning (Full Version)","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-10T21:02:01.720965Z"},"links":{"citing_paper":"/paper/2501.06650"},"observation_digest":"sha256:ed6aaa223d30d939f59be77c24e8fd768dc257e4731b624ae6148ee9bffa5742","observation_id":"dfebd9a9-0efa-4dc5-850f-9e41aaf29017","resolution":{"observed_at":"2026-08-10T21:02:03.263025Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T21:02:01.725583Z","title":"Fltrust: Byzantine-robust federated learning via trust bootstrapping","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2501.06650","last_updated":"2025-02-24T05:31:25Z","snapshot_observed_at":"2026-08-10T21:15:29.368518Z","submitted_at":"2025-01-11T22:20:20Z","title":"SafeSplit: A Novel Defense Against Client-Side Backdoor Attacks in Split Learning (Full Version)","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-10T21:02:01.725583Z"},"links":{"citing_paper":"/paper/2501.06650"},"observation_digest":"sha256:d4f2e3b9a9d6bdb33f3e0d02c4bfd6d2f7c919bd0003921f981c7535e76ccea2","observation_id":"0bdd5c62-52d2-479b-9e92-acc14f51bcef","resolution":{"observed_at":"2026-08-10T21:02:01.725583Z","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":"2026-08-10T21:02:03.227433Z","title":"Provably secure federated learning against malicious clients","venue":null,"work_id":"4c536cb1-15a8-431c-87a6-c3db98f18d0a","year":2021},"citing_paper":{"arxiv_id":"2501.06650","last_updated":"2025-02-24T05:31:25Z","snapshot_observed_at":"2026-08-10T21:15:29.368518Z","submitted_at":"2025-01-11T22:20:20Z","title":"SafeSplit: A Novel Defense Against Client-Side Backdoor Attacks in Split Learning (Full Version)","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-10T21:02:01.730300Z"},"links":{"citing_paper":"/paper/2501.06650"},"observation_digest":"sha256:de69f4560b25d2354304c163a2e18f612d1444c6f90fc6b7014f83cc8c8ef048","observation_id":"c9e0f9b4-4398-4d21-80bf-a2c1ea8f3d99","resolution":{"observed_at":"2026-08-10T21:02:03.233163Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T21:02:03.207920Z","title":"Fledge: Ledger-based federated learning resilient to inference and backdoor attacks","venue":null,"work_id":"2f7b50e5-9e75-4ff3-b046-74b55b7c5222","year":2023},"citing_paper":{"arxiv_id":"2501.06650","last_updated":"2025-02-24T05:31:25Z","snapshot_observed_at":"2026-08-10T21:15:29.368518Z","submitted_at":"2025-01-11T22:20:20Z","title":"SafeSplit: A Novel Defense Against Client-Side Backdoor Attacks in Split Learning (Full Version)","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-10T21:02:01.734631Z"},"links":{"citing_paper":"/paper/2501.06650"},"observation_digest":"sha256:29e8bc3f27c3eaef0f5e6537cdddf8bd9aa92650d06447435523a0a5eaeeecc1","observation_id":"d12bb39d-aecf-460c-ad90-21b2936aeac0","resolution":{"observed_at":"2026-08-10T21:02:03.214025Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T21:02:03.192044Z","title":"Harrison Smith, and S","venue":null,"work_id":"ca488daa-70e7-416c-ac58-fdecba01dd73","year":1977},"citing_paper":{"arxiv_id":"2501.06650","last_updated":"2025-02-24T05:31:25Z","snapshot_observed_at":"2026-08-10T21:15:29.368518Z","submitted_at":"2025-01-11T22:20:20Z","title":"SafeSplit: A Novel Defense Against Client-Side Backdoor Attacks in Split Learning (Full Version)","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-10T21:02:01.740008Z"},"links":{"citing_paper":"/paper/2501.06650"},"observation_digest":"sha256:52fdd224b8ec9a2946d9216139fbf90dff87edf72103d3a259153cd897472ff5","observation_id":"951d9f50-32d3-48bd-9221-8b2404afb4b8","resolution":{"observed_at":"2026-08-10T21:02:03.196899Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T21:02:03.170558Z","title":"Splitguard: Detecting and mitigating training-hijacking attacks in split learning","venue":null,"work_id":"50b344d0-e5ed-460a-9db2-c2cd9f6504a3","year":2022},"citing_paper":{"arxiv_id":"2501.06650","last_updated":"2025-02-24T05:31:25Z","snapshot_observed_at":"2026-08-10T21:15:29.368518Z","submitted_at":"2025-01-11T22:20:20Z","title":"SafeSplit: A Novel Defense Against Client-Side Backdoor Attacks in Split Learning (Full Version)","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-10T21:02:01.744554Z"},"links":{"citing_paper":"/paper/2501.06650"},"observation_digest":"sha256:b46567135f9ac7e54a4d7bbc14a863497f5933508495540162e70ca7e1b12c36","observation_id":"5e3d836f-f107-4678-b4e8-b3605da08c94","resolution":{"observed_at":"2026-08-10T21:02:03.177893Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T21:02:03.147390Z","title":"Freqfed: A frequency analysis- based approach for mitigating poisoning attacks in federated learning","venue":null,"work_id":"745d3fda-4ba6-4a34-9e3e-9a83800af127","year":2024},"citing_paper":{"arxiv_id":"2501.06650","last_updated":"2025-02-24T05:31:25Z","snapshot_observed_at":"2026-08-10T21:15:29.368518Z","submitted_at":"2025-01-11T22:20:20Z","title":"SafeSplit: A Novel Defense Against Client-Side Backdoor Attacks in Split Learning (Full Version)","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-10T21:02:01.749229Z"},"links":{"citing_paper":"/paper/2501.06650"},"observation_digest":"sha256:cdf74af2ee8a166c74d7a23e26b4cc940bb88df981826a6b43c8d91e96fc746e","observation_id":"b4a5996f-a544-4b67-b1af-59231c2a1473","resolution":{"observed_at":"2026-08-10T21:02:03.155091Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T21:02:03.126734Z","title":"Label inference attacks against vertical federated learning","venue":null,"work_id":"2b4a6bdf-acfe-4ab7-9486-13fd056037e3","year":2022},"citing_paper":{"arxiv_id":"2501.06650","last_updated":"2025-02-24T05:31:25Z","snapshot_observed_at":"2026-08-10T21:15:29.368518Z","submitted_at":"2025-01-11T22:20:20Z","title":"SafeSplit: A Novel Defense Against Client-Side Backdoor Attacks in Split Learning (Full Version)","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-10T21:02:01.754084Z"},"links":{"citing_paper":"/paper/2501.06650"},"observation_digest":"sha256:a7f2070ed1ed3f2a898009334bb3f9873b14f6af8d54ea75c18e4d5440c86c09","observation_id":"67b4a661-b8ba-40af-ab74-375ca054c344","resolution":{"observed_at":"2026-08-10T21:02:03.132076Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T21:02:03.099594Z","title":"Focusing on pinocchio’s nose: A gradients scrutinizer to thwart split-learning hijacking attacks using intrinsic attributes","venue":null,"work_id":"87a3f18a-759d-4495-9ff1-938ff834cff6","year":2023},"citing_paper":{"arxiv_id":"2501.06650","last_updated":"2025-02-24T05:31:25Z","snapshot_observed_at":"2026-08-10T21:15:29.368518Z","submitted_at":"2025-01-11T22:20:20Z","title":"SafeSplit: A Novel Defense Against Client-Side Backdoor Attacks in Split Learning (Full Version)","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-10T21:02:01.759030Z"},"links":{"citing_paper":"/paper/2501.06650"},"observation_digest":"sha256:bb72d9adb459fcf41e7dc6fd525af578b09ee1e7374814be7beb256be89706e4","observation_id":"122f60f2-742a-45d8-8542-06e4d39754d3","resolution":{"observed_at":"2026-08-10T21:02:03.108614Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T21:02:03.076457Z","title":"The limitations of federated learning in sybil settings","venue":null,"work_id":"43a48c39-f54b-4607-800c-bb35ce8cd926","year":2020},"citing_paper":{"arxiv_id":"2501.06650","last_updated":"2025-02-24T05:31:25Z","snapshot_observed_at":"2026-08-10T21:15:29.368518Z","submitted_at":"2025-01-11T22:20:20Z","title":"SafeSplit: A Novel Defense Against Client-Side Backdoor Attacks in Split Learning (Full Version)","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-10T21:02:01.763771Z"},"links":{"citing_paper":"/paper/2501.06650"},"observation_digest":"sha256:3ee496c841b8910e5428e53625090d6bd5ae1aaa4b2d1779f57db14518241886","observation_id":"c87a1193-ff50-4db4-a472-b796fea585ea","resolution":{"observed_at":"2026-08-10T21:02:03.082587Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T21:02:03.058175Z","title":"PCAT: Functionality and data stealing from split learning by Pseudo-Client attack","venue":null,"work_id":"0f754ff1-046e-4058-890e-dd59d1dd80e1","year":2023},"citing_paper":{"arxiv_id":"2501.06650","last_updated":"2025-02-24T05:31:25Z","snapshot_observed_at":"2026-08-10T21:15:29.368518Z","submitted_at":"2025-01-11T22:20:20Z","title":"SafeSplit: A Novel Defense Against Client-Side Backdoor Attacks in Split Learning (Full Version)","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-10T21:02:01.769287Z"},"links":{"citing_paper":"/paper/2501.06650"},"observation_digest":"sha256:2ea8b92e918959777e52b1cbdf81b1b2fa7ed2978bb599a093db96483cdb63b3","observation_id":"a58f33c9-c762-450b-a3f5-92fc527eb0f4","resolution":{"observed_at":"2026-08-10T21:02:03.064403Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2003.13376","last_updated":"2020-08-02T08:51:07Z","snapshot_observed_at":"2026-08-08T18:39:44.929077Z","submitted_at":"2020-03-30T12:12:51Z","title":"End-to-End Evaluation of Federated Learning and Split Learning for Internet of Things","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2003.13376","snapshot_observed_at":"2026-08-10T21:02:01.774335Z","title":"End-to-end evaluation of federated learning and split learning for internet of things","venue":null,"work_id":null,"year":2003},"citing_paper":{"arxiv_id":"2501.06650","last_updated":"2025-02-24T05:31:25Z","snapshot_observed_at":"2026-08-10T21:15:29.368518Z","submitted_at":"2025-01-11T22:20:20Z","title":"SafeSplit: A Novel Defense Against Client-Side Backdoor Attacks in Split Learning (Full Version)","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-10T21:02:01.774335Z"},"links":{"cited_paper":"/paper/2003.13376","citing_paper":"/paper/2501.06650"},"observation_digest":"sha256:955328cc02ba5e2350c78f09bbc52ed94c178ffe2d424e39157b3cba306fba9a","observation_id":"1f202d29-4ac3-4e4d-9384-ff44765fe133","resolution":{"observed_at":"2026-08-10T21:02:01.774335Z","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":"2026-08-10T21:02:03.038659Z","title":"Distributed learning of deep neural network over multiple agents","venue":null,"work_id":"d35f22a1-090e-4147-a2e6-f3106019c873","year":2018},"citing_paper":{"arxiv_id":"2501.06650","last_updated":"2025-02-24T05:31:25Z","snapshot_observed_at":"2026-08-10T21:15:29.368518Z","submitted_at":"2025-01-11T22:20:20Z","title":"SafeSplit: A Novel Defense Against Client-Side Backdoor Attacks in Split Learning (Full Version)","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-10T21:02:01.780745Z"},"links":{"citing_paper":"/paper/2501.06650"},"observation_digest":"sha256:253f22e43347024ba341ed73f426b17b4dd5ea54bae012c39edc7c1dfe5cc01d","observation_id":"567836ec-3ba5-47f4-86db-d6184ccc2616","resolution":{"observed_at":"2026-08-10T21:02:03.045869Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T21:02:03.018471Z","title":"Deep residual learning for image recognition","venue":null,"work_id":"670bdb0d-49a8-4aa7-9266-8e8dc4b22371","year":2016},"citing_paper":{"arxiv_id":"2501.06650","last_updated":"2025-02-24T05:31:25Z","snapshot_observed_at":"2026-08-10T21:15:29.368518Z","submitted_at":"2025-01-11T22:20:20Z","title":"SafeSplit: A Novel Defense Against Client-Side Backdoor Attacks in Split Learning (Full Version)","version":2},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-10T21:02:01.785565Z"},"links":{"citing_paper":"/paper/2501.06650"},"observation_digest":"sha256:ef748c89e2a5159c2a537ae93e1273d28b47bba9bad71f5397b85de67251c95a","observation_id":"4417f306-630b-4d95-9d7a-49cdc67aa176","resolution":{"observed_at":"2026-08-10T21:02:03.025524Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T21:02:02.999699Z","title":"Backdoor attack against split neural network-based vertical federated learning","venue":null,"work_id":"9b7e5edd-1257-49e2-9ab0-6569486b25c6","year":2023},"citing_paper":{"arxiv_id":"2501.06650","last_updated":"2025-02-24T05:31:25Z","snapshot_observed_at":"2026-08-10T21:15:29.368518Z","submitted_at":"2025-01-11T22:20:20Z","title":"SafeSplit: A Novel Defense Against Client-Side Backdoor Attacks in Split Learning (Full Version)","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-10T21:02:01.790589Z"},"links":{"citing_paper":"/paper/2501.06650"},"observation_digest":"sha256:e904d4a76cb773765437d62bd5a4d6e7e704fca036b91522f5acfa6cf3dbcbaf","observation_id":"021adbae-de3d-4a50-af43-97e74c3238a8","resolution":{"observed_at":"2026-08-10T21:02:03.005464Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T21:02:01.795655Z","title":"Advances and open problems in federated learning","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2501.06650","last_updated":"2025-02-24T05:31:25Z","snapshot_observed_at":"2026-08-10T21:15:29.368518Z","submitted_at":"2025-01-11T22:20:20Z","title":"SafeSplit: A Novel Defense Against Client-Side Backdoor Attacks in Split Learning (Full Version)","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-10T21:02:01.795655Z"},"links":{"citing_paper":"/paper/2501.06650"},"observation_digest":"sha256:ec1de89e4b2ec43839460e9f02ba7bf3177ccd96f4e9fd7d9b2fd2712b7df4e2","observation_id":"725c1645-078b-44c4-a308-27808c8ad118","resolution":{"observed_at":"2026-08-10T21:02:01.795655Z","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":"2026-08-10T21:02:02.964131Z","title":"Exploit: Extracting private labels in split learning","venue":null,"work_id":"47248edb-58de-4268-b299-96946b98b308","year":2023},"citing_paper":{"arxiv_id":"2501.06650","last_updated":"2025-02-24T05:31:25Z","snapshot_observed_at":"2026-08-10T21:15:29.368518Z","submitted_at":"2025-01-11T22:20:20Z","title":"SafeSplit: A Novel Defense Against Client-Side Backdoor Attacks in Split Learning (Full Version)","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-10T21:02:01.801791Z"},"links":{"citing_paper":"/paper/2501.06650"},"observation_digest":"sha256:7650a4fd6be18c56313345f54755556e1ebaab070d48a01b8b6bffd428b62276","observation_id":"ce70be66-bc02-4cfe-91a8-0d148fb12123","resolution":{"observed_at":"2026-08-10T21:02:02.970371Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T21:02:02.944228Z","title":"Mesas: Poisoning defense for federated learning resilient against adaptive attackers","venue":null,"work_id":"817f7a1b-3395-4dea-8061-0a4db739d422","year":2023},"citing_paper":{"arxiv_id":"2501.06650","last_updated":"2025-02-24T05:31:25Z","snapshot_observed_at":"2026-08-10T21:15:29.368518Z","submitted_at":"2025-01-11T22:20:20Z","title":"SafeSplit: A Novel Defense Against Client-Side Backdoor Attacks in Split Learning (Full Version)","version":2},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-10T21:02:01.806175Z"},"links":{"citing_paper":"/paper/2501.06650"},"observation_digest":"sha256:7eb6db6022836f2440da76fa09722d241988100fbf208f295982bba1e880d716","observation_id":"6d94c1e6-1f3a-44b8-b1c6-94c8eb1dd07d","resolution":{"observed_at":"2026-08-10T21:02:02.950312Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T21:02:02.915806Z","title":"Learning multiple layers of features from tiny images","venue":null,"work_id":"2e71f455-a290-4a08-9110-b4d1cba656bf","year":2009},"citing_paper":{"arxiv_id":"2501.06650","last_updated":"2025-02-24T05:31:25Z","snapshot_observed_at":"2026-08-10T21:15:29.368518Z","submitted_at":"2025-01-11T22:20:20Z","title":"SafeSplit: A Novel Defense Against Client-Side Backdoor Attacks in Split Learning (Full Version)","version":2},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-10T21:02:01.810662Z"},"links":{"citing_paper":"/paper/2501.06650"},"observation_digest":"sha256:16e480b17e63ce39c74c912408d59b6422ac09f559901f0df1f9e8d09e0d0ed5","observation_id":"cb9643f2-69c5-4ea7-8555-05ba257ec24e","resolution":{"observed_at":"2026-08-10T21:02:02.922151Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T21:02:02.898319Z","title":"Baybfed: Bayesian backdoor defense for federated learning","venue":null,"work_id":"bd030338-d830-49ed-b0fe-1982dd3df561","year":2023},"citing_paper":{"arxiv_id":"2501.06650","last_updated":"2025-02-24T05:31:25Z","snapshot_observed_at":"2026-08-10T21:15:29.368518Z","submitted_at":"2025-01-11T22:20:20Z","title":"SafeSplit: A Novel Defense Against Client-Side Backdoor Attacks in Split Learning (Full Version)","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-10T21:02:01.816360Z"},"links":{"citing_paper":"/paper/2501.06650"},"observation_digest":"sha256:fd2183106db3a85fb76ad0a24aa5938513c3798ea4b7a5bb3398bb77b104c5a5","observation_id":"89f6bc36-4aac-40ac-9943-b0ce1e8f7128","resolution":{"observed_at":"2026-08-10T21:02:02.903791Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2308.00553","last_updated":"2023-08-01T13:47:27Z","snapshot_observed_at":"2026-08-08T02:22:59.134879Z","submitted_at":"2023-08-01T13:47:27Z","title":"FLAIRS: FPGA-Accelerated Inference-Resistant & Secure Federated Learning","version":1},"cited_work":{"arxiv_id":"2308.00553","doi":null,"metadata_source":"pith","pith_arxiv_id":"2308.00553","snapshot_observed_at":"2026-08-10T21:02:02.302144Z","title":"FLAIRS: FPGA-Accelerated Inference-Resistant & Secure Federated Learning","venue":"cs.CR","work_id":"943db845-0bee-457f-b0cb-78eaffe40a1e","year":2023},"citing_paper":{"arxiv_id":"2501.06650","last_updated":"2025-02-24T05:31:25Z","snapshot_observed_at":"2026-08-10T21:15:29.368518Z","submitted_at":"2025-01-11T22:20:20Z","title":"SafeSplit: A Novel Defense Against Client-Side Backdoor Attacks in Split Learning (Full Version)","version":2},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-10T21:02:01.821952Z"},"links":{"cited_paper":"/paper/2308.00553","citing_paper":"/paper/2501.06650"},"observation_digest":"sha256:1398dfc193b1062b2d18e789a0d878e2041e6b5d0a5e2a9638b896788fc99f98","observation_id":"de299c0f-a8e6-42ae-b2f2-4f889dc949ba","resolution":{"observed_at":"2026-08-10T21:02:02.308379Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2102.08504","last_updated":"2022-05-24T22:30:30Z","snapshot_observed_at":"2026-08-11T16:47:12.501527Z","submitted_at":"2021-02-17T00:01:49Z","title":"Label Leakage and Protection in Two-party Split Learning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2102.08504","snapshot_observed_at":"2026-08-10T21:02:01.826941Z","title":"Label leakage and protection in two-party split learning","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2501.06650","last_updated":"2025-02-24T05:31:25Z","snapshot_observed_at":"2026-08-10T21:15:29.368518Z","submitted_at":"2025-01-11T22:20:20Z","title":"SafeSplit: A Novel Defense Against Client-Side Backdoor Attacks in Split Learning (Full Version)","version":2},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-10T21:02:01.826941Z"},"links":{"cited_paper":"/paper/2102.08504","citing_paper":"/paper/2501.06650"},"observation_digest":"sha256:7bbeff107d3760997676f0310742ecf101cb1e20102418072044a360a3057494","observation_id":"fab6422d-cf7d-4448-9dbf-521753d817cf","resolution":{"observed_at":"2026-08-10T21:02:01.826941Z","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":"2026-08-10T21:02:02.877637Z","title":"Federated learning: Challenges, methods, and future directions","venue":null,"work_id":"45366914-f339-48fb-82eb-f37c0d8f8065","year":2020},"citing_paper":{"arxiv_id":"2501.06650","last_updated":"2025-02-24T05:31:25Z","snapshot_observed_at":"2026-08-10T21:15:29.368518Z","submitted_at":"2025-01-11T22:20:20Z","title":"SafeSplit: A Novel Defense Against Client-Side Backdoor Attacks in Split Learning (Full Version)","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-10T21:02:01.832013Z"},"links":{"citing_paper":"/paper/2501.06650"},"observation_digest":"sha256:12b9199592ee8cd708b05a61d20b5ca160d598fec71eae84635cab94b2bf572a","observation_id":"79a65a39-eda1-45d0-a13e-a3ae4bf9aafc","resolution":{"observed_at":"2026-08-10T21:02:02.883915Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2203.05222","last_updated":"2024-03-22T09:38:29Z","snapshot_observed_at":"2026-07-06T12:46:19.587730Z","submitted_at":"2022-03-10T08:02:03Z","title":"Similarity-based Label Inference Attack against Training and Inference of Split Learning","version":2},"cited_work":{"arxiv_id":"2203.05222","doi":null,"metadata_source":"pith","pith_arxiv_id":"2203.05222","snapshot_observed_at":"2026-08-10T21:02:02.250543Z","title":"Similarity-based Label Inference Attack against Training and Inference of Split Learning","venue":"cs.LG","work_id":"9985c33f-de72-4f7d-b53b-5ff380abc6ca","year":2022},"citing_paper":{"arxiv_id":"2501.06650","last_updated":"2025-02-24T05:31:25Z","snapshot_observed_at":"2026-08-10T21:15:29.368518Z","submitted_at":"2025-01-11T22:20:20Z","title":"SafeSplit: A Novel Defense Against Client-Side Backdoor Attacks in Split Learning (Full Version)","version":2},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-10T21:02:01.836557Z"},"links":{"cited_paper":"/paper/2203.05222","citing_paper":"/paper/2501.06650"},"observation_digest":"sha256:ee43d83e2e5e9e2d470e7ba53f4f153f7ba9479c02794ac546e71064ccd43a7d","observation_id":"d9257f93-ad23-4ea4-a128-436b916d2920","resolution":{"observed_at":"2026-08-10T21:02:02.258752Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T21:02:02.861443Z","title":"Similarity-based label inference attack against training and inference of split learning","venue":null,"work_id":"ad82035f-3795-47a9-a003-2e16ed69247b","year":2024},"citing_paper":{"arxiv_id":"2501.06650","last_updated":"2025-02-24T05:31:25Z","snapshot_observed_at":"2026-08-10T21:15:29.368518Z","submitted_at":"2025-01-11T22:20:20Z","title":"SafeSplit: A Novel Defense Against Client-Side Backdoor Attacks in Split Learning (Full Version)","version":2},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-10T21:02:01.842517Z"},"links":{"citing_paper":"/paper/2501.06650"},"observation_digest":"sha256:afb11f174d340a07bb63273aca28dbb6e8ca15551e6194fb2af07d39da47ea22","observation_id":"6a194584-a44b-4d44-aa39-e99da08bc9cd","resolution":{"observed_at":"2026-08-10T21:02:02.866219Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T21:02:02.843413Z","title":"Secure split learning against property inference, data reconstruction, and feature space hijacking attacks","venue":null,"work_id":"0cb382cc-324e-49c3-afb9-f0d38c46b137","year":2023},"citing_paper":{"arxiv_id":"2501.06650","last_updated":"2025-02-24T05:31:25Z","snapshot_observed_at":"2026-08-10T21:15:29.368518Z","submitted_at":"2025-01-11T22:20:20Z","title":"SafeSplit: A Novel Defense Against Client-Side Backdoor Attacks in Split Learning (Full Version)","version":2},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-10T21:02:01.847662Z"},"links":{"citing_paper":"/paper/2501.06650"},"observation_digest":"sha256:c25362769d6eeb93bc901799bbaa99071c57b19cf1ed35fb341598f6f78e5eef","observation_id":"3cf95ee1-6350-4fb2-8b3e-608ab99ed562","resolution":{"observed_at":"2026-08-10T21:02:02.849799Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T21:02:02.822493Z","title":"Federated learning: Collabora- tive Machine Learning without Centralized Training Data","venue":null,"work_id":"e002b42a-4cb7-4225-b674-51e814c3bf21","year":2017},"citing_paper":{"arxiv_id":"2501.06650","last_updated":"2025-02-24T05:31:25Z","snapshot_observed_at":"2026-08-10T21:15:29.368518Z","submitted_at":"2025-01-11T22:20:20Z","title":"SafeSplit: A Novel Defense Against Client-Side Backdoor Attacks in Split Learning (Full Version)","version":2},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-10T21:02:01.852805Z"},"links":{"citing_paper":"/paper/2501.06650"},"observation_digest":"sha256:fec860cfe723c25e66f498ddd22602cbfcd1a66ddcea35c52fed5f3786741f41","observation_id":"58825169-b0c6-49fe-9789-0abdf2035900","resolution":{"observed_at":"2026-08-10T21:02:02.828261Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T21:02:02.805005Z","title":"Brendan McMahan, Daniel Ramage, Kunal Talwar, and Li Zhang","venue":null,"work_id":"c83df290-da1f-494e-83bf-e812f118a084","year":2018},"citing_paper":{"arxiv_id":"2501.06650","last_updated":"2025-02-24T05:31:25Z","snapshot_observed_at":"2026-08-10T21:15:29.368518Z","submitted_at":"2025-01-11T22:20:20Z","title":"SafeSplit: A Novel Defense Against Client-Side Backdoor Attacks in Split Learning (Full Version)","version":2},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-10T21:02:01.858355Z"},"links":{"citing_paper":"/paper/2501.06650"},"observation_digest":"sha256:d84297da6fbfd8e3c0226f50d637b25864cac22d713616295163201a24f9cd27","observation_id":"f21c3a65-4516-49ac-8ee4-cd59eb317fa9","resolution":{"observed_at":"2026-08-10T21:02:02.810756Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1909.05125","last_updated":"2019-09-11T15:19:36Z","snapshot_observed_at":"2026-08-09T18:17:36.382771Z","submitted_at":"2019-09-11T15:19:36Z","title":"Byzantine-Robust Federated Machine Learning through Adaptive Model Averaging","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1909.05125","snapshot_observed_at":"2026-08-10T21:02:01.865031Z","title":"Co, and Emil C","venue":null,"work_id":null,"year":1909},"citing_paper":{"arxiv_id":"2501.06650","last_updated":"2025-02-24T05:31:25Z","snapshot_observed_at":"2026-08-10T21:15:29.368518Z","submitted_at":"2025-01-11T22:20:20Z","title":"SafeSplit: A Novel Defense Against Client-Side Backdoor Attacks in Split Learning (Full Version)","version":2},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-10T21:02:01.865031Z"},"links":{"cited_paper":"/paper/1909.05125","citing_paper":"/paper/2501.06650"},"observation_digest":"sha256:92524a45bed87a9f4145cb14a5f25b7c420dbbcd583429b6c8e847ce6db3efe1","observation_id":"0e8a345a-7903-411e-8ca1-24fc9a710214","resolution":{"observed_at":"2026-08-10T21:02:01.865031Z","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":"2026-08-10T21:02:02.787908Z","title":"Discrete cosine transform","venue":null,"work_id":"681b2f67-7dff-4321-9514-78b0002cc617","year":1974},"citing_paper":{"arxiv_id":"2501.06650","last_updated":"2025-02-24T05:31:25Z","snapshot_observed_at":"2026-08-10T21:15:29.368518Z","submitted_at":"2025-01-11T22:20:20Z","title":"SafeSplit: A Novel Defense Against Client-Side Backdoor Attacks in Split Learning (Full Version)","version":2},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-10T21:02:01.871052Z"},"links":{"citing_paper":"/paper/2501.06650"},"observation_digest":"sha256:b7a33d4157f489ecac9bfab63d8e6f9a8c1fe7b1e8d8525479d47e51b46a0886","observation_id":"37ce57c5-816f-456d-93fe-b5bd1c50ca38","resolution":{"observed_at":"2026-08-10T21:02:02.792936Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T21:02:02.768180Z","title":"Unleashing the tiger: Inference attacks on split learning","venue":null,"work_id":"fe322773-c04e-4f50-b803-9be584fe549d","year":2021},"citing_paper":{"arxiv_id":"2501.06650","last_updated":"2025-02-24T05:31:25Z","snapshot_observed_at":"2026-08-10T21:15:29.368518Z","submitted_at":"2025-01-11T22:20:20Z","title":"SafeSplit: A Novel Defense Against Client-Side Backdoor Attacks in Split Learning (Full Version)","version":2},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-10T21:02:01.876994Z"},"links":{"citing_paper":"/paper/2501.06650"},"observation_digest":"sha256:d94f1d3fe82c623decb8e753aa6c3c9487f53785ac7bc0c0d0dd5c90b3774bf0","observation_id":"4b010a3c-0b4a-419b-945a-c7f3f0f190f5","resolution":{"observed_at":"2026-08-10T21:02:02.775355Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1912.12115","last_updated":"2019-12-27T14:39:58Z","snapshot_observed_at":"2026-08-10T21:15:03.836658Z","submitted_at":"2019-12-27T14:39:58Z","title":"Split Learning for collaborative deep learning in healthcare","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1912.12115","snapshot_observed_at":"2026-08-10T21:02:01.881841Z","title":"Poirot, Praneeth Vepakomma, Ken Chang, Jayashree Kalpathy-Cramer, Rajiv Gupta, and Ramesh Raskar","venue":null,"work_id":null,"year":1912},"citing_paper":{"arxiv_id":"2501.06650","last_updated":"2025-02-24T05:31:25Z","snapshot_observed_at":"2026-08-10T21:15:29.368518Z","submitted_at":"2025-01-11T22:20:20Z","title":"SafeSplit: A Novel Defense Against Client-Side Backdoor Attacks in Split Learning (Full Version)","version":2},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-10T21:02:01.881841Z"},"links":{"cited_paper":"/paper/1912.12115","citing_paper":"/paper/2501.06650"},"observation_digest":"sha256:d90576c9e4e17e6dc4880f7dd003ef86648e1512c25fe92aa2471ac199d1fc7c","observation_id":"21da2765-42c9-46d8-8596-1b5872701838","resolution":{"observed_at":"2026-08-10T21:02:01.881841Z","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":"2026-08-10T21:02:02.750380Z","title":"Hamprecht, Yoshua Bengio, and Aaron Courville","venue":null,"work_id":"1cdf57ef-9a62-4471-b5dd-c2c787126fe9","year":2019},"citing_paper":{"arxiv_id":"2501.06650","last_updated":"2025-02-24T05:31:25Z","snapshot_observed_at":"2026-08-10T21:15:29.368518Z","submitted_at":"2025-01-11T22:20:20Z","title":"SafeSplit: A Novel Defense Against Client-Side Backdoor Attacks in Split Learning (Full Version)","version":2},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-10T21:02:01.887310Z"},"links":{"citing_paper":"/paper/2501.06650"},"observation_digest":"sha256:4b90cc172d780196b760c31d2e84ddcf55bf81d396fc36292fac28c3dc87ea87","observation_id":"9a590c06-cd09-4744-87e5-0cb56f54f462","resolution":{"observed_at":"2026-08-10T21:02:02.755625Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T21:02:02.733134Z","title":"Crowdguard: Federated backdoor detection in federated learning","venue":null,"work_id":"e9de6b38-f61a-4f9c-b6ea-353597a47374","year":2024},"citing_paper":{"arxiv_id":"2501.06650","last_updated":"2025-02-24T05:31:25Z","snapshot_observed_at":"2026-08-10T21:15:29.368518Z","submitted_at":"2025-01-11T22:20:20Z","title":"SafeSplit: A Novel Defense Against Client-Side Backdoor Attacks in Split Learning (Full Version)","version":2},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-10T21:02:01.894228Z"},"links":{"citing_paper":"/paper/2501.06650"},"observation_digest":"sha256:20722ee9d6dfb3d97a70e9f5d7fd6af6fca3c885fd4f92dcccac1953e8d79439","observation_id":"bdcd0995-6a06-43b9-b105-56423ef766a4","resolution":{"observed_at":"2026-08-10T21:02:02.738839Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T21:02:02.716151Z","title":"Safesplit: A novel defense against client-side backdoor attacks in split learning","venue":null,"work_id":"276428e2-91c4-4ad3-9b78-a1d5d67f8ccd","year":2025},"citing_paper":{"arxiv_id":"2501.06650","last_updated":"2025-02-24T05:31:25Z","snapshot_observed_at":"2026-08-10T21:15:29.368518Z","submitted_at":"2025-01-11T22:20:20Z","title":"SafeSplit: A Novel Defense Against Client-Side Backdoor Attacks in Split Learning (Full Version)","version":2},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-10T21:02:01.898917Z"},"links":{"citing_paper":"/paper/2501.06650"},"observation_digest":"sha256:f2fd109886cc86208acca2bceca1d0423a04c2f1250a48e9a2e32022c825047c","observation_id":"00c8bde6-c60e-4e3f-a463-cf9736c93c8a","resolution":{"observed_at":"2026-08-10T21:02:02.721339Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T21:02:02.699003Z","title":"Hidden trigger backdoor attacks","venue":null,"work_id":"53d4ad0c-55cb-43f5-b97e-fba4828f6d57","year":2020},"citing_paper":{"arxiv_id":"2501.06650","last_updated":"2025-02-24T05:31:25Z","snapshot_observed_at":"2026-08-10T21:15:29.368518Z","submitted_at":"2025-01-11T22:20:20Z","title":"SafeSplit: A Novel Defense Against Client-Side Backdoor Attacks in Split Learning (Full Version)","version":2},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-10T21:02:01.904194Z"},"links":{"citing_paper":"/paper/2501.06650"},"observation_digest":"sha256:e01080480231d19e1eafafe38ce538267e4f71d3eea409a8277b2610a454d830","observation_id":"d6842b15-ac85-4c04-86f4-fa138184076c","resolution":{"observed_at":"2026-08-10T21:02:02.704691Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T21:02:02.681453Z","title":"Auror: Defending Against Poisoning Attacks in Collaborative Deep Learning Systems","venue":null,"work_id":"b5ee2ca2-d0be-4cb6-9d1b-28f30866c9bc","year":2016},"citing_paper":{"arxiv_id":"2501.06650","last_updated":"2025-02-24T05:31:25Z","snapshot_observed_at":"2026-08-10T21:15:29.368518Z","submitted_at":"2025-01-11T22:20:20Z","title":"SafeSplit: A Novel Defense Against Client-Side Backdoor Attacks in Split Learning (Full Version)","version":2},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-10T21:02:01.909562Z"},"links":{"citing_paper":"/paper/2501.06650"},"observation_digest":"sha256:1041945bd080fe951fd5c5b32222641ebea9deaf5f7a1533f8909e563f3f913b","observation_id":"cb88b232-0176-4160-89ee-78999fee6bae","resolution":{"observed_at":"2026-08-10T21:02:02.687243Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T21:02:02.664044Z","title":"Manipulating sgd with data ordering attacks","venue":null,"work_id":"9ab1cd73-d1db-4f1d-85de-7842035a2388","year":2021},"citing_paper":{"arxiv_id":"2501.06650","last_updated":"2025-02-24T05:31:25Z","snapshot_observed_at":"2026-08-10T21:15:29.368518Z","submitted_at":"2025-01-11T22:20:20Z","title":"SafeSplit: A Novel Defense Against Client-Side Backdoor Attacks in Split Learning (Full Version)","version":2},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-10T21:02:01.916458Z"},"links":{"citing_paper":"/paper/2501.06650"},"observation_digest":"sha256:982ff1846920ddb8170026dba89e3432fb3158bc34380151a90cf99369192b2e","observation_id":"1d79611d-69be-4d3e-82c4-2742071b2f83","resolution":{"observed_at":"2026-08-10T21:02:02.669739Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T21:02:02.646855Z","title":"Very deep convolutional networks for large-scale image recognition","venue":null,"work_id":"139c6043-38f7-43b5-84df-7839b6dbc19d","year":2015},"citing_paper":{"arxiv_id":"2501.06650","last_updated":"2025-02-24T05:31:25Z","snapshot_observed_at":"2026-08-10T21:15:29.368518Z","submitted_at":"2025-01-11T22:20:20Z","title":"SafeSplit: A Novel Defense Against Client-Side Backdoor Attacks in Split Learning (Full Version)","version":2},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-10T21:02:01.921486Z"},"links":{"citing_paper":"/paper/2501.06650"},"observation_digest":"sha256:2bcba9e977415f3887146e79e7de6687a7064e19af4693d25c5b72d06d526f16","observation_id":"0a45b99a-4487-43b2-9dee-e7d8c0525345","resolution":{"observed_at":"2026-08-10T21:02:02.652358Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1909.09145","last_updated":"2019-09-18T21:43:33Z","snapshot_observed_at":"2026-08-10T03:36:04.130832Z","submitted_at":"2019-09-18T21:43:33Z","title":"Detailed comparison of communication efficiency of split learning and federated learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1909.09145","snapshot_observed_at":"2026-08-10T21:02:01.926602Z","title":"Detailed comparison of communication efficiency of split learning and federated learning","venue":null,"work_id":null,"year":1909},"citing_paper":{"arxiv_id":"2501.06650","last_updated":"2025-02-24T05:31:25Z","snapshot_observed_at":"2026-08-10T21:15:29.368518Z","submitted_at":"2025-01-11T22:20:20Z","title":"SafeSplit: A Novel Defense Against Client-Side Backdoor Attacks in Split Learning (Full Version)","version":2},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-10T21:02:01.926602Z"},"links":{"cited_paper":"/paper/1909.09145","citing_paper":"/paper/2501.06650"},"observation_digest":"sha256:eb85297f957531ff6911ce19c87cf6768e6d91db5d04abb566edf4a9e74e2975","observation_id":"e0212708-52dd-4754-87dd-f30d768580e2","resolution":{"observed_at":"2026-08-10T21:02:01.926602Z","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":"2026-08-10T21:02:02.629004Z","title":"The german traffic sign recognition benchmark: a multi-class classifica- tion competition","venue":null,"work_id":"71c1c816-ced6-4ee7-8bfe-8ee152870a4b","year":2011},"citing_paper":{"arxiv_id":"2501.06650","last_updated":"2025-02-24T05:31:25Z","snapshot_observed_at":"2026-08-10T21:15:29.368518Z","submitted_at":"2025-01-11T22:20:20Z","title":"SafeSplit: A Novel Defense Against Client-Side Backdoor Attacks in Split Learning (Full Version)","version":2},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-10T21:02:01.932004Z"},"links":{"citing_paper":"/paper/2501.06650"},"observation_digest":"sha256:52d7fd73c3a50249a494c1eaab94b153b22f592a8966b03c0ccf3b27ebf9003b","observation_id":"b4a9fb6d-f567-4727-9f1e-1d8e17115730","resolution":{"observed_at":"2026-08-10T21:02:02.635073Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T21:02:02.611566Z","title":"Going deeper with convolutions","venue":null,"work_id":"c52e595f-53de-4bdd-b3ef-d35508e9d6c2","year":2015},"citing_paper":{"arxiv_id":"2501.06650","last_updated":"2025-02-24T05:31:25Z","snapshot_observed_at":"2026-08-10T21:15:29.368518Z","submitted_at":"2025-01-11T22:20:20Z","title":"SafeSplit: A Novel Defense Against Client-Side Backdoor Attacks in Split Learning (Full Version)","version":2},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-10T21:02:01.936835Z"},"links":{"citing_paper":"/paper/2501.06650"},"observation_digest":"sha256:c328357d1b215a64dd8909fb3882f36078d78185cfab730c7bb047fd22d1adaa","observation_id":"1ca561a1-ef27-4eca-a563-9d031210b64a","resolution":{"observed_at":"2026-08-10T21:02:02.617439Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T21:02:02.592381Z","title":"On feasibility of server-side backdoor attacks on split learning","venue":null,"work_id":"45060028-e723-431e-b620-f9f0ed8c6c76","year":2023},"citing_paper":{"arxiv_id":"2501.06650","last_updated":"2025-02-24T05:31:25Z","snapshot_observed_at":"2026-08-10T21:15:29.368518Z","submitted_at":"2025-01-11T22:20:20Z","title":"SafeSplit: A Novel Defense Against Client-Side Backdoor Attacks in Split Learning (Full Version)","version":2},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-10T21:02:01.941482Z"},"links":{"citing_paper":"/paper/2501.06650"},"observation_digest":"sha256:f49a1a95513be57309d1b22448ef16f0329cb37bff69a50ebfb61226a595306b","observation_id":"b6231cfa-f9d2-4838-a072-768291a8be94","resolution":{"observed_at":"2026-08-10T21:02:02.598595Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T21:02:02.573224Z","title":"Advancements of federated learning towards privacy preser- vation: from federated learning to split learning","venue":null,"work_id":"3884ef03-4bb8-497f-a36f-b9b4a444010b","year":2021},"citing_paper":{"arxiv_id":"2501.06650","last_updated":"2025-02-24T05:31:25Z","snapshot_observed_at":"2026-08-10T21:15:29.368518Z","submitted_at":"2025-01-11T22:20:20Z","title":"SafeSplit: A Novel Defense Against Client-Side Backdoor Attacks in Split Learning (Full Version)","version":2},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-10T21:02:01.945596Z"},"links":{"citing_paper":"/paper/2501.06650"},"observation_digest":"sha256:f851a908e06fad6f562d49b40e70217b363b2fc74d59f5c9b30c771eebf30fd5","observation_id":"13b94cfb-39b7-4da8-a6e9-6445b0d335a4","resolution":{"observed_at":"2026-08-10T21:02:02.579587Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T21:02:02.554692Z","title":"How to prove it: A structured approach","venue":null,"work_id":"c173076a-246a-464c-ab77-914b76cd25f6","year":2019},"citing_paper":{"arxiv_id":"2501.06650","last_updated":"2025-02-24T05:31:25Z","snapshot_observed_at":"2026-08-10T21:15:29.368518Z","submitted_at":"2025-01-11T22:20:20Z","title":"SafeSplit: A Novel Defense Against Client-Side Backdoor Attacks in Split Learning (Full Version)","version":2},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-10T21:02:01.950654Z"},"links":{"citing_paper":"/paper/2501.06650"},"observation_digest":"sha256:4ef8354b3a34a3db54d2911851305ebaff6399bd6f665ce74b9075f04cf0cd07","observation_id":"2670401f-ba99-424b-9c95-ce17b2e86f57","resolution":{"observed_at":"2026-08-10T21:02:02.560930Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1812.00564","last_updated":"2018-12-03T05:43:20Z","snapshot_observed_at":"2026-08-04T04:23:43.839800Z","submitted_at":"2018-12-03T05:43:20Z","title":"Split learning for health: Distributed deep learning without sharing raw patient data","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1812.00564","snapshot_observed_at":"2026-08-10T21:02:01.955217Z","title":"Split learning for health: Distributed deep learning without sharing raw patient data","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2501.06650","last_updated":"2025-02-24T05:31:25Z","snapshot_observed_at":"2026-08-10T21:15:29.368518Z","submitted_at":"2025-01-11T22:20:20Z","title":"SafeSplit: A Novel Defense Against Client-Side Backdoor Attacks in Split Learning (Full Version)","version":2},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-10T21:02:01.955217Z"},"links":{"cited_paper":"/paper/1812.00564","citing_paper":"/paper/2501.06650"},"observation_digest":"sha256:23ce99d51ff4185b1961a4ef127cf58aa89c7023daf0cf434ec36b449f412b40","observation_id":"1f08548f-009d-44f5-b8ff-822415e8e432","resolution":{"observed_at":"2026-08-10T21:02:01.955217Z","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":"2026-08-10T21:02:02.536169Z","title":"Flare: defending federated learning against model poisoning attacks via latent space representations","venue":null,"work_id":"bdbdc9c8-9cad-42c5-bdec-59058c72b72a","year":2022},"citing_paper":{"arxiv_id":"2501.06650","last_updated":"2025-02-24T05:31:25Z","snapshot_observed_at":"2026-08-10T21:15:29.368518Z","submitted_at":"2025-01-11T22:20:20Z","title":"SafeSplit: A Novel Defense Against Client-Side Backdoor Attacks in Split Learning (Full Version)","version":2},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-10T21:02:01.960341Z"},"links":{"citing_paper":"/paper/2501.06650"},"observation_digest":"sha256:da794fb6c9fc944ea981f2ecda08c3a5ec781111b9c91aea54dc56c7cd4f2644","observation_id":"6fbc5f11-caa8-4f53-9135-c5348e105c95","resolution":{"observed_at":"2026-08-10T21:02:02.542263Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T21:02:02.515841Z","title":"Fast algorithms for the discrete w transform and for the discrete fourier transform","venue":null,"work_id":"63df543c-f6e4-477c-93bb-4ecf74d4fe07","year":1984},"citing_paper":{"arxiv_id":"2501.06650","last_updated":"2025-02-24T05:31:25Z","snapshot_observed_at":"2026-08-10T21:15:29.368518Z","submitted_at":"2025-01-11T22:20:20Z","title":"SafeSplit: A Novel Defense Against Client-Side Backdoor Attacks in Split Learning (Full Version)","version":2},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-10T21:02:01.966211Z"},"links":{"citing_paper":"/paper/2501.06650"},"observation_digest":"sha256:b06eeb7eaf52804e694dedf4acff7dd0783edc065e641e7e62755418968b9c25","observation_id":"ea6989f1-5165-43fd-a3e5-038fa91fcb5c","resolution":{"observed_at":"2026-08-10T21:02:02.521897Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T21:02:02.495779Z","title":"Backdoor attacks against deep learning systems in the physical world","venue":null,"work_id":"fd90ea5c-0cfe-4305-9229-11f79987a5c6","year":2021},"citing_paper":{"arxiv_id":"2501.06650","last_updated":"2025-02-24T05:31:25Z","snapshot_observed_at":"2026-08-10T21:15:29.368518Z","submitted_at":"2025-01-11T22:20:20Z","title":"SafeSplit: A Novel Defense Against Client-Side Backdoor Attacks in Split Learning (Full Version)","version":2},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-10T21:02:01.971702Z"},"links":{"citing_paper":"/paper/2501.06650"},"observation_digest":"sha256:50e241d73a841b2a8f2db9f62b1566599536c745ea99445081721e6fed8fff24","observation_id":"a39b8ef1-55f0-4f27-8355-c823b62c5b97","resolution":{"observed_at":"2026-08-10T21:02:02.502318Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T21:02:02.475210Z","title":"Micronnet: A highly compact deep convolutional neural network archi- tecture for real-time embedded traffic sign classification","venue":null,"work_id":"3eedeef1-5aa0-4960-8c37-0caf952f95a8","year":2018},"citing_paper":{"arxiv_id":"2501.06650","last_updated":"2025-02-24T05:31:25Z","snapshot_observed_at":"2026-08-10T21:15:29.368518Z","submitted_at":"2025-01-11T22:20:20Z","title":"SafeSplit: A Novel Defense Against Client-Side Backdoor Attacks in Split Learning (Full Version)","version":2},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-10T21:02:01.976537Z"},"links":{"citing_paper":"/paper/2501.06650"},"observation_digest":"sha256:8678c11e37fab8e87b69b0d425f570fd0be10d07010f7fa1709976bdb52fb23f","observation_id":"c6e6d713-a34f-413e-9ccb-88f68b07dbc4","resolution":{"observed_at":"2026-08-10T21:02:02.482032Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T21:02:02.458037Z","title":"A study on quantization effects of dct based compression","venue":null,"work_id":"9911eca2-4efe-41f0-a811-fd8e606370dc","year":2017},"citing_paper":{"arxiv_id":"2501.06650","last_updated":"2025-02-24T05:31:25Z","snapshot_observed_at":"2026-08-10T21:15:29.368518Z","submitted_at":"2025-01-11T22:20:20Z","title":"SafeSplit: A Novel Defense Against Client-Side Backdoor Attacks in Split Learning (Full Version)","version":2},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-10T21:02:01.981384Z"},"links":{"citing_paper":"/paper/2501.06650"},"observation_digest":"sha256:3f3dcda7ef59082d96d680a4efac2b37ff577c152562cda4f8db687db81c93f7","observation_id":"72678e54-d474-4271-9a65-93c400a43791","resolution":{"observed_at":"2026-08-10T21:02:02.463336Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T21:02:01.986185Z","title":"Fashion-mnist: a novel image dataset for benchmarking machine learning algorithms, 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2501.06650","last_updated":"2025-02-24T05:31:25Z","snapshot_observed_at":"2026-08-10T21:15:29.368518Z","submitted_at":"2025-01-11T22:20:20Z","title":"SafeSplit: A Novel Defense Against Client-Side Backdoor Attacks in Split Learning (Full Version)","version":2},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-10T21:02:01.986185Z"},"links":{"citing_paper":"/paper/2501.06650"},"observation_digest":"sha256:83e6accd51966d828befd4e7b8be79e6e95b6c6c7c47fc76e0414cddc7ebf60c","observation_id":"50083cf8-2ef6-4b99-935e-d2c6b818516e","resolution":{"observed_at":"2026-08-10T21:02:01.986185Z","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":"2026-08-10T21:02:02.426732Z","title":"DBA: Distributed backdoor attacks against federated learning","venue":null,"work_id":"0765a23e-3999-478f-bf20-112f579fa6a3","year":2020},"citing_paper":{"arxiv_id":"2501.06650","last_updated":"2025-02-24T05:31:25Z","snapshot_observed_at":"2026-08-10T21:15:29.368518Z","submitted_at":"2025-01-11T22:20:20Z","title":"SafeSplit: A Novel Defense Against Client-Side Backdoor Attacks in Split Learning (Full Version)","version":2},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-10T21:02:01.991594Z"},"links":{"citing_paper":"/paper/2501.06650"},"observation_digest":"sha256:e99c8654a7abb1e5406159bb1219b3432e203948a3448e9da4b9031f7bbf67ee","observation_id":"14a03f00-5843-461d-9e7d-70961a41f3d5","resolution":{"observed_at":"2026-08-10T21:02:02.431838Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T21:02:02.408367Z","title":"Training behavior of deep neural network in frequency domain","venue":null,"work_id":"91f046c3-94f8-4375-8a9f-f10be07b604a","year":2019},"citing_paper":{"arxiv_id":"2501.06650","last_updated":"2025-02-24T05:31:25Z","snapshot_observed_at":"2026-08-10T21:15:29.368518Z","submitted_at":"2025-01-11T22:20:20Z","title":"SafeSplit: A Novel Defense Against Client-Side Backdoor Attacks in Split Learning (Full Version)","version":2},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-10T21:02:01.996302Z"},"links":{"citing_paper":"/paper/2501.06650"},"observation_digest":"sha256:c91e6b7a1176bf2889a46d1ad12c0044f87984c41cecb83f6b1344d8ba681cdf","observation_id":"9921cd6f-bc6b-406d-be45-7fea8903c32d","resolution":{"observed_at":"2026-08-10T21:02:02.414089Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2203.02073","last_updated":"2022-03-04T00:35:03Z","snapshot_observed_at":"2026-08-11T11:37:02.451079Z","submitted_at":"2022-03-04T00:35:03Z","title":"Differentially Private Label Protection in Split Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2203.02073","snapshot_observed_at":"2026-08-10T21:02:02.001136Z","title":"Differentially private label protection in split learning","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2501.06650","last_updated":"2025-02-24T05:31:25Z","snapshot_observed_at":"2026-08-10T21:15:29.368518Z","submitted_at":"2025-01-11T22:20:20Z","title":"SafeSplit: A Novel Defense Against Client-Side Backdoor Attacks in Split Learning (Full Version)","version":2},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-10T21:02:02.001136Z"},"links":{"cited_paper":"/paper/2203.02073","citing_paper":"/paper/2501.06650"},"observation_digest":"sha256:d11157d79fb0392517894b37cae4493cab979885dbbb18d38103bd5173a01706","observation_id":"c2ec2967-31cf-4eab-bbee-f36700fcc1d4","resolution":{"observed_at":"2026-08-10T21:02:02.001136Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2212.06378","last_updated":"2022-12-13T05:26:31Z","snapshot_observed_at":"2026-08-03T07:04:23.390921Z","submitted_at":"2022-12-13T05:26:31Z","title":"Robust Split Federated Learning for U-shaped Medical Image Networks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2212.06378","snapshot_observed_at":"2026-08-10T21:02:02.006971Z","title":"Robust split federated learning for u-shaped medical image networks","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2501.06650","last_updated":"2025-02-24T05:31:25Z","snapshot_observed_at":"2026-08-10T21:15:29.368518Z","submitted_at":"2025-01-11T22:20:20Z","title":"SafeSplit: A Novel Defense Against Client-Side Backdoor Attacks in Split Learning (Full Version)","version":2},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-10T21:02:02.006971Z"},"links":{"cited_paper":"/paper/2212.06378","citing_paper":"/paper/2501.06650"},"observation_digest":"sha256:7034c39099e4d86e5d63094290fb97b166f232a12d39aaf75c164fd8476cb0b7","observation_id":"4edbf0e8-112b-40e1-9dc5-333267d50aee","resolution":{"observed_at":"2026-08-10T21:02:02.006971Z","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":"2026-08-10T21:02:02.385577Z","title":"How to backdoor split learning","venue":null,"work_id":"458ec1ec-b891-425a-ae4d-fc30e0ad52a9","year":2023},"citing_paper":{"arxiv_id":"2501.06650","last_updated":"2025-02-24T05:31:25Z","snapshot_observed_at":"2026-08-10T21:15:29.368518Z","submitted_at":"2025-01-11T22:20:20Z","title":"SafeSplit: A Novel Defense Against Client-Side Backdoor Attacks in Split Learning (Full Version)","version":2},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-10T21:02:02.012433Z"},"links":{"citing_paper":"/paper/2501.06650"},"observation_digest":"sha256:4492796726e4617433db305f13a3ce270742cd975e1b7c2811ae1994ee3acb41","observation_id":"a68c80cd-ef38-42d3-8cb8-9a2c5357cb51","resolution":{"observed_at":"2026-08-10T21:02:02.393779Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T21:02:02.357940Z","title":"Chronic poisoning: Backdoor attack against split learning","venue":null,"work_id":"2d4e3b0d-3dc7-4abf-a77f-2092b99515c0","year":2024},"citing_paper":{"arxiv_id":"2501.06650","last_updated":"2025-02-24T05:31:25Z","snapshot_observed_at":"2026-08-10T21:15:29.368518Z","submitted_at":"2025-01-11T22:20:20Z","title":"SafeSplit: A Novel Defense Against Client-Side Backdoor Attacks in Split Learning (Full Version)","version":2},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-10T21:02:02.018450Z"},"links":{"citing_paper":"/paper/2501.06650"},"observation_digest":"sha256:c8576f0a46a9770178c55380ecdbd53cf7bf3f52515449cf2149584ddf9b887b","observation_id":"26a07cc2-3d1e-4265-a802-ca10d29acec9","resolution":{"observed_at":"2026-08-10T21:02:02.363391Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1605.07146","last_updated":"2017-06-14T06:06:48Z","snapshot_observed_at":"2026-08-08T14:57:17.868613Z","submitted_at":"2016-05-23T19:27:13Z","title":"Wide Residual Networks","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1605.07146","snapshot_observed_at":"2026-08-10T21:02:02.023901Z","title":"Wide residual networks","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2501.06650","last_updated":"2025-02-24T05:31:25Z","snapshot_observed_at":"2026-08-10T21:15:29.368518Z","submitted_at":"2025-01-11T22:20:20Z","title":"SafeSplit: A Novel Defense Against Client-Side Backdoor Attacks in Split Learning (Full Version)","version":2},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-10T21:02:02.023901Z"},"links":{"cited_paper":"/paper/1605.07146","citing_paper":"/paper/2501.06650"},"observation_digest":"sha256:fa42009205a70f615116fc45d26c16971943ea99bde0dc441926875b3ae02768","observation_id":"27658d13-4622-4556-a9ad-b6bd07a66771","resolution":{"observed_at":"2026-08-10T21:02:02.023901Z","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":"2026-08-10T21:02:02.338939Z","title":"Label inference attack based on soft label towards two-party split learning","venue":null,"work_id":"9e57c7fe-90ec-489b-a8be-2e83ac103655","year":2023},"citing_paper":{"arxiv_id":"2501.06650","last_updated":"2025-02-24T05:31:25Z","snapshot_observed_at":"2026-08-10T21:15:29.368518Z","submitted_at":"2025-01-11T22:20:20Z","title":"SafeSplit: A Novel Defense Against Client-Side Backdoor Attacks in Split Learning (Full Version)","version":2},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-10T21:02:02.029798Z"},"links":{"citing_paper":"/paper/2501.06650"},"observation_digest":"sha256:6f5a93a0a9ad81ce08e0bb2a95c714457fd0fa97b44a1199f8feb3891c338155","observation_id":"e4ac39a2-9145-4388-86d9-359fed84d820","resolution":{"observed_at":"2026-08-10T21:02:02.345738Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2310.10483","last_updated":"2025-03-21T22:27:01Z","snapshot_observed_at":"2026-07-06T16:33:55.369704Z","submitted_at":"2023-10-16T15:03:55Z","title":"Passive Inference Attacks on Split Learning via Adversarial Regularization","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.10483","snapshot_observed_at":"2026-08-10T21:02:02.035875Z","title":"Passive inference attacks on split learning via adversarial regularization","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.06650","last_updated":"2025-02-24T05:31:25Z","snapshot_observed_at":"2026-08-10T21:15:29.368518Z","submitted_at":"2025-01-11T22:20:20Z","title":"SafeSplit: A Novel Defense Against Client-Side Backdoor Attacks in Split Learning (Full Version)","version":2},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-10T21:02:02.035875Z"},"links":{"cited_paper":"/paper/2310.10483","citing_paper":"/paper/2501.06650"},"observation_digest":"sha256:1bda32c488c3650dd5f81ae74e6ab26f499b0055300eb884e395227c5990174d","observation_id":"ecab5552-3e3d-4407-868e-52358e6bd9e8","resolution":{"observed_at":"2026-08-10T21:02:02.035875Z","resolver_source":null,"status":"malformed_identifier"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2501.06650","last_updated":"2025-02-24T05:31:25Z","latest_version":2,"primary_category":"cs.CR","snapshot_observed_at":"2026-08-10T21:15:29.368518Z","submitted_at":"2025-01-11T22:20:20Z","title":"SafeSplit: A Novel Defense Against Client-Side Backdoor Attacks in Split Learning (Full Version)"},"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":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"thesis":"As of 11 August 2026, this Paper Citation Record lists 68 of 68 outbound references and 0 inbound Pith citation observations for arXiv:2501.06650."}