{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:YZ6DZRXY2GMPIJG5VBBZB2H4J2","short_pith_number":"pith:YZ6DZRXY","schema_version":"1.0","canonical_sha256":"c67c3cc6f8d198f424dda84390e8fc4ea86e718c0a72e74f5683e5e2d4527b8c","source":{"kind":"arxiv","id":"2310.10483","version":6},"attestation_state":"computed","paper":{"title":"Passive Inference Attacks on Split Learning via Adversarial Regularization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CR","authors_text":"Beng Chin Ooi, Xiaochen Zhu, Xiaokui Xiao, Xinjian Luo, YangFan Jiang, Yuncheng Wu","submitted_at":"2023-10-16T15:03:55Z","abstract_excerpt":"Split Learning (SL) has emerged as a practical and efficient alternative to traditional federated learning. While previous attempts to attack SL have often relied on overly strong assumptions or targeted easily exploitable models, we seek to develop more capable attacks. We introduce SDAR, a novel attack framework against SL with an honest-but-curious server. SDAR leverages auxiliary data and adversarial regularization to learn a decodable simulator of the client's private model, which can effectively infer the client's private features under the vanilla SL, and both features and labels under "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2310.10483","kind":"arxiv","version":6},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2023-10-16T15:03:55Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"819dc713b66df2d2afc2ecd5b086923759ab24aafac1d947d8008bdddb69dfe5","abstract_canon_sha256":"ceb5d45e70a152a570249aea16b552bdb28660085209b77d7bd3cbb2258ace7f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:37:05.320718Z","signature_b64":"sojN+5oyQkN5Lh0eZIpq2guKNOOAMtKth+BfsCexn59cCmm5zmn7XdOaB2DrpTFjbXQCJrMy6UYbdtoO0Wd0BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c67c3cc6f8d198f424dda84390e8fc4ea86e718c0a72e74f5683e5e2d4527b8c","last_reissued_at":"2026-07-05T10:37:05.319827Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:37:05.319827Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Passive Inference Attacks on Split Learning via Adversarial Regularization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CR","authors_text":"Beng Chin Ooi, Xiaochen Zhu, Xiaokui Xiao, Xinjian Luo, YangFan Jiang, Yuncheng Wu","submitted_at":"2023-10-16T15:03:55Z","abstract_excerpt":"Split Learning (SL) has emerged as a practical and efficient alternative to traditional federated learning. While previous attempts to attack SL have often relied on overly strong assumptions or targeted easily exploitable models, we seek to develop more capable attacks. We introduce SDAR, a novel attack framework against SL with an honest-but-curious server. SDAR leverages auxiliary data and adversarial regularization to learn a decodable simulator of the client's private model, which can effectively infer the client's private features under the vanilla SL, and both features and labels under "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.10483","kind":"arxiv","version":6},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2310.10483/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2310.10483","created_at":"2026-07-05T10:37:05.319947+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.10483v6","created_at":"2026-07-05T10:37:05.319947+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.10483","created_at":"2026-07-05T10:37:05.319947+00:00"},{"alias_kind":"pith_short_12","alias_value":"YZ6DZRXY2GMP","created_at":"2026-07-05T10:37:05.319947+00:00"},{"alias_kind":"pith_short_16","alias_value":"YZ6DZRXY2GMPIJG5","created_at":"2026-07-05T10:37:05.319947+00:00"},{"alias_kind":"pith_short_8","alias_value":"YZ6DZRXY","created_at":"2026-07-05T10:37:05.319947+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.18710","citing_title":"Image Prompt Reconstruction Attacks on Distributed MLLM Inference Frameworks","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YZ6DZRXY2GMPIJG5VBBZB2H4J2","json":"https://pith.science/pith/YZ6DZRXY2GMPIJG5VBBZB2H4J2.json","graph_json":"https://pith.science/api/pith-number/YZ6DZRXY2GMPIJG5VBBZB2H4J2/graph.json","events_json":"https://pith.science/api/pith-number/YZ6DZRXY2GMPIJG5VBBZB2H4J2/events.json","paper":"https://pith.science/paper/YZ6DZRXY"},"agent_actions":{"view_html":"https://pith.science/pith/YZ6DZRXY2GMPIJG5VBBZB2H4J2","download_json":"https://pith.science/pith/YZ6DZRXY2GMPIJG5VBBZB2H4J2.json","view_paper":"https://pith.science/paper/YZ6DZRXY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.10483&json=true","fetch_graph":"https://pith.science/api/pith-number/YZ6DZRXY2GMPIJG5VBBZB2H4J2/graph.json","fetch_events":"https://pith.science/api/pith-number/YZ6DZRXY2GMPIJG5VBBZB2H4J2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YZ6DZRXY2GMPIJG5VBBZB2H4J2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YZ6DZRXY2GMPIJG5VBBZB2H4J2/action/storage_attestation","attest_author":"https://pith.science/pith/YZ6DZRXY2GMPIJG5VBBZB2H4J2/action/author_attestation","sign_citation":"https://pith.science/pith/YZ6DZRXY2GMPIJG5VBBZB2H4J2/action/citation_signature","submit_replication":"https://pith.science/pith/YZ6DZRXY2GMPIJG5VBBZB2H4J2/action/replication_record"}},"created_at":"2026-07-05T10:37:05.319947+00:00","updated_at":"2026-07-05T10:37:05.319947+00:00"}