{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:2MHU2GVU6ZSSTBJB5Y3WGJWGJ2","short_pith_number":"pith:2MHU2GVU","schema_version":"1.0","canonical_sha256":"d30f4d1ab4f665298521ee376326c64ea7c663410b62cc3d92d546d9ca31788d","source":{"kind":"arxiv","id":"2112.02918","version":2},"attestation_state":"computed","paper":{"title":"When the Curious Abandon Honesty: Federated Learning Is Not Private","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","cs.DC"],"primary_cat":"cs.LG","authors_text":"Adam Dziedzic, Ali Shahin Shamsabadi, Franziska Boenisch, Ilia Shumailov, Nicolas Papernot, Roei Schuster","submitted_at":"2021-12-06T10:37:03Z","abstract_excerpt":"In federated learning (FL), data does not leave personal devices when they are jointly training a machine learning model. Instead, these devices share gradients, parameters, or other model updates, with a central party (e.g., a company) coordinating the training. Because data never \"leaves\" personal devices, FL is often presented as privacy-preserving. Yet, recently it was shown that this protection is but a thin facade, as even a passive, honest-but-curious attacker observing gradients can reconstruct data of individual users contributing to the protocol. In this work, we show a novel data re"},"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":"2112.02918","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-12-06T10:37:03Z","cross_cats_sorted":["cs.CR","cs.DC"],"title_canon_sha256":"c1eaebf1057b8bea48750437ef64631e1c5bd9c40213128ce99223a90b3b08dc","abstract_canon_sha256":"7bd82539e5c17adabdd832e1847cfec516c9f47707149d5b5d75a70ddc11f3b0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:00:29.204936Z","signature_b64":"8CNyOaNuuFgE0eopj27lUkHpeI3jgjQRcuMrADhk99cmSxuD9NofyXzjiNskCapn4KxEECdXkKUi6Pez9OlFBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d30f4d1ab4f665298521ee376326c64ea7c663410b62cc3d92d546d9ca31788d","last_reissued_at":"2026-07-05T06:00:29.204519Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:00:29.204519Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"When the Curious Abandon Honesty: Federated Learning Is Not Private","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","cs.DC"],"primary_cat":"cs.LG","authors_text":"Adam Dziedzic, Ali Shahin Shamsabadi, Franziska Boenisch, Ilia Shumailov, Nicolas Papernot, Roei Schuster","submitted_at":"2021-12-06T10:37:03Z","abstract_excerpt":"In federated learning (FL), data does not leave personal devices when they are jointly training a machine learning model. Instead, these devices share gradients, parameters, or other model updates, with a central party (e.g., a company) coordinating the training. Because data never \"leaves\" personal devices, FL is often presented as privacy-preserving. Yet, recently it was shown that this protection is but a thin facade, as even a passive, honest-but-curious attacker observing gradients can reconstruct data of individual users contributing to the protocol. In this work, we show a novel data re"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.02918","kind":"arxiv","version":2},"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/2112.02918/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":"2112.02918","created_at":"2026-07-05T06:00:29.204575+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.02918v2","created_at":"2026-07-05T06:00:29.204575+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.02918","created_at":"2026-07-05T06:00:29.204575+00:00"},{"alias_kind":"pith_short_12","alias_value":"2MHU2GVU6ZSS","created_at":"2026-07-05T06:00:29.204575+00:00"},{"alias_kind":"pith_short_16","alias_value":"2MHU2GVU6ZSSTBJB","created_at":"2026-07-05T06:00:29.204575+00:00"},{"alias_kind":"pith_short_8","alias_value":"2MHU2GVU","created_at":"2026-07-05T06:00:29.204575+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.31208","citing_title":"Probing Memorization of Tabular In-Context Learning","ref_index":42,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2MHU2GVU6ZSSTBJB5Y3WGJWGJ2","json":"https://pith.science/pith/2MHU2GVU6ZSSTBJB5Y3WGJWGJ2.json","graph_json":"https://pith.science/api/pith-number/2MHU2GVU6ZSSTBJB5Y3WGJWGJ2/graph.json","events_json":"https://pith.science/api/pith-number/2MHU2GVU6ZSSTBJB5Y3WGJWGJ2/events.json","paper":"https://pith.science/paper/2MHU2GVU"},"agent_actions":{"view_html":"https://pith.science/pith/2MHU2GVU6ZSSTBJB5Y3WGJWGJ2","download_json":"https://pith.science/pith/2MHU2GVU6ZSSTBJB5Y3WGJWGJ2.json","view_paper":"https://pith.science/paper/2MHU2GVU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.02918&json=true","fetch_graph":"https://pith.science/api/pith-number/2MHU2GVU6ZSSTBJB5Y3WGJWGJ2/graph.json","fetch_events":"https://pith.science/api/pith-number/2MHU2GVU6ZSSTBJB5Y3WGJWGJ2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2MHU2GVU6ZSSTBJB5Y3WGJWGJ2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2MHU2GVU6ZSSTBJB5Y3WGJWGJ2/action/storage_attestation","attest_author":"https://pith.science/pith/2MHU2GVU6ZSSTBJB5Y3WGJWGJ2/action/author_attestation","sign_citation":"https://pith.science/pith/2MHU2GVU6ZSSTBJB5Y3WGJWGJ2/action/citation_signature","submit_replication":"https://pith.science/pith/2MHU2GVU6ZSSTBJB5Y3WGJWGJ2/action/replication_record"}},"created_at":"2026-07-05T06:00:29.204575+00:00","updated_at":"2026-07-05T06:00:29.204575+00:00"}