{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:4OCFFSBQNQH7EQ7HMMAD3TCV54","short_pith_number":"pith:4OCFFSBQ","schema_version":"1.0","canonical_sha256":"e38452c8306c0ff243e763003dcc55ef3367a00f5c38dcf677085cd168add3d4","source":{"kind":"arxiv","id":"2303.10837","version":3},"attestation_state":"computed","paper":{"title":"FedML-HE: An Efficient Homomorphic-Encryption-Based Privacy-Preserving Federated Learning System","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.LG","authors_text":"Carlee Joe-Wong, Chaoyang He, Jiajun Gu, Salman Avestimehr, Shanshan Han, Srivatsan Ravi, Weizhao Jin, Yuhang Yao","submitted_at":"2023-03-20T02:44:35Z","abstract_excerpt":"Federated Learning trains machine learning models on distributed devices by aggregating local model updates instead of local data. However, privacy concerns arise as the aggregated local models on the server may reveal sensitive personal information by inversion attacks. Privacy-preserving methods, such as homomorphic encryption (HE), then become necessary for FL training. Despite HE's privacy advantages, its applications suffer from impractical overheads, especially for foundation models. In this paper, we present FedML-HE, the first practical federated learning system with efficient HE-based"},"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":"2303.10837","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-03-20T02:44:35Z","cross_cats_sorted":["cs.CR"],"title_canon_sha256":"653a73a54cf010fae0c993a23c84b2a8797c58049313923b91f63bf2525e47f6","abstract_canon_sha256":"327b2a6db247177535f6970e50c4cb6391b5a4bc2ec1cc608d05818a5f2017b5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:32:28.822490Z","signature_b64":"Mp1i65bXjSUUmGQyi5Uy/cp3ETkxqabjx1jTZgRdy0QVsLTwhV15dsN/rLgtG/9n9QTcekxOCmPbz6na8JMuAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e38452c8306c0ff243e763003dcc55ef3367a00f5c38dcf677085cd168add3d4","last_reissued_at":"2026-07-05T08:32:28.822003Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:32:28.822003Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FedML-HE: An Efficient Homomorphic-Encryption-Based Privacy-Preserving Federated Learning System","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.LG","authors_text":"Carlee Joe-Wong, Chaoyang He, Jiajun Gu, Salman Avestimehr, Shanshan Han, Srivatsan Ravi, Weizhao Jin, Yuhang Yao","submitted_at":"2023-03-20T02:44:35Z","abstract_excerpt":"Federated Learning trains machine learning models on distributed devices by aggregating local model updates instead of local data. However, privacy concerns arise as the aggregated local models on the server may reveal sensitive personal information by inversion attacks. Privacy-preserving methods, such as homomorphic encryption (HE), then become necessary for FL training. Despite HE's privacy advantages, its applications suffer from impractical overheads, especially for foundation models. In this paper, we present FedML-HE, the first practical federated learning system with efficient HE-based"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.10837","kind":"arxiv","version":3},"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/2303.10837/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":"2303.10837","created_at":"2026-07-05T08:32:28.822057+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.10837v3","created_at":"2026-07-05T08:32:28.822057+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.10837","created_at":"2026-07-05T08:32:28.822057+00:00"},{"alias_kind":"pith_short_12","alias_value":"4OCFFSBQNQH7","created_at":"2026-07-05T08:32:28.822057+00:00"},{"alias_kind":"pith_short_16","alias_value":"4OCFFSBQNQH7EQ7H","created_at":"2026-07-05T08:32:28.822057+00:00"},{"alias_kind":"pith_short_8","alias_value":"4OCFFSBQ","created_at":"2026-07-05T08:32:28.822057+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06612","citing_title":"PRoVeFL: Private Robust and Verifiable Aggregation in Federated Learning","ref_index":21,"is_internal_anchor":true},{"citing_arxiv_id":"2412.20495","citing_title":"A Multiparty Homomorphic Encryption Approach to Confidential Federated Kaplan Meier Survival Analysis","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12168","citing_title":"On What We Can Learn from Low-Resolution Data","ref_index":92,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4OCFFSBQNQH7EQ7HMMAD3TCV54","json":"https://pith.science/pith/4OCFFSBQNQH7EQ7HMMAD3TCV54.json","graph_json":"https://pith.science/api/pith-number/4OCFFSBQNQH7EQ7HMMAD3TCV54/graph.json","events_json":"https://pith.science/api/pith-number/4OCFFSBQNQH7EQ7HMMAD3TCV54/events.json","paper":"https://pith.science/paper/4OCFFSBQ"},"agent_actions":{"view_html":"https://pith.science/pith/4OCFFSBQNQH7EQ7HMMAD3TCV54","download_json":"https://pith.science/pith/4OCFFSBQNQH7EQ7HMMAD3TCV54.json","view_paper":"https://pith.science/paper/4OCFFSBQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.10837&json=true","fetch_graph":"https://pith.science/api/pith-number/4OCFFSBQNQH7EQ7HMMAD3TCV54/graph.json","fetch_events":"https://pith.science/api/pith-number/4OCFFSBQNQH7EQ7HMMAD3TCV54/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4OCFFSBQNQH7EQ7HMMAD3TCV54/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4OCFFSBQNQH7EQ7HMMAD3TCV54/action/storage_attestation","attest_author":"https://pith.science/pith/4OCFFSBQNQH7EQ7HMMAD3TCV54/action/author_attestation","sign_citation":"https://pith.science/pith/4OCFFSBQNQH7EQ7HMMAD3TCV54/action/citation_signature","submit_replication":"https://pith.science/pith/4OCFFSBQNQH7EQ7HMMAD3TCV54/action/replication_record"}},"created_at":"2026-07-05T08:32:28.822057+00:00","updated_at":"2026-07-05T08:32:28.822057+00:00"}