{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:UW7YQE4LEIRCHO3LD3WLPFTZJ6","short_pith_number":"pith:UW7YQE4L","schema_version":"1.0","canonical_sha256":"a5bf88138b222223bb6b1eecb796794fbaa9a75a74ef78135afcbb3b1242fcda","source":{"kind":"arxiv","id":"2606.22928","version":1},"attestation_state":"computed","paper":{"title":"HADES: Privacy-Preserving Federated Learning via Selective Feature Encryption and Hybrid Model Fusion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CR","authors_text":"Erg\\\"un Batuhan Kaynak, Kerem Bayramoglu, Sinem Sav","submitted_at":"2026-06-22T07:05:53Z","abstract_excerpt":"In this paper, we address the challenge of privacy-preserving training in federated learning (FL) by introducing a novel framework that selectively encrypts only the most privacy-sensitive features while leaving the remaining data and the corresponding model portion unencrypted. We propose HADES, a hybrid system that identifies and encrypts the most critical features, ensuring both privacy protection and computational efficiency. Unlike fully encrypted FL training pipelines, which suffer from high computational overhead, HADES integrates an encrypted and non-encrypted training pipeline via a f"},"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":"2606.22928","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2026-06-22T07:05:53Z","cross_cats_sorted":[],"title_canon_sha256":"84631008545cec4da752d18d52c8d7b916466df4fe11f8e6f66e74668eeec8da","abstract_canon_sha256":"9f40b083faf1f5dc2a1e657652fee5e026fbacd7d50e8c628652aa761fd3c7f7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T03:14:04.514534Z","signature_b64":"rtdV/y2eBsFvQ7oomEc6ylkWq+h2cTiRSZee9JkBFUhMRTbaWhWDX4Ll/GMW17ifXT9GCw2GHkUDXog+dfrLDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a5bf88138b222223bb6b1eecb796794fbaa9a75a74ef78135afcbb3b1242fcda","last_reissued_at":"2026-06-23T03:14:04.514123Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T03:14:04.514123Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HADES: Privacy-Preserving Federated Learning via Selective Feature Encryption and Hybrid Model Fusion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CR","authors_text":"Erg\\\"un Batuhan Kaynak, Kerem Bayramoglu, Sinem Sav","submitted_at":"2026-06-22T07:05:53Z","abstract_excerpt":"In this paper, we address the challenge of privacy-preserving training in federated learning (FL) by introducing a novel framework that selectively encrypts only the most privacy-sensitive features while leaving the remaining data and the corresponding model portion unencrypted. We propose HADES, a hybrid system that identifies and encrypts the most critical features, ensuring both privacy protection and computational efficiency. Unlike fully encrypted FL training pipelines, which suffer from high computational overhead, HADES integrates an encrypted and non-encrypted training pipeline via a f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.22928","kind":"arxiv","version":1},"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/2606.22928/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":"2606.22928","created_at":"2026-06-23T03:14:04.514184+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.22928v1","created_at":"2026-06-23T03:14:04.514184+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.22928","created_at":"2026-06-23T03:14:04.514184+00:00"},{"alias_kind":"pith_short_12","alias_value":"UW7YQE4LEIRC","created_at":"2026-06-23T03:14:04.514184+00:00"},{"alias_kind":"pith_short_16","alias_value":"UW7YQE4LEIRCHO3L","created_at":"2026-06-23T03:14:04.514184+00:00"},{"alias_kind":"pith_short_8","alias_value":"UW7YQE4L","created_at":"2026-06-23T03:14:04.514184+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UW7YQE4LEIRCHO3LD3WLPFTZJ6","json":"https://pith.science/pith/UW7YQE4LEIRCHO3LD3WLPFTZJ6.json","graph_json":"https://pith.science/api/pith-number/UW7YQE4LEIRCHO3LD3WLPFTZJ6/graph.json","events_json":"https://pith.science/api/pith-number/UW7YQE4LEIRCHO3LD3WLPFTZJ6/events.json","paper":"https://pith.science/paper/UW7YQE4L"},"agent_actions":{"view_html":"https://pith.science/pith/UW7YQE4LEIRCHO3LD3WLPFTZJ6","download_json":"https://pith.science/pith/UW7YQE4LEIRCHO3LD3WLPFTZJ6.json","view_paper":"https://pith.science/paper/UW7YQE4L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.22928&json=true","fetch_graph":"https://pith.science/api/pith-number/UW7YQE4LEIRCHO3LD3WLPFTZJ6/graph.json","fetch_events":"https://pith.science/api/pith-number/UW7YQE4LEIRCHO3LD3WLPFTZJ6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UW7YQE4LEIRCHO3LD3WLPFTZJ6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UW7YQE4LEIRCHO3LD3WLPFTZJ6/action/storage_attestation","attest_author":"https://pith.science/pith/UW7YQE4LEIRCHO3LD3WLPFTZJ6/action/author_attestation","sign_citation":"https://pith.science/pith/UW7YQE4LEIRCHO3LD3WLPFTZJ6/action/citation_signature","submit_replication":"https://pith.science/pith/UW7YQE4LEIRCHO3LD3WLPFTZJ6/action/replication_record"}},"created_at":"2026-06-23T03:14:04.514184+00:00","updated_at":"2026-06-23T03:14:04.514184+00:00"}