{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:6H46HC5PJPIJBTFYOBKTBXNHOZ","short_pith_number":"pith:6H46HC5P","schema_version":"1.0","canonical_sha256":"f1f9e38baf4bd090ccb8705530dda776772ef5090a4ce4176df59b37625d819e","source":{"kind":"arxiv","id":"2104.14380","version":2},"attestation_state":"computed","paper":{"title":"PPFL: Privacy-preserving Federated Learning with Trusted Execution Environments","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.DC","cs.LG"],"primary_cat":"cs.CR","authors_text":"Diego Perino, Eduard Marin, Fan Mo, Hamed Haddadi, Kleomenis Katevas, Nicolas Kourtellis","submitted_at":"2021-04-29T14:46:16Z","abstract_excerpt":"We propose and implement a Privacy-preserving Federated Learning ($PPFL$) framework for mobile systems to limit privacy leakages in federated learning. Leveraging the widespread presence of Trusted Execution Environments (TEEs) in high-end and mobile devices, we utilize TEEs on clients for local training, and on servers for secure aggregation, so that model/gradient updates are hidden from adversaries. Challenged by the limited memory size of current TEEs, we leverage greedy layer-wise training to train each model's layer inside the trusted area until its convergence. The performance evaluatio"},"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":"2104.14380","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CR","submitted_at":"2021-04-29T14:46:16Z","cross_cats_sorted":["cs.DC","cs.LG"],"title_canon_sha256":"1a9f627dcaf1afea3bcd3cc80d2b5ec5d1b08ef337187b232de1f98519e554b3","abstract_canon_sha256":"bd31a95bf3c30906ec3618981a6cb4705466933a32cd90251a022bc323dd3509"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:53:02.047644Z","signature_b64":"HImIEfLvevkf0NpAzi/Xvtw4LyAcJep4yTer+3Hj65PwMN1sYUd78DF+C0AVdZPG4wTIKdGBibkLwTPxNoTsDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f1f9e38baf4bd090ccb8705530dda776772ef5090a4ce4176df59b37625d819e","last_reissued_at":"2026-07-05T02:53:02.047293Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:53:02.047293Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PPFL: Privacy-preserving Federated Learning with Trusted Execution Environments","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.DC","cs.LG"],"primary_cat":"cs.CR","authors_text":"Diego Perino, Eduard Marin, Fan Mo, Hamed Haddadi, Kleomenis Katevas, Nicolas Kourtellis","submitted_at":"2021-04-29T14:46:16Z","abstract_excerpt":"We propose and implement a Privacy-preserving Federated Learning ($PPFL$) framework for mobile systems to limit privacy leakages in federated learning. Leveraging the widespread presence of Trusted Execution Environments (TEEs) in high-end and mobile devices, we utilize TEEs on clients for local training, and on servers for secure aggregation, so that model/gradient updates are hidden from adversaries. Challenged by the limited memory size of current TEEs, we leverage greedy layer-wise training to train each model's layer inside the trusted area until its convergence. The performance evaluatio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.14380","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/2104.14380/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":"2104.14380","created_at":"2026-07-05T02:53:02.047363+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.14380v2","created_at":"2026-07-05T02:53:02.047363+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.14380","created_at":"2026-07-05T02:53:02.047363+00:00"},{"alias_kind":"pith_short_12","alias_value":"6H46HC5PJPIJ","created_at":"2026-07-05T02:53:02.047363+00:00"},{"alias_kind":"pith_short_16","alias_value":"6H46HC5PJPIJBTFY","created_at":"2026-07-05T02:53:02.047363+00:00"},{"alias_kind":"pith_short_8","alias_value":"6H46HC5P","created_at":"2026-07-05T02:53:02.047363+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/6H46HC5PJPIJBTFYOBKTBXNHOZ","json":"https://pith.science/pith/6H46HC5PJPIJBTFYOBKTBXNHOZ.json","graph_json":"https://pith.science/api/pith-number/6H46HC5PJPIJBTFYOBKTBXNHOZ/graph.json","events_json":"https://pith.science/api/pith-number/6H46HC5PJPIJBTFYOBKTBXNHOZ/events.json","paper":"https://pith.science/paper/6H46HC5P"},"agent_actions":{"view_html":"https://pith.science/pith/6H46HC5PJPIJBTFYOBKTBXNHOZ","download_json":"https://pith.science/pith/6H46HC5PJPIJBTFYOBKTBXNHOZ.json","view_paper":"https://pith.science/paper/6H46HC5P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.14380&json=true","fetch_graph":"https://pith.science/api/pith-number/6H46HC5PJPIJBTFYOBKTBXNHOZ/graph.json","fetch_events":"https://pith.science/api/pith-number/6H46HC5PJPIJBTFYOBKTBXNHOZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6H46HC5PJPIJBTFYOBKTBXNHOZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6H46HC5PJPIJBTFYOBKTBXNHOZ/action/storage_attestation","attest_author":"https://pith.science/pith/6H46HC5PJPIJBTFYOBKTBXNHOZ/action/author_attestation","sign_citation":"https://pith.science/pith/6H46HC5PJPIJBTFYOBKTBXNHOZ/action/citation_signature","submit_replication":"https://pith.science/pith/6H46HC5PJPIJBTFYOBKTBXNHOZ/action/replication_record"}},"created_at":"2026-07-05T02:53:02.047363+00:00","updated_at":"2026-07-05T02:53:02.047363+00:00"}