{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:ZLH57TO5PN4CU4SX3OG3W3GA5C","short_pith_number":"pith:ZLH57TO5","schema_version":"1.0","canonical_sha256":"cacfdfcddd7b782a7257db8dbb6cc0e8af2dbb1df3b2fadbb52c05c8d2d0ab98","source":{"kind":"arxiv","id":"2105.02295","version":1},"attestation_state":"computed","paper":{"title":"Byzantine-Robust and Privacy-Preserving Framework for FedML","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AR","cs.LG"],"primary_cat":"cs.CR","authors_text":"Chuan Guo, Hanieh Hashemi, Murali Annavaram, Yongqin Wang","submitted_at":"2021-05-05T19:36:21Z","abstract_excerpt":"Federated learning has emerged as a popular paradigm for collaboratively training a model from data distributed among a set of clients. This learning setting presents, among others, two unique challenges: how to protect privacy of the clients' data during training, and how to ensure integrity of the trained model. We propose a two-pronged solution that aims to address both challenges under a single framework. First, we propose to create secure enclaves using a trusted execution environment (TEE) within the server. Each client can then encrypt their gradients and send them to verifiable enclave"},"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":"2105.02295","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2021-05-05T19:36:21Z","cross_cats_sorted":["cs.AR","cs.LG"],"title_canon_sha256":"a5f0ffb35f2de96ae2ba78d41ded254ea63b1c0b8313a9f76c581214570b76af","abstract_canon_sha256":"34a415fe0317c5bc9da379e06ee1a686fc03764cbea1a968e9b8867fbe4ad064"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:38:00.063093Z","signature_b64":"276gHIArkfsTyAn8z6Uk+l4RrIFz9/xyQqxftvOf7GLfohZ1PO2+GqukTxa4hC67u/5TthNGhEQmbN8FHoPvCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cacfdfcddd7b782a7257db8dbb6cc0e8af2dbb1df3b2fadbb52c05c8d2d0ab98","last_reissued_at":"2026-07-05T02:38:00.062518Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:38:00.062518Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Byzantine-Robust and Privacy-Preserving Framework for FedML","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AR","cs.LG"],"primary_cat":"cs.CR","authors_text":"Chuan Guo, Hanieh Hashemi, Murali Annavaram, Yongqin Wang","submitted_at":"2021-05-05T19:36:21Z","abstract_excerpt":"Federated learning has emerged as a popular paradigm for collaboratively training a model from data distributed among a set of clients. This learning setting presents, among others, two unique challenges: how to protect privacy of the clients' data during training, and how to ensure integrity of the trained model. We propose a two-pronged solution that aims to address both challenges under a single framework. First, we propose to create secure enclaves using a trusted execution environment (TEE) within the server. Each client can then encrypt their gradients and send them to verifiable enclave"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.02295","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/2105.02295/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":"2105.02295","created_at":"2026-07-05T02:38:00.062594+00:00"},{"alias_kind":"arxiv_version","alias_value":"2105.02295v1","created_at":"2026-07-05T02:38:00.062594+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.02295","created_at":"2026-07-05T02:38:00.062594+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZLH57TO5PN4C","created_at":"2026-07-05T02:38:00.062594+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZLH57TO5PN4CU4SX","created_at":"2026-07-05T02:38:00.062594+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZLH57TO5","created_at":"2026-07-05T02:38:00.062594+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.04899","citing_title":"DIST-FL: Enhancing Security for TEE-based Aggregation in Federated Learning","ref_index":61,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZLH57TO5PN4CU4SX3OG3W3GA5C","json":"https://pith.science/pith/ZLH57TO5PN4CU4SX3OG3W3GA5C.json","graph_json":"https://pith.science/api/pith-number/ZLH57TO5PN4CU4SX3OG3W3GA5C/graph.json","events_json":"https://pith.science/api/pith-number/ZLH57TO5PN4CU4SX3OG3W3GA5C/events.json","paper":"https://pith.science/paper/ZLH57TO5"},"agent_actions":{"view_html":"https://pith.science/pith/ZLH57TO5PN4CU4SX3OG3W3GA5C","download_json":"https://pith.science/pith/ZLH57TO5PN4CU4SX3OG3W3GA5C.json","view_paper":"https://pith.science/paper/ZLH57TO5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2105.02295&json=true","fetch_graph":"https://pith.science/api/pith-number/ZLH57TO5PN4CU4SX3OG3W3GA5C/graph.json","fetch_events":"https://pith.science/api/pith-number/ZLH57TO5PN4CU4SX3OG3W3GA5C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZLH57TO5PN4CU4SX3OG3W3GA5C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZLH57TO5PN4CU4SX3OG3W3GA5C/action/storage_attestation","attest_author":"https://pith.science/pith/ZLH57TO5PN4CU4SX3OG3W3GA5C/action/author_attestation","sign_citation":"https://pith.science/pith/ZLH57TO5PN4CU4SX3OG3W3GA5C/action/citation_signature","submit_replication":"https://pith.science/pith/ZLH57TO5PN4CU4SX3OG3W3GA5C/action/replication_record"}},"created_at":"2026-07-05T02:38:00.062594+00:00","updated_at":"2026-07-05T02:38:00.062594+00:00"}