{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:PQP3GPJMLOX5APYJ3E2KWWKWG6","short_pith_number":"pith:PQP3GPJM","schema_version":"1.0","canonical_sha256":"7c1fb33d2c5bafd03f09d934ab5956379808817046dfbd21c488968f1a65db4b","source":{"kind":"arxiv","id":"2012.13995","version":3},"attestation_state":"computed","paper":{"title":"FLTrust: Byzantine-robust Federated Learning via Trust Bootstrapping","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.DC"],"primary_cat":"cs.CR","authors_text":"Jia Liu, Minghong Fang, Neil Zhenqiang Gong, Xiaoyu Cao","submitted_at":"2020-12-27T18:43:39Z","abstract_excerpt":"Byzantine-robust federated learning aims to enable a service provider to learn an accurate global model when a bounded number of clients are malicious. The key idea of existing Byzantine-robust federated learning methods is that the service provider performs statistical analysis among the clients' local model updates and removes suspicious ones, before aggregating them to update the global model. However, malicious clients can still corrupt the global models in these methods via sending carefully crafted local model updates to the service provider. The fundamental reason is that there is no ro"},"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":"2012.13995","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2020-12-27T18:43:39Z","cross_cats_sorted":["cs.AI","cs.DC"],"title_canon_sha256":"584389355ffc6b1b41e7caf4c24e1c6fcdc209c9557731987f00de701d11be21","abstract_canon_sha256":"3e773a65ff7b870970cd434c35aa977bb5c0e5962a0b62600bf071de8df81691"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:13:21.551060Z","signature_b64":"PefzSXT7QkB/hWSjdWc+0lsaiKxK2uItWnZrFtX0auwLlm/+60EcMvcOa514d9q53UhnGXGkjkrfo7g2u+PKBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7c1fb33d2c5bafd03f09d934ab5956379808817046dfbd21c488968f1a65db4b","last_reissued_at":"2026-07-05T04:13:21.550607Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:13:21.550607Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FLTrust: Byzantine-robust Federated Learning via Trust Bootstrapping","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.DC"],"primary_cat":"cs.CR","authors_text":"Jia Liu, Minghong Fang, Neil Zhenqiang Gong, Xiaoyu Cao","submitted_at":"2020-12-27T18:43:39Z","abstract_excerpt":"Byzantine-robust federated learning aims to enable a service provider to learn an accurate global model when a bounded number of clients are malicious. The key idea of existing Byzantine-robust federated learning methods is that the service provider performs statistical analysis among the clients' local model updates and removes suspicious ones, before aggregating them to update the global model. However, malicious clients can still corrupt the global models in these methods via sending carefully crafted local model updates to the service provider. The fundamental reason is that there is no ro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.13995","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/2012.13995/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":"2012.13995","created_at":"2026-07-05T04:13:21.550653+00:00"},{"alias_kind":"arxiv_version","alias_value":"2012.13995v3","created_at":"2026-07-05T04:13:21.550653+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.13995","created_at":"2026-07-05T04:13:21.550653+00:00"},{"alias_kind":"pith_short_12","alias_value":"PQP3GPJMLOX5","created_at":"2026-07-05T04:13:21.550653+00:00"},{"alias_kind":"pith_short_16","alias_value":"PQP3GPJMLOX5APYJ","created_at":"2026-07-05T04:13:21.550653+00:00"},{"alias_kind":"pith_short_8","alias_value":"PQP3GPJM","created_at":"2026-07-05T04:13:21.550653+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":15,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22700","citing_title":"SCRUB-FL: Sanitizing and Cleansing Representations via Unlearning of Backdoors","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2606.27622","citing_title":"FoggyTrust: Robust Federated Learning with Hierarchical Trust Networks","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31066","citing_title":"Secure-CHG: A Comprehensive Framework for Robust and Fair Federated Learning via Hybrid Defense and Contribution-Aware Trust","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30650","citing_title":"When AI Meets Wall Street: A Survey on Trustworthy AI in Fintech","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2411.12220","citing_title":"DeTrigger: A Gradient-Centric Approach to Backdoor Attack Mitigation in Federated Learning","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17508","citing_title":"BESplit: Bias-Compensated Split Federated Learning with Evidential Aggregation","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2507.16134","citing_title":"DP2Guard: A Lightweight and Byzantine-Robust Privacy-Preserving Federated Learning Scheme for Industrial IoT","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2508.12672","citing_title":"Robust Federated Learning under Adversarial Attacks via Loss-Based Client Clustering","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2511.14715","citing_title":"FLARE: Adaptive Multi-Dimensional Reputation for Robust Client Reliability in Federated Learning","ref_index":66,"is_internal_anchor":false},{"citing_arxiv_id":"2603.29328","citing_title":"Beyond Corner Patches: Semantics-Aware Backdoor Attack in Federated Learning","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11122","citing_title":"FedSurrogate: Backdoor Defense in Federated Learning via Layer Criticality and Surrogate Replacement","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03213","citing_title":"When Agents Handle Secrets: A Survey of Confidential Computing for Agentic AI","ref_index":72,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27434","citing_title":"AdaBFL: Multi-Layer Defensive Adaptive Aggregation for Bzantine-Robust Federated Learning","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08616","citing_title":"Robust Server Defense Against Unreliable Clients in One-Shot Fair Collaborative Machine Learning","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03213","citing_title":"When Agents Handle Secrets: A Survey of Confidential Computing for Agentic AI","ref_index":72,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PQP3GPJMLOX5APYJ3E2KWWKWG6","json":"https://pith.science/pith/PQP3GPJMLOX5APYJ3E2KWWKWG6.json","graph_json":"https://pith.science/api/pith-number/PQP3GPJMLOX5APYJ3E2KWWKWG6/graph.json","events_json":"https://pith.science/api/pith-number/PQP3GPJMLOX5APYJ3E2KWWKWG6/events.json","paper":"https://pith.science/paper/PQP3GPJM"},"agent_actions":{"view_html":"https://pith.science/pith/PQP3GPJMLOX5APYJ3E2KWWKWG6","download_json":"https://pith.science/pith/PQP3GPJMLOX5APYJ3E2KWWKWG6.json","view_paper":"https://pith.science/paper/PQP3GPJM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2012.13995&json=true","fetch_graph":"https://pith.science/api/pith-number/PQP3GPJMLOX5APYJ3E2KWWKWG6/graph.json","fetch_events":"https://pith.science/api/pith-number/PQP3GPJMLOX5APYJ3E2KWWKWG6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PQP3GPJMLOX5APYJ3E2KWWKWG6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PQP3GPJMLOX5APYJ3E2KWWKWG6/action/storage_attestation","attest_author":"https://pith.science/pith/PQP3GPJMLOX5APYJ3E2KWWKWG6/action/author_attestation","sign_citation":"https://pith.science/pith/PQP3GPJMLOX5APYJ3E2KWWKWG6/action/citation_signature","submit_replication":"https://pith.science/pith/PQP3GPJMLOX5APYJ3E2KWWKWG6/action/replication_record"}},"created_at":"2026-07-05T04:13:21.550653+00:00","updated_at":"2026-07-05T04:13:21.550653+00:00"}