{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:F5QX4YJGMDHDLFSV5CSD5OWQZP","short_pith_number":"pith:F5QX4YJG","schema_version":"1.0","canonical_sha256":"2f617e612660ce359655e8a43ebad0cbf3647965698349310bfa71a5953adc4a","source":{"kind":"arxiv","id":"2503.23511","version":1},"attestation_state":"computed","paper":{"title":"Buffer is All You Need: Defending Federated Learning against Backdoor Attacks under Non-iids via Buffering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CR","authors_text":"Danjue Chen, Ning Wang, Shixiong Li, Tao Li, Xingyu Lyu, Yang Xiao, Yimin Chen","submitted_at":"2025-03-30T16:46:14Z","abstract_excerpt":"Federated Learning (FL) is a popular paradigm enabling clients to jointly train a global model without sharing raw data. However, FL is known to be vulnerable towards backdoor attacks due to its distributed nature. As participants, attackers can upload model updates that effectively compromise FL. What's worse, existing defenses are mostly designed under independent-and-identically-distributed (iid) settings, hence neglecting the fundamental non-iid characteristic of FL. Here we propose FLBuff for tackling backdoor attacks even under non-iids. The main challenge for such defenses is that non-i"},"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":"2503.23511","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2025-03-30T16:46:14Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3e8e8ffa47e0d7894611e1125b88e9745d245236acf6e7619ae12a3a7c03a3a3","abstract_canon_sha256":"382a0af83f7c8bd9af000a6d06b4c08d00b35fbce381941c16bb9d115f0ff853"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:41:37.715279Z","signature_b64":"qPfY+qrZCvaX7yAvxCFljwTUs35RTEmH2/2hXoX0jZBrQOJ4MILN7WYO/iqNwvPRWNJAvxi17Us7ohN3ILiSCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2f617e612660ce359655e8a43ebad0cbf3647965698349310bfa71a5953adc4a","last_reissued_at":"2026-07-05T10:41:37.714809Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:41:37.714809Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Buffer is All You Need: Defending Federated Learning against Backdoor Attacks under Non-iids via Buffering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CR","authors_text":"Danjue Chen, Ning Wang, Shixiong Li, Tao Li, Xingyu Lyu, Yang Xiao, Yimin Chen","submitted_at":"2025-03-30T16:46:14Z","abstract_excerpt":"Federated Learning (FL) is a popular paradigm enabling clients to jointly train a global model without sharing raw data. However, FL is known to be vulnerable towards backdoor attacks due to its distributed nature. As participants, attackers can upload model updates that effectively compromise FL. What's worse, existing defenses are mostly designed under independent-and-identically-distributed (iid) settings, hence neglecting the fundamental non-iid characteristic of FL. Here we propose FLBuff for tackling backdoor attacks even under non-iids. The main challenge for such defenses is that non-i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.23511","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/2503.23511/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":"2503.23511","created_at":"2026-07-05T10:41:37.714872+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.23511v1","created_at":"2026-07-05T10:41:37.714872+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.23511","created_at":"2026-07-05T10:41:37.714872+00:00"},{"alias_kind":"pith_short_12","alias_value":"F5QX4YJGMDHD","created_at":"2026-07-05T10:41:37.714872+00:00"},{"alias_kind":"pith_short_16","alias_value":"F5QX4YJGMDHDLFSV","created_at":"2026-07-05T10:41:37.714872+00:00"},{"alias_kind":"pith_short_8","alias_value":"F5QX4YJG","created_at":"2026-07-05T10:41:37.714872+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/F5QX4YJGMDHDLFSV5CSD5OWQZP","json":"https://pith.science/pith/F5QX4YJGMDHDLFSV5CSD5OWQZP.json","graph_json":"https://pith.science/api/pith-number/F5QX4YJGMDHDLFSV5CSD5OWQZP/graph.json","events_json":"https://pith.science/api/pith-number/F5QX4YJGMDHDLFSV5CSD5OWQZP/events.json","paper":"https://pith.science/paper/F5QX4YJG"},"agent_actions":{"view_html":"https://pith.science/pith/F5QX4YJGMDHDLFSV5CSD5OWQZP","download_json":"https://pith.science/pith/F5QX4YJGMDHDLFSV5CSD5OWQZP.json","view_paper":"https://pith.science/paper/F5QX4YJG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.23511&json=true","fetch_graph":"https://pith.science/api/pith-number/F5QX4YJGMDHDLFSV5CSD5OWQZP/graph.json","fetch_events":"https://pith.science/api/pith-number/F5QX4YJGMDHDLFSV5CSD5OWQZP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F5QX4YJGMDHDLFSV5CSD5OWQZP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F5QX4YJGMDHDLFSV5CSD5OWQZP/action/storage_attestation","attest_author":"https://pith.science/pith/F5QX4YJGMDHDLFSV5CSD5OWQZP/action/author_attestation","sign_citation":"https://pith.science/pith/F5QX4YJGMDHDLFSV5CSD5OWQZP/action/citation_signature","submit_replication":"https://pith.science/pith/F5QX4YJGMDHDLFSV5CSD5OWQZP/action/replication_record"}},"created_at":"2026-07-05T10:41:37.714872+00:00","updated_at":"2026-07-05T10:41:37.714872+00:00"}