{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:4E3HFFOHSHNE5BZINHUMPDYITY","short_pith_number":"pith:4E3HFFOH","schema_version":"1.0","canonical_sha256":"e1367295c791da4e872869e8c78f089e2db3714e11aa4027dc36e901731a1b5c","source":{"kind":"arxiv","id":"2305.01267","version":1},"attestation_state":"computed","paper":{"title":"DABS: Data-Agnostic Backdoor attack at the Server in Federated Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.CR","authors_text":"Jun Zhang, Sen Li, Wenqiang Sun, Yuchang Sun","submitted_at":"2023-05-02T09:04:34Z","abstract_excerpt":"Federated learning (FL) attempts to train a global model by aggregating local models from distributed devices under the coordination of a central server. However, the existence of a large number of heterogeneous devices makes FL vulnerable to various attacks, especially the stealthy backdoor attack. Backdoor attack aims to trick a neural network to misclassify data to a target label by injecting specific triggers while keeping correct predictions on original training data. Existing works focus on client-side attacks which try to poison the global model by modifying the local datasets. In this "},"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":"2305.01267","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2023-05-02T09:04:34Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"10e30321f83693f1a635e6f26dc546ee11945733cff0233dfd93fa49ad57a106","abstract_canon_sha256":"7f0fe13640a16dc81746ca808cc0908b29af919e813f8bb116fe209ba345b544"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:06:23.580129Z","signature_b64":"3WoROOm/EalksupG6hasa8wVc8XXpMTyQ5wTmJIdZhVf0nkWCu2TM3bpewcmTAh0ntRq2mG6zcAZtCNJpkZJCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e1367295c791da4e872869e8c78f089e2db3714e11aa4027dc36e901731a1b5c","last_reissued_at":"2026-07-05T06:06:23.579657Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:06:23.579657Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DABS: Data-Agnostic Backdoor attack at the Server in Federated Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.CR","authors_text":"Jun Zhang, Sen Li, Wenqiang Sun, Yuchang Sun","submitted_at":"2023-05-02T09:04:34Z","abstract_excerpt":"Federated learning (FL) attempts to train a global model by aggregating local models from distributed devices under the coordination of a central server. However, the existence of a large number of heterogeneous devices makes FL vulnerable to various attacks, especially the stealthy backdoor attack. Backdoor attack aims to trick a neural network to misclassify data to a target label by injecting specific triggers while keeping correct predictions on original training data. Existing works focus on client-side attacks which try to poison the global model by modifying the local datasets. In this "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.01267","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/2305.01267/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":"2305.01267","created_at":"2026-07-05T06:06:23.579715+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.01267v1","created_at":"2026-07-05T06:06:23.579715+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.01267","created_at":"2026-07-05T06:06:23.579715+00:00"},{"alias_kind":"pith_short_12","alias_value":"4E3HFFOHSHNE","created_at":"2026-07-05T06:06:23.579715+00:00"},{"alias_kind":"pith_short_16","alias_value":"4E3HFFOHSHNE5BZI","created_at":"2026-07-05T06:06:23.579715+00:00"},{"alias_kind":"pith_short_8","alias_value":"4E3HFFOH","created_at":"2026-07-05T06:06:23.579715+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.27511","citing_title":"When the Aggregator Cheats: Data-Free Backdoors in Federated LLM-based QA Systems","ref_index":42,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4E3HFFOHSHNE5BZINHUMPDYITY","json":"https://pith.science/pith/4E3HFFOHSHNE5BZINHUMPDYITY.json","graph_json":"https://pith.science/api/pith-number/4E3HFFOHSHNE5BZINHUMPDYITY/graph.json","events_json":"https://pith.science/api/pith-number/4E3HFFOHSHNE5BZINHUMPDYITY/events.json","paper":"https://pith.science/paper/4E3HFFOH"},"agent_actions":{"view_html":"https://pith.science/pith/4E3HFFOHSHNE5BZINHUMPDYITY","download_json":"https://pith.science/pith/4E3HFFOHSHNE5BZINHUMPDYITY.json","view_paper":"https://pith.science/paper/4E3HFFOH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.01267&json=true","fetch_graph":"https://pith.science/api/pith-number/4E3HFFOHSHNE5BZINHUMPDYITY/graph.json","fetch_events":"https://pith.science/api/pith-number/4E3HFFOHSHNE5BZINHUMPDYITY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4E3HFFOHSHNE5BZINHUMPDYITY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4E3HFFOHSHNE5BZINHUMPDYITY/action/storage_attestation","attest_author":"https://pith.science/pith/4E3HFFOHSHNE5BZINHUMPDYITY/action/author_attestation","sign_citation":"https://pith.science/pith/4E3HFFOHSHNE5BZINHUMPDYITY/action/citation_signature","submit_replication":"https://pith.science/pith/4E3HFFOHSHNE5BZINHUMPDYITY/action/replication_record"}},"created_at":"2026-07-05T06:06:23.579715+00:00","updated_at":"2026-07-05T06:06:23.579715+00:00"}