{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:EW2I64MWO5HOTSW4CYLWS7SQWO","short_pith_number":"pith:EW2I64MW","schema_version":"1.0","canonical_sha256":"25b48f7196774ee9cadc1617697e50b3ae96ef1d628d9b89ac724a91f8031fae","source":{"kind":"arxiv","id":"2108.04551","version":4},"attestation_state":"computed","paper":{"title":"ABC-FL: Anomalous and Benign client Classification in Federated Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CR","cs.DC"],"primary_cat":"cs.LG","authors_text":"Hyejun Jeong, Joonyong Hwang, Tai Myung Chung","submitted_at":"2021-08-10T09:54:25Z","abstract_excerpt":"Federated Learning is a distributed machine learning framework designed for data privacy preservation i.e., local data remain private throughout the entire training and testing procedure. Federated Learning is gaining popularity because it allows one to use machine learning techniques while preserving privacy. However, it inherits the vulnerabilities and susceptibilities raised in deep learning techniques. For instance, Federated Learning is particularly vulnerable to data poisoning attacks that may deteriorate its performance and integrity due to its distributed nature and inaccessibility to "},"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":"2108.04551","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2021-08-10T09:54:25Z","cross_cats_sorted":["cs.AI","cs.CR","cs.DC"],"title_canon_sha256":"6956be9ee976abd12b24827e0761e2e3edcfaef4e48a78dc544ec9e6895d4deb","abstract_canon_sha256":"793d39ee20229380f6924145354b0e4267a88c72bb8330ffeb2b55dece675646"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:21:22.889479Z","signature_b64":"cbD6yyPo8isVhyCHSPD7YV2pWvpFJWiriZ3tBteVfO6fMELyfaUu3QeIeduzCwGYOrAXP/7Lj/V50VeQaSXcDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"25b48f7196774ee9cadc1617697e50b3ae96ef1d628d9b89ac724a91f8031fae","last_reissued_at":"2026-07-05T05:21:22.888966Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:21:22.888966Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ABC-FL: Anomalous and Benign client Classification in Federated Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CR","cs.DC"],"primary_cat":"cs.LG","authors_text":"Hyejun Jeong, Joonyong Hwang, Tai Myung Chung","submitted_at":"2021-08-10T09:54:25Z","abstract_excerpt":"Federated Learning is a distributed machine learning framework designed for data privacy preservation i.e., local data remain private throughout the entire training and testing procedure. Federated Learning is gaining popularity because it allows one to use machine learning techniques while preserving privacy. However, it inherits the vulnerabilities and susceptibilities raised in deep learning techniques. For instance, Federated Learning is particularly vulnerable to data poisoning attacks that may deteriorate its performance and integrity due to its distributed nature and inaccessibility to "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.04551","kind":"arxiv","version":4},"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/2108.04551/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":"2108.04551","created_at":"2026-07-05T05:21:22.889035+00:00"},{"alias_kind":"arxiv_version","alias_value":"2108.04551v4","created_at":"2026-07-05T05:21:22.889035+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.04551","created_at":"2026-07-05T05:21:22.889035+00:00"},{"alias_kind":"pith_short_12","alias_value":"EW2I64MWO5HO","created_at":"2026-07-05T05:21:22.889035+00:00"},{"alias_kind":"pith_short_16","alias_value":"EW2I64MWO5HOTSW4","created_at":"2026-07-05T05:21:22.889035+00:00"},{"alias_kind":"pith_short_8","alias_value":"EW2I64MW","created_at":"2026-07-05T05:21:22.889035+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.16167","citing_title":"Mind the Cost of Scaffold! Benign Clients May Even Become Accomplices of Backdoor Attack","ref_index":10,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EW2I64MWO5HOTSW4CYLWS7SQWO","json":"https://pith.science/pith/EW2I64MWO5HOTSW4CYLWS7SQWO.json","graph_json":"https://pith.science/api/pith-number/EW2I64MWO5HOTSW4CYLWS7SQWO/graph.json","events_json":"https://pith.science/api/pith-number/EW2I64MWO5HOTSW4CYLWS7SQWO/events.json","paper":"https://pith.science/paper/EW2I64MW"},"agent_actions":{"view_html":"https://pith.science/pith/EW2I64MWO5HOTSW4CYLWS7SQWO","download_json":"https://pith.science/pith/EW2I64MWO5HOTSW4CYLWS7SQWO.json","view_paper":"https://pith.science/paper/EW2I64MW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2108.04551&json=true","fetch_graph":"https://pith.science/api/pith-number/EW2I64MWO5HOTSW4CYLWS7SQWO/graph.json","fetch_events":"https://pith.science/api/pith-number/EW2I64MWO5HOTSW4CYLWS7SQWO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EW2I64MWO5HOTSW4CYLWS7SQWO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EW2I64MWO5HOTSW4CYLWS7SQWO/action/storage_attestation","attest_author":"https://pith.science/pith/EW2I64MWO5HOTSW4CYLWS7SQWO/action/author_attestation","sign_citation":"https://pith.science/pith/EW2I64MWO5HOTSW4CYLWS7SQWO/action/citation_signature","submit_replication":"https://pith.science/pith/EW2I64MWO5HOTSW4CYLWS7SQWO/action/replication_record"}},"created_at":"2026-07-05T05:21:22.889035+00:00","updated_at":"2026-07-05T05:21:22.889035+00:00"}