{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:NGQME2WZRUGPR3FUYG236PV5JY","short_pith_number":"pith:NGQME2WZ","schema_version":"1.0","canonical_sha256":"69a0c26ad98d0cf8ecb4c1b5bf3ebd4e26b51ee225692e5f0d80b7a6d4d2d259","source":{"kind":"arxiv","id":"1808.04866","version":5},"attestation_state":"computed","paper":{"title":"Mitigating Sybils in Federated Learning Poisoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","cs.DC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Chris J.M. Yoon, Clement Fung, Ivan Beschastnikh","submitted_at":"2018-08-14T19:20:35Z","abstract_excerpt":"Machine learning (ML) over distributed multi-party data is required for a variety of domains. Existing approaches, such as federated learning, collect the outputs computed by a group of devices at a central aggregator and run iterative algorithms to train a globally shared model. Unfortunately, such approaches are susceptible to a variety of attacks, including model poisoning, which is made substantially worse in the presence of sybils.\n  In this paper we first evaluate the vulnerability of federated learning to sybil-based poisoning attacks. We then describe \\emph{FoolsGold}, a novel defense "},"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":"1808.04866","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-08-14T19:20:35Z","cross_cats_sorted":["cs.CR","cs.DC","stat.ML"],"title_canon_sha256":"517d702ee90af848a85a9bed51fc4e4b5fac0fdc6e320c8e08630a7c23902214","abstract_canon_sha256":"62ac945003d858e9559c18b3bab3b0c05ccb1078997ac2fdce42a1966489f3ee"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:19:23.359423Z","signature_b64":"gLkSYIjvJ18X2rFsLl6wESSb+MT+BQkx1t3t4qkEclw5HTWfizDTEG5FvExMt/lHX21jIllMGyaslXb/kCxlCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"69a0c26ad98d0cf8ecb4c1b5bf3ebd4e26b51ee225692e5f0d80b7a6d4d2d259","last_reissued_at":"2026-07-05T01:19:23.358890Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:19:23.358890Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mitigating Sybils in Federated Learning Poisoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","cs.DC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Chris J.M. Yoon, Clement Fung, Ivan Beschastnikh","submitted_at":"2018-08-14T19:20:35Z","abstract_excerpt":"Machine learning (ML) over distributed multi-party data is required for a variety of domains. Existing approaches, such as federated learning, collect the outputs computed by a group of devices at a central aggregator and run iterative algorithms to train a globally shared model. Unfortunately, such approaches are susceptible to a variety of attacks, including model poisoning, which is made substantially worse in the presence of sybils.\n  In this paper we first evaluate the vulnerability of federated learning to sybil-based poisoning attacks. We then describe \\emph{FoolsGold}, a novel defense "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.04866","kind":"arxiv","version":5},"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/1808.04866/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":"1808.04866","created_at":"2026-07-05T01:19:23.358949+00:00"},{"alias_kind":"arxiv_version","alias_value":"1808.04866v5","created_at":"2026-07-05T01:19:23.358949+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.04866","created_at":"2026-07-05T01:19:23.358949+00:00"},{"alias_kind":"pith_short_12","alias_value":"NGQME2WZRUGP","created_at":"2026-07-05T01:19:23.358949+00:00"},{"alias_kind":"pith_short_16","alias_value":"NGQME2WZRUGPR3FU","created_at":"2026-07-05T01:19:23.358949+00:00"},{"alias_kind":"pith_short_8","alias_value":"NGQME2WZ","created_at":"2026-07-05T01:19:23.358949+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2607.08651","citing_title":"Secure Decentralized Federated Learning via Gossip and Virtual Voting","ref_index":18,"is_internal_anchor":true},{"citing_arxiv_id":"2607.07529","citing_title":"FedMark-FM: Auditable, Risk-Adjusted Data Markets for Federated Foundation-Model Adaptation","ref_index":15,"is_internal_anchor":true},{"citing_arxiv_id":"2606.22875","citing_title":"FedOT: Ownership Verification and Leakage Tracing via Watermarks for Federated LDMs","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2407.09658","citing_title":"BoBa: Boosting Backdoor Detection through Data Distribution Inference in Federated Learning","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2407.15389","citing_title":"Poisoning with A Pill: Circumventing Detection in Federated Learning","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2411.03926","citing_title":"Act in Collusion: Distributed Multi-Target Backdoor Attacks in Federated Learning","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12792","citing_title":"SoK: A Comprehensive Analysis of the Current Status of Neural Tangent Generalization Attacks with Research Directions","ref_index":30,"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":8,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09489","citing_title":"XFED: Non-Collusive Model Poisoning Attack Against Byzantine-Robust Federated Classifiers","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NGQME2WZRUGPR3FUYG236PV5JY","json":"https://pith.science/pith/NGQME2WZRUGPR3FUYG236PV5JY.json","graph_json":"https://pith.science/api/pith-number/NGQME2WZRUGPR3FUYG236PV5JY/graph.json","events_json":"https://pith.science/api/pith-number/NGQME2WZRUGPR3FUYG236PV5JY/events.json","paper":"https://pith.science/paper/NGQME2WZ"},"agent_actions":{"view_html":"https://pith.science/pith/NGQME2WZRUGPR3FUYG236PV5JY","download_json":"https://pith.science/pith/NGQME2WZRUGPR3FUYG236PV5JY.json","view_paper":"https://pith.science/paper/NGQME2WZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1808.04866&json=true","fetch_graph":"https://pith.science/api/pith-number/NGQME2WZRUGPR3FUYG236PV5JY/graph.json","fetch_events":"https://pith.science/api/pith-number/NGQME2WZRUGPR3FUYG236PV5JY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NGQME2WZRUGPR3FUYG236PV5JY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NGQME2WZRUGPR3FUYG236PV5JY/action/storage_attestation","attest_author":"https://pith.science/pith/NGQME2WZRUGPR3FUYG236PV5JY/action/author_attestation","sign_citation":"https://pith.science/pith/NGQME2WZRUGPR3FUYG236PV5JY/action/citation_signature","submit_replication":"https://pith.science/pith/NGQME2WZRUGPR3FUYG236PV5JY/action/replication_record"}},"created_at":"2026-07-05T01:19:23.358949+00:00","updated_at":"2026-07-05T01:19:23.358949+00:00"}