{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:H7WKNFUJDH3423HLP4GOPE74WA","short_pith_number":"pith:H7WKNFUJ","schema_version":"1.0","canonical_sha256":"3feca6968919f7cd6ceb7f0ce793fcb022332647ee84ff89d29403b52dd78882","source":{"kind":"arxiv","id":"2608.06469","version":1},"attestation_state":"computed","paper":{"title":"Fairis: Fairness-Aware Aggregation with Provable Influence Containment against Fairness Poisoning Attacks in Collaborative Machine Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CR","authors_text":"Devharsh Trivedi, Jackson Walters, Maryline Laurent, Nesrine Kaaniche, Nikos Triandopoulos","submitted_at":"2026-08-06T18:02:54Z","abstract_excerpt":"Collaborative machine learning among financial institutions must be both group-fair and robust against deliberate adversarial manipulation. Existing fairness-aware aggregation methods remain formally vulnerable to fairness poisoning: a malicious client maximizing group disparity while preserving accuracy evades accuracy-based Byzantine defenses, and in our threat model FairFed's gap-based weighting can be gamed by an adversary who observes the global fairness score. We present Fairis, a server-side reweighting scheme in which each client's update receives the normalized weight $\\omega_k = \\bar"},"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":"2608.06469","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2026-08-06T18:02:54Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"693f8a686238f866f0900207b5880046dd930b6ef28ad175b926baf958c2bea9","abstract_canon_sha256":"4ce8b94eb63d09a03566582aec994b048c514361e03a91e7bd4d09028bc28c40"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-10T01:10:47.000541Z","signature_b64":"3tfBDvTaeHke1+6spbXRr8LfB9vi7Uv/PdnrTZKN6CLVDiyyNvMAMFdMeSqkoQOPSpIC8Zy8GTny74COI1T4Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3feca6968919f7cd6ceb7f0ce793fcb022332647ee84ff89d29403b52dd78882","last_reissued_at":"2026-08-10T01:10:46.998038Z","signature_status":"signed_v1","first_computed_at":"2026-08-10T01:10:46.998038Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fairis: Fairness-Aware Aggregation with Provable Influence Containment against Fairness Poisoning Attacks in Collaborative Machine Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CR","authors_text":"Devharsh Trivedi, Jackson Walters, Maryline Laurent, Nesrine Kaaniche, Nikos Triandopoulos","submitted_at":"2026-08-06T18:02:54Z","abstract_excerpt":"Collaborative machine learning among financial institutions must be both group-fair and robust against deliberate adversarial manipulation. Existing fairness-aware aggregation methods remain formally vulnerable to fairness poisoning: a malicious client maximizing group disparity while preserving accuracy evades accuracy-based Byzantine defenses, and in our threat model FairFed's gap-based weighting can be gamed by an adversary who observes the global fairness score. We present Fairis, a server-side reweighting scheme in which each client's update receives the normalized weight $\\omega_k = \\bar"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.06469","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/2608.06469/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":"2608.06469","created_at":"2026-08-10T01:10:46.999153+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.06469v1","created_at":"2026-08-10T01:10:46.999153+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.06469","created_at":"2026-08-10T01:10:46.999153+00:00"},{"alias_kind":"pith_short_12","alias_value":"H7WKNFUJDH34","created_at":"2026-08-10T01:10:46.999153+00:00"},{"alias_kind":"pith_short_16","alias_value":"H7WKNFUJDH3423HL","created_at":"2026-08-10T01:10:46.999153+00:00"},{"alias_kind":"pith_short_8","alias_value":"H7WKNFUJ","created_at":"2026-08-10T01:10:46.999153+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/H7WKNFUJDH3423HLP4GOPE74WA","json":"https://pith.science/pith/H7WKNFUJDH3423HLP4GOPE74WA.json","graph_json":"https://pith.science/api/pith-number/H7WKNFUJDH3423HLP4GOPE74WA/graph.json","events_json":"https://pith.science/api/pith-number/H7WKNFUJDH3423HLP4GOPE74WA/events.json","paper":"https://pith.science/paper/H7WKNFUJ"},"agent_actions":{"view_html":"https://pith.science/pith/H7WKNFUJDH3423HLP4GOPE74WA","download_json":"https://pith.science/pith/H7WKNFUJDH3423HLP4GOPE74WA.json","view_paper":"https://pith.science/paper/H7WKNFUJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.06469&json=true","fetch_graph":"https://pith.science/api/pith-number/H7WKNFUJDH3423HLP4GOPE74WA/graph.json","fetch_events":"https://pith.science/api/pith-number/H7WKNFUJDH3423HLP4GOPE74WA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H7WKNFUJDH3423HLP4GOPE74WA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H7WKNFUJDH3423HLP4GOPE74WA/action/storage_attestation","attest_author":"https://pith.science/pith/H7WKNFUJDH3423HLP4GOPE74WA/action/author_attestation","sign_citation":"https://pith.science/pith/H7WKNFUJDH3423HLP4GOPE74WA/action/citation_signature","submit_replication":"https://pith.science/pith/H7WKNFUJDH3423HLP4GOPE74WA/action/replication_record"}},"created_at":"2026-08-10T01:10:46.999153+00:00","updated_at":"2026-08-10T01:10:46.999153+00:00"}