{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:EPISR75SAAOPHNXCAGEJOU4JBH","short_pith_number":"pith:EPISR75S","schema_version":"1.0","canonical_sha256":"23d128ffb2001cf3b6e2018897538909ca9267232125ef4faafcf6fe76a462d3","source":{"kind":"arxiv","id":"2106.07504","version":3},"attestation_state":"computed","paper":{"title":"Characterizing the risk of fairwashing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CY"],"primary_cat":"cs.LG","authors_text":"Hiromi Arai, Satoshi Hara, S\\'ebastien Gambs, Ulrich A\\\"ivodji","submitted_at":"2021-06-14T15:33:17Z","abstract_excerpt":"Fairwashing refers to the risk that an unfair black-box model can be explained by a fairer model through post-hoc explanation manipulation. In this paper, we investigate the capability of fairwashing attacks by analyzing their fidelity-unfairness trade-offs. In particular, we show that fairwashed explanation models can generalize beyond the suing group (i.e., data points that are being explained), meaning that a fairwashed explainer can be used to rationalize subsequent unfair decisions of a black-box model. We also demonstrate that fairwashing attacks can transfer across black-box models, mea"},"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":"2106.07504","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-14T15:33:17Z","cross_cats_sorted":["cs.CY"],"title_canon_sha256":"2048b24c8b7a62eacebcfe265813a8c140474d817cd1898454aa6c8cec8d3879","abstract_canon_sha256":"615bfdcf9fcf82aca3cd30b77aec1372a26e05032291381740b09b745530226d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:28:37.919697Z","signature_b64":"18Z16MCYtZFueXg3Rt5O6ZdrrwCpgwVOh4J2++C5FhJpkVMk1JHM6J+T+gt87fnCfh/Ui4muMIyf967LTYMTDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"23d128ffb2001cf3b6e2018897538909ca9267232125ef4faafcf6fe76a462d3","last_reissued_at":"2026-07-05T03:28:37.919237Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:28:37.919237Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Characterizing the risk of fairwashing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CY"],"primary_cat":"cs.LG","authors_text":"Hiromi Arai, Satoshi Hara, S\\'ebastien Gambs, Ulrich A\\\"ivodji","submitted_at":"2021-06-14T15:33:17Z","abstract_excerpt":"Fairwashing refers to the risk that an unfair black-box model can be explained by a fairer model through post-hoc explanation manipulation. In this paper, we investigate the capability of fairwashing attacks by analyzing their fidelity-unfairness trade-offs. In particular, we show that fairwashed explanation models can generalize beyond the suing group (i.e., data points that are being explained), meaning that a fairwashed explainer can be used to rationalize subsequent unfair decisions of a black-box model. We also demonstrate that fairwashing attacks can transfer across black-box models, mea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.07504","kind":"arxiv","version":3},"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/2106.07504/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":"2106.07504","created_at":"2026-07-05T03:28:37.919294+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.07504v3","created_at":"2026-07-05T03:28:37.919294+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.07504","created_at":"2026-07-05T03:28:37.919294+00:00"},{"alias_kind":"pith_short_12","alias_value":"EPISR75SAAOP","created_at":"2026-07-05T03:28:37.919294+00:00"},{"alias_kind":"pith_short_16","alias_value":"EPISR75SAAOPHNXC","created_at":"2026-07-05T03:28:37.919294+00:00"},{"alias_kind":"pith_short_8","alias_value":"EPISR75S","created_at":"2026-07-05T03:28:37.919294+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/EPISR75SAAOPHNXCAGEJOU4JBH","json":"https://pith.science/pith/EPISR75SAAOPHNXCAGEJOU4JBH.json","graph_json":"https://pith.science/api/pith-number/EPISR75SAAOPHNXCAGEJOU4JBH/graph.json","events_json":"https://pith.science/api/pith-number/EPISR75SAAOPHNXCAGEJOU4JBH/events.json","paper":"https://pith.science/paper/EPISR75S"},"agent_actions":{"view_html":"https://pith.science/pith/EPISR75SAAOPHNXCAGEJOU4JBH","download_json":"https://pith.science/pith/EPISR75SAAOPHNXCAGEJOU4JBH.json","view_paper":"https://pith.science/paper/EPISR75S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.07504&json=true","fetch_graph":"https://pith.science/api/pith-number/EPISR75SAAOPHNXCAGEJOU4JBH/graph.json","fetch_events":"https://pith.science/api/pith-number/EPISR75SAAOPHNXCAGEJOU4JBH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EPISR75SAAOPHNXCAGEJOU4JBH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EPISR75SAAOPHNXCAGEJOU4JBH/action/storage_attestation","attest_author":"https://pith.science/pith/EPISR75SAAOPHNXCAGEJOU4JBH/action/author_attestation","sign_citation":"https://pith.science/pith/EPISR75SAAOPHNXCAGEJOU4JBH/action/citation_signature","submit_replication":"https://pith.science/pith/EPISR75SAAOPHNXCAGEJOU4JBH/action/replication_record"}},"created_at":"2026-07-05T03:28:37.919294+00:00","updated_at":"2026-07-05T03:28:37.919294+00:00"}