{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:GXFZ3MZANQ2VXYXA3QSCPUSWYX","short_pith_number":"pith:GXFZ3MZA","schema_version":"1.0","canonical_sha256":"35cb9db3206c355be2e0dc2427d256c5c028b622fc88002ea3e3d171e5646466","source":{"kind":"arxiv","id":"2211.11835","version":2},"attestation_state":"computed","paper":{"title":"Fairness Increases Adversarial Vulnerability","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CR"],"primary_cat":"cs.LG","authors_text":"Cuong Tran, Ferdinando Fioretto, Keyu Zhu, Pascal Van Hentenryck","submitted_at":"2022-11-21T19:55:35Z","abstract_excerpt":"The remarkable performance of deep learning models and their applications in consequential domains (e.g., facial recognition) introduces important challenges at the intersection of equity and security. Fairness and robustness are two desired notions often required in learning models. Fairness ensures that models do not disproportionately harm (or benefit) some groups over others, while robustness measures the models' resilience against small input perturbations.\n  This paper shows the existence of a dichotomy between fairness and robustness, and analyzes when achieving fairness decreases the m"},"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":"2211.11835","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-11-21T19:55:35Z","cross_cats_sorted":["cs.AI","cs.CR"],"title_canon_sha256":"03fc87c1f08795e330d4ca1bbd3b42ea24deb17361fcff11f3195af8fe757168","abstract_canon_sha256":"408a38d54804712d0a3c9fbc22ed69c0e05b2ef48c7d5ab055c62d83d077a49c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:18:51.305141Z","signature_b64":"uP5MzRW6d+jH2v+WULRNTFGFRL2jPOod8hoVKyEwEHe2iPiv4UTWr/cq3d99zf3iZvVkLRls6A0IeTezDEclCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"35cb9db3206c355be2e0dc2427d256c5c028b622fc88002ea3e3d171e5646466","last_reissued_at":"2026-07-05T05:18:51.304793Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:18:51.304793Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fairness Increases Adversarial Vulnerability","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CR"],"primary_cat":"cs.LG","authors_text":"Cuong Tran, Ferdinando Fioretto, Keyu Zhu, Pascal Van Hentenryck","submitted_at":"2022-11-21T19:55:35Z","abstract_excerpt":"The remarkable performance of deep learning models and their applications in consequential domains (e.g., facial recognition) introduces important challenges at the intersection of equity and security. Fairness and robustness are two desired notions often required in learning models. Fairness ensures that models do not disproportionately harm (or benefit) some groups over others, while robustness measures the models' resilience against small input perturbations.\n  This paper shows the existence of a dichotomy between fairness and robustness, and analyzes when achieving fairness decreases the m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.11835","kind":"arxiv","version":2},"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/2211.11835/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":"2211.11835","created_at":"2026-07-05T05:18:51.304851+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.11835v2","created_at":"2026-07-05T05:18:51.304851+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.11835","created_at":"2026-07-05T05:18:51.304851+00:00"},{"alias_kind":"pith_short_12","alias_value":"GXFZ3MZANQ2V","created_at":"2026-07-05T05:18:51.304851+00:00"},{"alias_kind":"pith_short_16","alias_value":"GXFZ3MZANQ2VXYXA","created_at":"2026-07-05T05:18:51.304851+00:00"},{"alias_kind":"pith_short_8","alias_value":"GXFZ3MZA","created_at":"2026-07-05T05:18:51.304851+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/GXFZ3MZANQ2VXYXA3QSCPUSWYX","json":"https://pith.science/pith/GXFZ3MZANQ2VXYXA3QSCPUSWYX.json","graph_json":"https://pith.science/api/pith-number/GXFZ3MZANQ2VXYXA3QSCPUSWYX/graph.json","events_json":"https://pith.science/api/pith-number/GXFZ3MZANQ2VXYXA3QSCPUSWYX/events.json","paper":"https://pith.science/paper/GXFZ3MZA"},"agent_actions":{"view_html":"https://pith.science/pith/GXFZ3MZANQ2VXYXA3QSCPUSWYX","download_json":"https://pith.science/pith/GXFZ3MZANQ2VXYXA3QSCPUSWYX.json","view_paper":"https://pith.science/paper/GXFZ3MZA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.11835&json=true","fetch_graph":"https://pith.science/api/pith-number/GXFZ3MZANQ2VXYXA3QSCPUSWYX/graph.json","fetch_events":"https://pith.science/api/pith-number/GXFZ3MZANQ2VXYXA3QSCPUSWYX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GXFZ3MZANQ2VXYXA3QSCPUSWYX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GXFZ3MZANQ2VXYXA3QSCPUSWYX/action/storage_attestation","attest_author":"https://pith.science/pith/GXFZ3MZANQ2VXYXA3QSCPUSWYX/action/author_attestation","sign_citation":"https://pith.science/pith/GXFZ3MZANQ2VXYXA3QSCPUSWYX/action/citation_signature","submit_replication":"https://pith.science/pith/GXFZ3MZANQ2VXYXA3QSCPUSWYX/action/replication_record"}},"created_at":"2026-07-05T05:18:51.304851+00:00","updated_at":"2026-07-05T05:18:51.304851+00:00"}