{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:G5U4TQCNM4D5SD5FNHMYHWEW47","short_pith_number":"pith:G5U4TQCN","schema_version":"1.0","canonical_sha256":"3769c9c04d6707d90fa569d983d896e7fed913fc343fd9f12fa8af24afd565cc","source":{"kind":"arxiv","id":"2504.00454","version":1},"attestation_state":"computed","paper":{"title":"FA^{3}-CLIP: Frequency-Aware Cues Fusion and Attack-Agnostic Prompt Learning for Unified Face Attack Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ajian Liu, Hui Ma, Jun Wan, Liying Yang, Ning Li, Xihong Chen, Yanyan Liang, Yongze Li, Zhen Lei, Zhiyao Liang","submitted_at":"2025-04-01T06:19:50Z","abstract_excerpt":"Facial recognition systems are vulnerable to physical (e.g., printed photos) and digital (e.g., DeepFake) face attacks. Existing methods struggle to simultaneously detect physical and digital attacks due to: 1) significant intra-class variations between these attack types, and 2) the inadequacy of spatial information alone to comprehensively capture live and fake cues. To address these issues, we propose a unified attack detection model termed Frequency-Aware and Attack-Agnostic CLIP (FA\\textsuperscript{3}-CLIP), which introduces attack-agnostic prompt learning to express generic live and fake"},"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":"2504.00454","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-01T06:19:50Z","cross_cats_sorted":[],"title_canon_sha256":"4a1c182fb2f839dcbad8bce1c7380381b66cb1ff46478e491690deb574a26b48","abstract_canon_sha256":"d54f0a27a6d1969ff649a2ac1e8ec6bca881534427707f9be63ac89060b17eae"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:42:26.843594Z","signature_b64":"5G+phP0OqubNO2p6PpDLsqBQQtlcae/an9eRH9uy5TsuOTFyVGbk/okycA8p5WChg3N7TgkhEmnTejM/7eTKCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3769c9c04d6707d90fa569d983d896e7fed913fc343fd9f12fa8af24afd565cc","last_reissued_at":"2026-07-05T10:42:26.843118Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:42:26.843118Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FA^{3}-CLIP: Frequency-Aware Cues Fusion and Attack-Agnostic Prompt Learning for Unified Face Attack Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ajian Liu, Hui Ma, Jun Wan, Liying Yang, Ning Li, Xihong Chen, Yanyan Liang, Yongze Li, Zhen Lei, Zhiyao Liang","submitted_at":"2025-04-01T06:19:50Z","abstract_excerpt":"Facial recognition systems are vulnerable to physical (e.g., printed photos) and digital (e.g., DeepFake) face attacks. Existing methods struggle to simultaneously detect physical and digital attacks due to: 1) significant intra-class variations between these attack types, and 2) the inadequacy of spatial information alone to comprehensively capture live and fake cues. To address these issues, we propose a unified attack detection model termed Frequency-Aware and Attack-Agnostic CLIP (FA\\textsuperscript{3}-CLIP), which introduces attack-agnostic prompt learning to express generic live and fake"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.00454","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/2504.00454/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":"2504.00454","created_at":"2026-07-05T10:42:26.843179+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.00454v1","created_at":"2026-07-05T10:42:26.843179+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.00454","created_at":"2026-07-05T10:42:26.843179+00:00"},{"alias_kind":"pith_short_12","alias_value":"G5U4TQCNM4D5","created_at":"2026-07-05T10:42:26.843179+00:00"},{"alias_kind":"pith_short_16","alias_value":"G5U4TQCNM4D5SD5F","created_at":"2026-07-05T10:42:26.843179+00:00"},{"alias_kind":"pith_short_8","alias_value":"G5U4TQCN","created_at":"2026-07-05T10:42:26.843179+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.13327","citing_title":"Benchmarking Unified Face Attack Detection via Hierarchical Prompt Tuning","ref_index":59,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/G5U4TQCNM4D5SD5FNHMYHWEW47","json":"https://pith.science/pith/G5U4TQCNM4D5SD5FNHMYHWEW47.json","graph_json":"https://pith.science/api/pith-number/G5U4TQCNM4D5SD5FNHMYHWEW47/graph.json","events_json":"https://pith.science/api/pith-number/G5U4TQCNM4D5SD5FNHMYHWEW47/events.json","paper":"https://pith.science/paper/G5U4TQCN"},"agent_actions":{"view_html":"https://pith.science/pith/G5U4TQCNM4D5SD5FNHMYHWEW47","download_json":"https://pith.science/pith/G5U4TQCNM4D5SD5FNHMYHWEW47.json","view_paper":"https://pith.science/paper/G5U4TQCN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.00454&json=true","fetch_graph":"https://pith.science/api/pith-number/G5U4TQCNM4D5SD5FNHMYHWEW47/graph.json","fetch_events":"https://pith.science/api/pith-number/G5U4TQCNM4D5SD5FNHMYHWEW47/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G5U4TQCNM4D5SD5FNHMYHWEW47/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G5U4TQCNM4D5SD5FNHMYHWEW47/action/storage_attestation","attest_author":"https://pith.science/pith/G5U4TQCNM4D5SD5FNHMYHWEW47/action/author_attestation","sign_citation":"https://pith.science/pith/G5U4TQCNM4D5SD5FNHMYHWEW47/action/citation_signature","submit_replication":"https://pith.science/pith/G5U4TQCNM4D5SD5FNHMYHWEW47/action/replication_record"}},"created_at":"2026-07-05T10:42:26.843179+00:00","updated_at":"2026-07-05T10:42:26.843179+00:00"}