{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:XTSY3L7MQDNZOIPRW5OTQHC6J6","short_pith_number":"pith:XTSY3L7M","schema_version":"1.0","canonical_sha256":"bce58dafec80db9721f1b75d381c5e4f91230bc5f260435a5a979146df1f6978","source":{"kind":"arxiv","id":"2311.17088","version":2},"attestation_state":"computed","paper":{"title":"Unsupervised Multimodal Deepfake Detection Using Intra- and Cross-Modal Inconsistencies","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Joe Mathai, Mahyar Khayatkhoei, Mulin Tian, Wael AbdAlmageed","submitted_at":"2023-11-28T03:28:19Z","abstract_excerpt":"Deepfake videos present an increasing threat to society with potentially negative impact on criminal justice, democracy, and personal safety and privacy. Meanwhile, detecting deepfakes, at scale, remains a very challenging task that often requires labeled training data from existing deepfake generation methods. Further, even the most accurate supervised deepfake detection methods do not generalize to deepfakes generated using new generation methods. In this paper, we propose a novel unsupervised method for detecting deepfake videos by directly identifying intra-modal and cross-modal inconsiste"},"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":"2311.17088","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-11-28T03:28:19Z","cross_cats_sorted":[],"title_canon_sha256":"622fc90a3c9227fcda4817e97311f08ac4a73636704afcf185818233235c0e2c","abstract_canon_sha256":"ba9486ebfde208a85af1bf4415c233dd06ecb297375244c436af3625a5b66fb1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:34:57.902936Z","signature_b64":"EMG20KRwohXZOcBtapwE48yT+RCrfiV7tGURQmHODYE/M3BWF4ADfUAPVjC/+8ODTgrEXwSCT4NCA+Cfy2rRBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bce58dafec80db9721f1b75d381c5e4f91230bc5f260435a5a979146df1f6978","last_reissued_at":"2026-07-05T08:34:57.902401Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:34:57.902401Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unsupervised Multimodal Deepfake Detection Using Intra- and Cross-Modal Inconsistencies","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Joe Mathai, Mahyar Khayatkhoei, Mulin Tian, Wael AbdAlmageed","submitted_at":"2023-11-28T03:28:19Z","abstract_excerpt":"Deepfake videos present an increasing threat to society with potentially negative impact on criminal justice, democracy, and personal safety and privacy. Meanwhile, detecting deepfakes, at scale, remains a very challenging task that often requires labeled training data from existing deepfake generation methods. Further, even the most accurate supervised deepfake detection methods do not generalize to deepfakes generated using new generation methods. In this paper, we propose a novel unsupervised method for detecting deepfake videos by directly identifying intra-modal and cross-modal inconsiste"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.17088","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/2311.17088/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":"2311.17088","created_at":"2026-07-05T08:34:57.902461+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.17088v2","created_at":"2026-07-05T08:34:57.902461+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.17088","created_at":"2026-07-05T08:34:57.902461+00:00"},{"alias_kind":"pith_short_12","alias_value":"XTSY3L7MQDNZ","created_at":"2026-07-05T08:34:57.902461+00:00"},{"alias_kind":"pith_short_16","alias_value":"XTSY3L7MQDNZOIPR","created_at":"2026-07-05T08:34:57.902461+00:00"},{"alias_kind":"pith_short_8","alias_value":"XTSY3L7M","created_at":"2026-07-05T08:34:57.902461+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22772","citing_title":"LoCC: Detection and Localization of Lip-Syncing Deepfakes via Counterfactual Frame Consistency","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19630","citing_title":"EMO-BOOST: Emotion-Augmented Audio-Visual Features for Improved Generalization in Deepfake Detection","ref_index":39,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XTSY3L7MQDNZOIPRW5OTQHC6J6","json":"https://pith.science/pith/XTSY3L7MQDNZOIPRW5OTQHC6J6.json","graph_json":"https://pith.science/api/pith-number/XTSY3L7MQDNZOIPRW5OTQHC6J6/graph.json","events_json":"https://pith.science/api/pith-number/XTSY3L7MQDNZOIPRW5OTQHC6J6/events.json","paper":"https://pith.science/paper/XTSY3L7M"},"agent_actions":{"view_html":"https://pith.science/pith/XTSY3L7MQDNZOIPRW5OTQHC6J6","download_json":"https://pith.science/pith/XTSY3L7MQDNZOIPRW5OTQHC6J6.json","view_paper":"https://pith.science/paper/XTSY3L7M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.17088&json=true","fetch_graph":"https://pith.science/api/pith-number/XTSY3L7MQDNZOIPRW5OTQHC6J6/graph.json","fetch_events":"https://pith.science/api/pith-number/XTSY3L7MQDNZOIPRW5OTQHC6J6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XTSY3L7MQDNZOIPRW5OTQHC6J6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XTSY3L7MQDNZOIPRW5OTQHC6J6/action/storage_attestation","attest_author":"https://pith.science/pith/XTSY3L7MQDNZOIPRW5OTQHC6J6/action/author_attestation","sign_citation":"https://pith.science/pith/XTSY3L7MQDNZOIPRW5OTQHC6J6/action/citation_signature","submit_replication":"https://pith.science/pith/XTSY3L7MQDNZOIPRW5OTQHC6J6/action/replication_record"}},"created_at":"2026-07-05T08:34:57.902461+00:00","updated_at":"2026-07-05T08:34:57.902461+00:00"}