{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:77SMH234G3NKAMCKW7LQBWMYD6","short_pith_number":"pith:77SMH234","schema_version":"1.0","canonical_sha256":"ffe4c3eb7c36daa0304ab7d700d9981fb096c8e419ffb985b47b3ac5968bc747","source":{"kind":"arxiv","id":"2108.05080","version":4},"attestation_state":"computed","paper":{"title":"FakeAVCeleb: A Novel Audio-Video Multimodal Deepfake Dataset","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM","cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Hasam Khalid, Minha Kim, Shahroz Tariq, Simon S. Woo","submitted_at":"2021-08-11T07:49:36Z","abstract_excerpt":"While the significant advancements have made in the generation of deepfakes using deep learning technologies, its misuse is a well-known issue now. Deepfakes can cause severe security and privacy issues as they can be used to impersonate a person's identity in a video by replacing his/her face with another person's face. Recently, a new problem of generating synthesized human voice of a person is emerging, where AI-based deep learning models can synthesize any person's voice requiring just a few seconds of audio. With the emerging threat of impersonation attacks using deepfake audios and video"},"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":"2108.05080","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-08-11T07:49:36Z","cross_cats_sorted":["cs.MM","cs.SD","eess.AS"],"title_canon_sha256":"34de78e47a63a5c4d90b68f3126814d37b7668c14705f66c90dbbc326f1bd9cf","abstract_canon_sha256":"c92ecfe38cdf8667ef1d0a994645dc980f60d0f77ae86f2ad7a4e32aad8c6d91"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:00:55.619519Z","signature_b64":"Kqv/5lqVxlnlIajmyGpT75UrIenYxVUAdklmClOSbfkucJbH258Zey2FMD/BjLFluTXG4GBdhEZ1j+GyBFUqBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ffe4c3eb7c36daa0304ab7d700d9981fb096c8e419ffb985b47b3ac5968bc747","last_reissued_at":"2026-07-05T04:00:55.619095Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:00:55.619095Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FakeAVCeleb: A Novel Audio-Video Multimodal Deepfake Dataset","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM","cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Hasam Khalid, Minha Kim, Shahroz Tariq, Simon S. Woo","submitted_at":"2021-08-11T07:49:36Z","abstract_excerpt":"While the significant advancements have made in the generation of deepfakes using deep learning technologies, its misuse is a well-known issue now. Deepfakes can cause severe security and privacy issues as they can be used to impersonate a person's identity in a video by replacing his/her face with another person's face. Recently, a new problem of generating synthesized human voice of a person is emerging, where AI-based deep learning models can synthesize any person's voice requiring just a few seconds of audio. With the emerging threat of impersonation attacks using deepfake audios and video"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.05080","kind":"arxiv","version":4},"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/2108.05080/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":"2108.05080","created_at":"2026-07-05T04:00:55.619151+00:00"},{"alias_kind":"arxiv_version","alias_value":"2108.05080v4","created_at":"2026-07-05T04:00:55.619151+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.05080","created_at":"2026-07-05T04:00:55.619151+00:00"},{"alias_kind":"pith_short_12","alias_value":"77SMH234G3NK","created_at":"2026-07-05T04:00:55.619151+00:00"},{"alias_kind":"pith_short_16","alias_value":"77SMH234G3NKAMCK","created_at":"2026-07-05T04:00:55.619151+00:00"},{"alias_kind":"pith_short_8","alias_value":"77SMH234","created_at":"2026-07-05T04:00:55.619151+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":18,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06872","citing_title":"Ensemble Deep Learning Approaches for AI-Altered Video Detection","ref_index":36,"is_internal_anchor":true},{"citing_arxiv_id":"2606.22772","citing_title":"LoCC: Detection and Localization of Lip-Syncing Deepfakes via Counterfactual Frame Consistency","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2606.09881","citing_title":"Toward Calibrated, Fair, and accurate Deepfake Detection","ref_index":234,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16808","citing_title":"BioLip: Language-Generalizable Lip-Sync Deepfake Detection via Biomechanical Constraint Violation Modeling","ref_index":2,"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":18,"is_internal_anchor":false},{"citing_arxiv_id":"2508.06248","citing_title":"Deepfake Detection that Generalizes Across Benchmarks","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2411.15633","citing_title":"Orthogonal Subspace Decomposition for Generalizable AI-Generated Image Detection","ref_index":295,"is_internal_anchor":false},{"citing_arxiv_id":"2512.00336","citing_title":"MVAD: A Benchmark Dataset for Multimodal AI-Generated Video-Audio Detection","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2512.13281","citing_title":"VideoASMR-Bench: Can AI-Generated ASMR Videos Fool VLMs and Humans?","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12075","citing_title":"The Deepfakes We Missed: We Built Detectors for a Threat That Didn't Arrive","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03390","citing_title":"Enhancing Self-Supervised Talking Head Forgery Detection via a Training-Free Dual-System Framework","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2604.28022","citing_title":"Are DeepFakes Realistic Enough? Exploring Semantic Mismatch as a Novel Challenge","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10334","citing_title":"The Alpha Blending Hypothesis: Compositing Shortcut in Deepfake Detection","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23957","citing_title":"LAVA: Layered Audio-Visual Anti-tampering Watermarking for Robust Deepfake Detection and Localization","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01638","citing_title":"Omni-Fake: Benchmarking Unified Multimodal Social Media Deepfake Detection","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09110","citing_title":"Generalizing Video DeepFake Detection by Self-generated Audio-Visual Pseudo-Fakes","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16207","citing_title":"AIFIND: Artifact-Aware Interpreting Fine-Grained Alignment for Incremental Face Forgery Detection","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16808","citing_title":"BioLip: Language-Generalizable Lip-Sync Deepfake Detection via Biomechanical Constraint Violation Modeling","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/77SMH234G3NKAMCKW7LQBWMYD6","json":"https://pith.science/pith/77SMH234G3NKAMCKW7LQBWMYD6.json","graph_json":"https://pith.science/api/pith-number/77SMH234G3NKAMCKW7LQBWMYD6/graph.json","events_json":"https://pith.science/api/pith-number/77SMH234G3NKAMCKW7LQBWMYD6/events.json","paper":"https://pith.science/paper/77SMH234"},"agent_actions":{"view_html":"https://pith.science/pith/77SMH234G3NKAMCKW7LQBWMYD6","download_json":"https://pith.science/pith/77SMH234G3NKAMCKW7LQBWMYD6.json","view_paper":"https://pith.science/paper/77SMH234","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2108.05080&json=true","fetch_graph":"https://pith.science/api/pith-number/77SMH234G3NKAMCKW7LQBWMYD6/graph.json","fetch_events":"https://pith.science/api/pith-number/77SMH234G3NKAMCKW7LQBWMYD6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/77SMH234G3NKAMCKW7LQBWMYD6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/77SMH234G3NKAMCKW7LQBWMYD6/action/storage_attestation","attest_author":"https://pith.science/pith/77SMH234G3NKAMCKW7LQBWMYD6/action/author_attestation","sign_citation":"https://pith.science/pith/77SMH234G3NKAMCKW7LQBWMYD6/action/citation_signature","submit_replication":"https://pith.science/pith/77SMH234G3NKAMCKW7LQBWMYD6/action/replication_record"}},"created_at":"2026-07-05T04:00:55.619151+00:00","updated_at":"2026-07-05T04:00:55.619151+00:00"}