{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ADSPIDQEYV4NY366QABMY4EJTV","short_pith_number":"pith:ADSPIDQE","schema_version":"1.0","canonical_sha256":"00e4f40e04c578dc6fde8002cc70899d5cc3db9f4f75c71b27fb7432364e9829","source":{"kind":"arxiv","id":"2401.13856","version":2},"attestation_state":"computed","paper":{"title":"LAA-Net: Localized Artifact Attention Network for Quality-Agnostic and Generalizable Deepfake Detection","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anis Kacem, Dat Nguyen, Djamila Aouada, Enjie Ghorbel, Inder Pal Singh, Marcella Astrid, Nesryne Mejri, Polina Kuleshova","submitted_at":"2024-01-24T23:42:08Z","abstract_excerpt":"This paper introduces a novel approach for high-quality deepfake detection called Localized Artifact Attention Network (LAA-Net). Existing methods for high-quality deepfake detection are mainly based on a supervised binary classifier coupled with an implicit attention mechanism. As a result, they do not generalize well to unseen manipulations. To handle this issue, two main contributions are made. First, an explicit attention mechanism within a multi-task learning framework is proposed. By combining heatmap-based and self-consistency attention strategies, LAA-Net is forced to focus on a few sm"},"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":"2401.13856","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-24T23:42:08Z","cross_cats_sorted":[],"title_canon_sha256":"59a9ba9e9bbdaacb9a2b2d3d9a515698289ee07239d7700fb68421bb645b9850","abstract_canon_sha256":"65ab3b5d033c6b3bfe70059706c9f426b2c5146d8f9de2186fed077dca09a361"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:22:36.338003Z","signature_b64":"PDyRowEY4/XQnPvZT867CUmBEXGlc02yWKXyexFtNi/aiFzDF/kXtOfPvYVRun1gsAxcXF1LZ85kxBK1WLLUCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"00e4f40e04c578dc6fde8002cc70899d5cc3db9f4f75c71b27fb7432364e9829","last_reissued_at":"2026-07-05T08:22:36.337507Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:22:36.337507Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LAA-Net: Localized Artifact Attention Network for Quality-Agnostic and Generalizable Deepfake Detection","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anis Kacem, Dat Nguyen, Djamila Aouada, Enjie Ghorbel, Inder Pal Singh, Marcella Astrid, Nesryne Mejri, Polina Kuleshova","submitted_at":"2024-01-24T23:42:08Z","abstract_excerpt":"This paper introduces a novel approach for high-quality deepfake detection called Localized Artifact Attention Network (LAA-Net). Existing methods for high-quality deepfake detection are mainly based on a supervised binary classifier coupled with an implicit attention mechanism. As a result, they do not generalize well to unseen manipulations. To handle this issue, two main contributions are made. First, an explicit attention mechanism within a multi-task learning framework is proposed. By combining heatmap-based and self-consistency attention strategies, LAA-Net is forced to focus on a few sm"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.13856","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/2401.13856/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":"2401.13856","created_at":"2026-07-05T08:22:36.337568+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.13856v2","created_at":"2026-07-05T08:22:36.337568+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.13856","created_at":"2026-07-05T08:22:36.337568+00:00"},{"alias_kind":"pith_short_12","alias_value":"ADSPIDQEYV4N","created_at":"2026-07-05T08:22:36.337568+00:00"},{"alias_kind":"pith_short_16","alias_value":"ADSPIDQEYV4NY366","created_at":"2026-07-05T08:22:36.337568+00:00"},{"alias_kind":"pith_short_8","alias_value":"ADSPIDQE","created_at":"2026-07-05T08:22:36.337568+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.14570","citing_title":"Deepfake Detection Generalization with Diffusion Noise","ref_index":42,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ADSPIDQEYV4NY366QABMY4EJTV","json":"https://pith.science/pith/ADSPIDQEYV4NY366QABMY4EJTV.json","graph_json":"https://pith.science/api/pith-number/ADSPIDQEYV4NY366QABMY4EJTV/graph.json","events_json":"https://pith.science/api/pith-number/ADSPIDQEYV4NY366QABMY4EJTV/events.json","paper":"https://pith.science/paper/ADSPIDQE"},"agent_actions":{"view_html":"https://pith.science/pith/ADSPIDQEYV4NY366QABMY4EJTV","download_json":"https://pith.science/pith/ADSPIDQEYV4NY366QABMY4EJTV.json","view_paper":"https://pith.science/paper/ADSPIDQE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.13856&json=true","fetch_graph":"https://pith.science/api/pith-number/ADSPIDQEYV4NY366QABMY4EJTV/graph.json","fetch_events":"https://pith.science/api/pith-number/ADSPIDQEYV4NY366QABMY4EJTV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ADSPIDQEYV4NY366QABMY4EJTV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ADSPIDQEYV4NY366QABMY4EJTV/action/storage_attestation","attest_author":"https://pith.science/pith/ADSPIDQEYV4NY366QABMY4EJTV/action/author_attestation","sign_citation":"https://pith.science/pith/ADSPIDQEYV4NY366QABMY4EJTV/action/citation_signature","submit_replication":"https://pith.science/pith/ADSPIDQEYV4NY366QABMY4EJTV/action/replication_record"}},"created_at":"2026-07-05T08:22:36.337568+00:00","updated_at":"2026-07-05T08:22:36.337568+00:00"}