{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:JIZJFFQOAVUOM7STDGPFSAKWR7","short_pith_number":"pith:JIZJFFQO","schema_version":"1.0","canonical_sha256":"4a3292960e0568e67e53199e5901568fcaa6f075dc157847deb446b91ca68e64","source":{"kind":"arxiv","id":"2309.09526","version":1},"attestation_state":"computed","paper":{"title":"DFIL: Deepfake Incremental Learning by Exploiting Domain-invariant Forgery Clues","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Feng Lin, Kui Ren, Kun Pan, Lorenzo Cavallaro, Yao Wei, Yin Yifang, Zhenguang Liu, Zhibo Wang, Zhongjie Ba","submitted_at":"2023-09-18T07:02:26Z","abstract_excerpt":"The malicious use and widespread dissemination of deepfake pose a significant crisis of trust. Current deepfake detection models can generally recognize forgery images by training on a large dataset. However, the accuracy of detection models degrades significantly on images generated by new deepfake methods due to the difference in data distribution. To tackle this issue, we present a novel incremental learning framework that improves the generalization of deepfake detection models by continual learning from a small number of new samples. To cope with different data distributions, we propose t"},"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":"2309.09526","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-09-18T07:02:26Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"17801c9f5454adf0df945ef66be60ed93374b11375498da06245bf16628cf200","abstract_canon_sha256":"adefc3a430bd8f8ca230155a90cba18ebed3de147c2c655ecaecade99699f6a4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:51:40.619596Z","signature_b64":"l+4zDlQXUZc0aIeA1bhfIvwwPtNavz+918BU3Hn7y7BP59PrP7IZIuhcTNV7SRCYI3kjQWN9MybDCFAFSi8UBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4a3292960e0568e67e53199e5901568fcaa6f075dc157847deb446b91ca68e64","last_reissued_at":"2026-07-05T06:51:40.618990Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:51:40.618990Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DFIL: Deepfake Incremental Learning by Exploiting Domain-invariant Forgery Clues","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Feng Lin, Kui Ren, Kun Pan, Lorenzo Cavallaro, Yao Wei, Yin Yifang, Zhenguang Liu, Zhibo Wang, Zhongjie Ba","submitted_at":"2023-09-18T07:02:26Z","abstract_excerpt":"The malicious use and widespread dissemination of deepfake pose a significant crisis of trust. Current deepfake detection models can generally recognize forgery images by training on a large dataset. However, the accuracy of detection models degrades significantly on images generated by new deepfake methods due to the difference in data distribution. To tackle this issue, we present a novel incremental learning framework that improves the generalization of deepfake detection models by continual learning from a small number of new samples. To cope with different data distributions, we propose t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.09526","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/2309.09526/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":"2309.09526","created_at":"2026-07-05T06:51:40.619068+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.09526v1","created_at":"2026-07-05T06:51:40.619068+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.09526","created_at":"2026-07-05T06:51:40.619068+00:00"},{"alias_kind":"pith_short_12","alias_value":"JIZJFFQOAVUO","created_at":"2026-07-05T06:51:40.619068+00:00"},{"alias_kind":"pith_short_16","alias_value":"JIZJFFQOAVUOM7ST","created_at":"2026-07-05T06:51:40.619068+00:00"},{"alias_kind":"pith_short_8","alias_value":"JIZJFFQO","created_at":"2026-07-05T06:51:40.619068+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/JIZJFFQOAVUOM7STDGPFSAKWR7","json":"https://pith.science/pith/JIZJFFQOAVUOM7STDGPFSAKWR7.json","graph_json":"https://pith.science/api/pith-number/JIZJFFQOAVUOM7STDGPFSAKWR7/graph.json","events_json":"https://pith.science/api/pith-number/JIZJFFQOAVUOM7STDGPFSAKWR7/events.json","paper":"https://pith.science/paper/JIZJFFQO"},"agent_actions":{"view_html":"https://pith.science/pith/JIZJFFQOAVUOM7STDGPFSAKWR7","download_json":"https://pith.science/pith/JIZJFFQOAVUOM7STDGPFSAKWR7.json","view_paper":"https://pith.science/paper/JIZJFFQO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.09526&json=true","fetch_graph":"https://pith.science/api/pith-number/JIZJFFQOAVUOM7STDGPFSAKWR7/graph.json","fetch_events":"https://pith.science/api/pith-number/JIZJFFQOAVUOM7STDGPFSAKWR7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JIZJFFQOAVUOM7STDGPFSAKWR7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JIZJFFQOAVUOM7STDGPFSAKWR7/action/storage_attestation","attest_author":"https://pith.science/pith/JIZJFFQOAVUOM7STDGPFSAKWR7/action/author_attestation","sign_citation":"https://pith.science/pith/JIZJFFQOAVUOM7STDGPFSAKWR7/action/citation_signature","submit_replication":"https://pith.science/pith/JIZJFFQOAVUOM7STDGPFSAKWR7/action/replication_record"}},"created_at":"2026-07-05T06:51:40.619068+00:00","updated_at":"2026-07-05T06:51:40.619068+00:00"}