{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:P6EYKPFZEC5P4N7JYET46ZOPV2","short_pith_number":"pith:P6EYKPFZ","schema_version":"1.0","canonical_sha256":"7f89853cb920bafe37e9c127cf65cfaeb58ae4ff4fdc4137919a426763e4db7a","source":{"kind":"arxiv","id":"2508.03067","version":1},"attestation_state":"computed","paper":{"title":"Untraceable DeepFakes via Traceable Fingerprint Elimination","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CR","authors_text":"Chen Tang, Jiewei Lai, Lan Zhang, Pengcheng Sun, Xinming Wang, Yunhao Wang","submitted_at":"2025-08-05T04:27:57Z","abstract_excerpt":"Recent advancements in DeepFakes attribution technologies have significantly enhanced forensic capabilities, enabling the extraction of traces left by generative models (GMs) in images, making DeepFakes traceable back to their source GMs. Meanwhile, several attacks have attempted to evade attribution models (AMs) for exploring their limitations, calling for more robust AMs. However, existing attacks fail to eliminate GMs' traces, thus can be mitigated by defensive measures. In this paper, we identify that untraceable DeepFakes can be achieved through a multiplicative attack, which can fundamen"},"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":"2508.03067","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2025-08-05T04:27:57Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5cc7bee636f7252d9e5f4c660395f3da3ebf4402fca32df611ae7ceec697341b","abstract_canon_sha256":"c5d8f950a9e0da0f04a61546e708f23cc5f33a76ae82cb93617e6318fc997ed7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:48:35.796340Z","signature_b64":"aQawizuWuycEbiMzrIMt6YNWzq55wPMUaitpXKg9P/LXeJIsihufY+ABgqz7MDto2RBJt4nwdVDdhvFnBeS6DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7f89853cb920bafe37e9c127cf65cfaeb58ae4ff4fdc4137919a426763e4db7a","last_reissued_at":"2026-07-05T11:48:35.795762Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:48:35.795762Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Untraceable DeepFakes via Traceable Fingerprint Elimination","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CR","authors_text":"Chen Tang, Jiewei Lai, Lan Zhang, Pengcheng Sun, Xinming Wang, Yunhao Wang","submitted_at":"2025-08-05T04:27:57Z","abstract_excerpt":"Recent advancements in DeepFakes attribution technologies have significantly enhanced forensic capabilities, enabling the extraction of traces left by generative models (GMs) in images, making DeepFakes traceable back to their source GMs. Meanwhile, several attacks have attempted to evade attribution models (AMs) for exploring their limitations, calling for more robust AMs. However, existing attacks fail to eliminate GMs' traces, thus can be mitigated by defensive measures. In this paper, we identify that untraceable DeepFakes can be achieved through a multiplicative attack, which can fundamen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.03067","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/2508.03067/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":"2508.03067","created_at":"2026-07-05T11:48:35.795818+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.03067v1","created_at":"2026-07-05T11:48:35.795818+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.03067","created_at":"2026-07-05T11:48:35.795818+00:00"},{"alias_kind":"pith_short_12","alias_value":"P6EYKPFZEC5P","created_at":"2026-07-05T11:48:35.795818+00:00"},{"alias_kind":"pith_short_16","alias_value":"P6EYKPFZEC5P4N7J","created_at":"2026-07-05T11:48:35.795818+00:00"},{"alias_kind":"pith_short_8","alias_value":"P6EYKPFZ","created_at":"2026-07-05T11:48:35.795818+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.01479","citing_title":"CSGuard: Toward Forgery-Resistant Watermarking in Diffusion Models via Compressed Sensing Constraint","ref_index":26,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/P6EYKPFZEC5P4N7JYET46ZOPV2","json":"https://pith.science/pith/P6EYKPFZEC5P4N7JYET46ZOPV2.json","graph_json":"https://pith.science/api/pith-number/P6EYKPFZEC5P4N7JYET46ZOPV2/graph.json","events_json":"https://pith.science/api/pith-number/P6EYKPFZEC5P4N7JYET46ZOPV2/events.json","paper":"https://pith.science/paper/P6EYKPFZ"},"agent_actions":{"view_html":"https://pith.science/pith/P6EYKPFZEC5P4N7JYET46ZOPV2","download_json":"https://pith.science/pith/P6EYKPFZEC5P4N7JYET46ZOPV2.json","view_paper":"https://pith.science/paper/P6EYKPFZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.03067&json=true","fetch_graph":"https://pith.science/api/pith-number/P6EYKPFZEC5P4N7JYET46ZOPV2/graph.json","fetch_events":"https://pith.science/api/pith-number/P6EYKPFZEC5P4N7JYET46ZOPV2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P6EYKPFZEC5P4N7JYET46ZOPV2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P6EYKPFZEC5P4N7JYET46ZOPV2/action/storage_attestation","attest_author":"https://pith.science/pith/P6EYKPFZEC5P4N7JYET46ZOPV2/action/author_attestation","sign_citation":"https://pith.science/pith/P6EYKPFZEC5P4N7JYET46ZOPV2/action/citation_signature","submit_replication":"https://pith.science/pith/P6EYKPFZEC5P4N7JYET46ZOPV2/action/replication_record"}},"created_at":"2026-07-05T11:48:35.795818+00:00","updated_at":"2026-07-05T11:48:35.795818+00:00"}