{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:INL2WNI2PH4QPLBORRZZH2C54Q","short_pith_number":"pith:INL2WNI2","schema_version":"1.0","canonical_sha256":"4357ab351a79f907ac2e8c7393e85de41cc9343112ed538c8e564bd48567d140","source":{"kind":"arxiv","id":"2212.13344","version":1},"attestation_state":"computed","paper":{"title":"DiffFace: Diffusion-based Face Swapping with Facial Guidance","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jisu Nam, Junyoung Seo, Kihong Kim, Kwanghee Lee, Kychul Lee, Seokju Cho, Seungryong Kim, Yunho Kim","submitted_at":"2022-12-27T02:51:46Z","abstract_excerpt":"In this paper, we propose a diffusion-based face swapping framework for the first time, called DiffFace, composed of training ID conditional DDPM, sampling with facial guidance, and a target-preserving blending. In specific, in the training process, the ID conditional DDPM is trained to generate face images with the desired identity. In the sampling process, we use the off-the-shelf facial expert models to make the model transfer source identity while preserving target attributes faithfully. During this process, to preserve the background of the target image and obtain the desired face swappin"},"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":"2212.13344","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-12-27T02:51:46Z","cross_cats_sorted":[],"title_canon_sha256":"b1a309dbda9ab4b70770c4d15563f3ab7c55d3729dffada27039c3ca7ac421cb","abstract_canon_sha256":"a9aa1500553b54487508f8a49bfe21ab7b0fdb9a882398318dc1fe4e8ea96433"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:28:50.643476Z","signature_b64":"5yfKwwbBRak52hZvS2OegCPAmyugqxPzVvha7XIYZCqIFlyI/8n5YjEufw8chcHnusFuf/ShfJDOO2JNRQkkCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4357ab351a79f907ac2e8c7393e85de41cc9343112ed538c8e564bd48567d140","last_reissued_at":"2026-07-05T05:28:50.642977Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:28:50.642977Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DiffFace: Diffusion-based Face Swapping with Facial Guidance","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jisu Nam, Junyoung Seo, Kihong Kim, Kwanghee Lee, Kychul Lee, Seokju Cho, Seungryong Kim, Yunho Kim","submitted_at":"2022-12-27T02:51:46Z","abstract_excerpt":"In this paper, we propose a diffusion-based face swapping framework for the first time, called DiffFace, composed of training ID conditional DDPM, sampling with facial guidance, and a target-preserving blending. In specific, in the training process, the ID conditional DDPM is trained to generate face images with the desired identity. In the sampling process, we use the off-the-shelf facial expert models to make the model transfer source identity while preserving target attributes faithfully. During this process, to preserve the background of the target image and obtain the desired face swappin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.13344","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/2212.13344/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":"2212.13344","created_at":"2026-07-05T05:28:50.643032+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.13344v1","created_at":"2026-07-05T05:28:50.643032+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.13344","created_at":"2026-07-05T05:28:50.643032+00:00"},{"alias_kind":"pith_short_12","alias_value":"INL2WNI2PH4Q","created_at":"2026-07-05T05:28:50.643032+00:00"},{"alias_kind":"pith_short_16","alias_value":"INL2WNI2PH4QPLBO","created_at":"2026-07-05T05:28:50.643032+00:00"},{"alias_kind":"pith_short_8","alias_value":"INL2WNI2","created_at":"2026-07-05T05:28:50.643032+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25376","citing_title":"Transferable Attack against Face Swapping in an Extended Space","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2504.14129","citing_title":"PVLM: Parsing-Aware Vision Language Model with Dynamic Contrastive Learning for Zero-Shot Deepfake Attribution","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00883","citing_title":"Towards High Fidelity Face Swapping: A Comprehensive Survey and New Benchmark","ref_index":75,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14570","citing_title":"Deepfake Detection Generalization with Diffusion Noise","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/INL2WNI2PH4QPLBORRZZH2C54Q","json":"https://pith.science/pith/INL2WNI2PH4QPLBORRZZH2C54Q.json","graph_json":"https://pith.science/api/pith-number/INL2WNI2PH4QPLBORRZZH2C54Q/graph.json","events_json":"https://pith.science/api/pith-number/INL2WNI2PH4QPLBORRZZH2C54Q/events.json","paper":"https://pith.science/paper/INL2WNI2"},"agent_actions":{"view_html":"https://pith.science/pith/INL2WNI2PH4QPLBORRZZH2C54Q","download_json":"https://pith.science/pith/INL2WNI2PH4QPLBORRZZH2C54Q.json","view_paper":"https://pith.science/paper/INL2WNI2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.13344&json=true","fetch_graph":"https://pith.science/api/pith-number/INL2WNI2PH4QPLBORRZZH2C54Q/graph.json","fetch_events":"https://pith.science/api/pith-number/INL2WNI2PH4QPLBORRZZH2C54Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/INL2WNI2PH4QPLBORRZZH2C54Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/INL2WNI2PH4QPLBORRZZH2C54Q/action/storage_attestation","attest_author":"https://pith.science/pith/INL2WNI2PH4QPLBORRZZH2C54Q/action/author_attestation","sign_citation":"https://pith.science/pith/INL2WNI2PH4QPLBORRZZH2C54Q/action/citation_signature","submit_replication":"https://pith.science/pith/INL2WNI2PH4QPLBORRZZH2C54Q/action/replication_record"}},"created_at":"2026-07-05T05:28:50.643032+00:00","updated_at":"2026-07-05T05:28:50.643032+00:00"}