{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:QE63P34JDJNPQS6YEPXAN3VC5Y","short_pith_number":"pith:QE63P34J","schema_version":"1.0","canonical_sha256":"813db7ef891a5af84bd823ee06eea2ee396c4dc189710ce36481abd8a46d700d","source":{"kind":"arxiv","id":"2407.03043","version":2},"attestation_state":"computed","paper":{"title":"SlerpFace: Face Template Protection via Spherical Linear Interpolation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guodong Mu, Jianqing Xu, Jingyun Zhang, Rizen Guo, Shouhong Ding, Shuigeng Zhou, Yuge Huang, Yunsheng Wu, Yuxi Mi, Zhizhou Zhong","submitted_at":"2024-07-03T12:07:36Z","abstract_excerpt":"Contemporary face recognition systems use feature templates extracted from face images to identify persons. To enhance privacy, face template protection techniques are widely employed to conceal sensitive identity and appearance information stored in the template. This paper identifies an emerging privacy attack form utilizing diffusion models that could nullify prior protection. The attack can synthesize high-quality, identity-preserving face images from templates, revealing persons' appearance. Based on studies of the diffusion model's generative capability, this paper proposes a defense by "},"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":"2407.03043","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-03T12:07:36Z","cross_cats_sorted":[],"title_canon_sha256":"86097824691951989f95104c1a960985556b6bff0c84b6e603860d2f33b3e1cb","abstract_canon_sha256":"1becaa420d432dc5ded0b7463973200e25bd1b5c1f4a93b8b0aac9c83acb8c8c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:55:33.852434Z","signature_b64":"B1htUkIUnCMJZBjbg/CJc0LDjQxY/RVIPUFE/BngZnPWNF/osC+9PHsO5aHlJy3SGzcxMW0JPAA+i0qg4khzCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"813db7ef891a5af84bd823ee06eea2ee396c4dc189710ce36481abd8a46d700d","last_reissued_at":"2026-07-05T09:55:33.851827Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:55:33.851827Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SlerpFace: Face Template Protection via Spherical Linear Interpolation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guodong Mu, Jianqing Xu, Jingyun Zhang, Rizen Guo, Shouhong Ding, Shuigeng Zhou, Yuge Huang, Yunsheng Wu, Yuxi Mi, Zhizhou Zhong","submitted_at":"2024-07-03T12:07:36Z","abstract_excerpt":"Contemporary face recognition systems use feature templates extracted from face images to identify persons. To enhance privacy, face template protection techniques are widely employed to conceal sensitive identity and appearance information stored in the template. This paper identifies an emerging privacy attack form utilizing diffusion models that could nullify prior protection. The attack can synthesize high-quality, identity-preserving face images from templates, revealing persons' appearance. Based on studies of the diffusion model's generative capability, this paper proposes a defense by "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.03043","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/2407.03043/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":"2407.03043","created_at":"2026-07-05T09:55:33.851906+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.03043v2","created_at":"2026-07-05T09:55:33.851906+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.03043","created_at":"2026-07-05T09:55:33.851906+00:00"},{"alias_kind":"pith_short_12","alias_value":"QE63P34JDJNP","created_at":"2026-07-05T09:55:33.851906+00:00"},{"alias_kind":"pith_short_16","alias_value":"QE63P34JDJNPQS6Y","created_at":"2026-07-05T09:55:33.851906+00:00"},{"alias_kind":"pith_short_8","alias_value":"QE63P34J","created_at":"2026-07-05T09:55:33.851906+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.30894","citing_title":"SteerFace: Debiasing Synthetic Face Generation via Adaptive Residue Perturbation","ref_index":66,"is_internal_anchor":false},{"citing_arxiv_id":"2409.14204","citing_title":"A Unified Deep Learning Framework for Motion Correction in Medical Imaging","ref_index":48,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QE63P34JDJNPQS6YEPXAN3VC5Y","json":"https://pith.science/pith/QE63P34JDJNPQS6YEPXAN3VC5Y.json","graph_json":"https://pith.science/api/pith-number/QE63P34JDJNPQS6YEPXAN3VC5Y/graph.json","events_json":"https://pith.science/api/pith-number/QE63P34JDJNPQS6YEPXAN3VC5Y/events.json","paper":"https://pith.science/paper/QE63P34J"},"agent_actions":{"view_html":"https://pith.science/pith/QE63P34JDJNPQS6YEPXAN3VC5Y","download_json":"https://pith.science/pith/QE63P34JDJNPQS6YEPXAN3VC5Y.json","view_paper":"https://pith.science/paper/QE63P34J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.03043&json=true","fetch_graph":"https://pith.science/api/pith-number/QE63P34JDJNPQS6YEPXAN3VC5Y/graph.json","fetch_events":"https://pith.science/api/pith-number/QE63P34JDJNPQS6YEPXAN3VC5Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QE63P34JDJNPQS6YEPXAN3VC5Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QE63P34JDJNPQS6YEPXAN3VC5Y/action/storage_attestation","attest_author":"https://pith.science/pith/QE63P34JDJNPQS6YEPXAN3VC5Y/action/author_attestation","sign_citation":"https://pith.science/pith/QE63P34JDJNPQS6YEPXAN3VC5Y/action/citation_signature","submit_replication":"https://pith.science/pith/QE63P34JDJNPQS6YEPXAN3VC5Y/action/replication_record"}},"created_at":"2026-07-05T09:55:33.851906+00:00","updated_at":"2026-07-05T09:55:33.851906+00:00"}