{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:GHXTQYPXDLJVPYV3JPWVB77NBX","short_pith_number":"pith:GHXTQYPX","schema_version":"1.0","canonical_sha256":"31ef3861f71ad357e2bb4bed50ffed0dfcd66065c6128c510870ac6aa81737df","source":{"kind":"arxiv","id":"2312.07865","version":4},"attestation_state":"computed","paper":{"title":"SimAC: A Simple Anti-Customization Method for Protecting Face Privacy against Text-to-Image Synthesis of Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Feifei Wang, Qidong Huang, Tianyi Wei, Yue Wu, Zhentao Tan","submitted_at":"2023-12-13T03:04:22Z","abstract_excerpt":"Despite the success of diffusion-based customization methods on visual content creation, increasing concerns have been raised about such techniques from both privacy and political perspectives. To tackle this issue, several anti-customization methods have been proposed in very recent months, predominantly grounded in adversarial attacks. Unfortunately, most of these methods adopt straightforward designs, such as end-to-end optimization with a focus on adversarially maximizing the original training loss, thereby neglecting nuanced internal properties intrinsic to the diffusion model, and even l"},"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":"2312.07865","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-13T03:04:22Z","cross_cats_sorted":[],"title_canon_sha256":"2b9760a5f086251713b841090cf21113cd76d30435948a6a38a9faeb40138107","abstract_canon_sha256":"186b142c3ede94c1b1831c8b5c0b1b027591ee1ca40ff6108e4152ec5da5e3c8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T03:13:43.002785Z","signature_b64":"IztdNuJEe1k7rZEahg9NGAClmt4VbBKhvmCwd6lB5S7RGxK1jEIXTV5UKQy+PVwgUiR5D5QsM7csd5XcdmzkBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"31ef3861f71ad357e2bb4bed50ffed0dfcd66065c6128c510870ac6aa81737df","last_reissued_at":"2026-06-23T03:13:43.002265Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T03:13:43.002265Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SimAC: A Simple Anti-Customization Method for Protecting Face Privacy against Text-to-Image Synthesis of Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Feifei Wang, Qidong Huang, Tianyi Wei, Yue Wu, Zhentao Tan","submitted_at":"2023-12-13T03:04:22Z","abstract_excerpt":"Despite the success of diffusion-based customization methods on visual content creation, increasing concerns have been raised about such techniques from both privacy and political perspectives. To tackle this issue, several anti-customization methods have been proposed in very recent months, predominantly grounded in adversarial attacks. Unfortunately, most of these methods adopt straightforward designs, such as end-to-end optimization with a focus on adversarially maximizing the original training loss, thereby neglecting nuanced internal properties intrinsic to the diffusion model, and even l"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.07865","kind":"arxiv","version":4},"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/2312.07865/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":"2312.07865","created_at":"2026-06-23T03:13:43.002330+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.07865v4","created_at":"2026-06-23T03:13:43.002330+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.07865","created_at":"2026-06-23T03:13:43.002330+00:00"},{"alias_kind":"pith_short_12","alias_value":"GHXTQYPXDLJV","created_at":"2026-06-23T03:13:43.002330+00:00"},{"alias_kind":"pith_short_16","alias_value":"GHXTQYPXDLJVPYV3","created_at":"2026-06-23T03:13:43.002330+00:00"},{"alias_kind":"pith_short_8","alias_value":"GHXTQYPX","created_at":"2026-06-23T03:13:43.002330+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.09844","citing_title":"Real-time Identity Defenses against Malicious Personalization of Diffusion Models","ref_index":20,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GHXTQYPXDLJVPYV3JPWVB77NBX","json":"https://pith.science/pith/GHXTQYPXDLJVPYV3JPWVB77NBX.json","graph_json":"https://pith.science/api/pith-number/GHXTQYPXDLJVPYV3JPWVB77NBX/graph.json","events_json":"https://pith.science/api/pith-number/GHXTQYPXDLJVPYV3JPWVB77NBX/events.json","paper":"https://pith.science/paper/GHXTQYPX"},"agent_actions":{"view_html":"https://pith.science/pith/GHXTQYPXDLJVPYV3JPWVB77NBX","download_json":"https://pith.science/pith/GHXTQYPXDLJVPYV3JPWVB77NBX.json","view_paper":"https://pith.science/paper/GHXTQYPX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.07865&json=true","fetch_graph":"https://pith.science/api/pith-number/GHXTQYPXDLJVPYV3JPWVB77NBX/graph.json","fetch_events":"https://pith.science/api/pith-number/GHXTQYPXDLJVPYV3JPWVB77NBX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GHXTQYPXDLJVPYV3JPWVB77NBX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GHXTQYPXDLJVPYV3JPWVB77NBX/action/storage_attestation","attest_author":"https://pith.science/pith/GHXTQYPXDLJVPYV3JPWVB77NBX/action/author_attestation","sign_citation":"https://pith.science/pith/GHXTQYPXDLJVPYV3JPWVB77NBX/action/citation_signature","submit_replication":"https://pith.science/pith/GHXTQYPXDLJVPYV3JPWVB77NBX/action/replication_record"}},"created_at":"2026-06-23T03:13:43.002330+00:00","updated_at":"2026-06-23T03:13:43.002330+00:00"}