{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:TLGZLP5XXHIMW4N5VT66S4VDOT","short_pith_number":"pith:TLGZLP5X","schema_version":"1.0","canonical_sha256":"9acd95bfb7b9d0cb71bdacfde972a374c50690af6e72282b77bae9cd7cb95152","source":{"kind":"arxiv","id":"2504.12129","version":2},"attestation_state":"computed","paper":{"title":"Anti-Aesthetics: Protecting Facial Privacy against Customized Text-to-Image Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Caifeng Shan, Hao Sun, Ning Li, Shiqi Liu, Songping Wang, Tong Tong, Yueming Lyu","submitted_at":"2025-04-16T14:44:00Z","abstract_excerpt":"The rise of customized diffusion models has spurred a boom in personalized visual content creation, but also poses risks of malicious misuse, severely threatening personal privacy and copyright protection. Some studies show that the aesthetic properties of images are highly positively correlated with human perception of image quality. Inspired by this, we approach the problem from a novel and intriguing aesthetic perspective to degrade the generation quality of maliciously customized models, thereby achieving better protection of facial identity. Specifically, we propose a Hierarchical Anti-Ae"},"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":"2504.12129","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-16T14:44:00Z","cross_cats_sorted":[],"title_canon_sha256":"8fda3f2bd62a176da05298d29c2ac115d9957176d0616ff2df745623915f212a","abstract_canon_sha256":"7fb14f78ca5b5ff5de7cc76321d262cf4512e419124bc48f2239ab59f7ad24d4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:52:59.502379Z","signature_b64":"S4OsjSwc/8Mk8miSi9+mBuIbeeCs8GAlZo01hpOhjddp4I7W/8wTdyKEaNRLQnTh1JfTptpLTSw+zk1DV9ZyCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9acd95bfb7b9d0cb71bdacfde972a374c50690af6e72282b77bae9cd7cb95152","last_reissued_at":"2026-07-05T10:52:59.501945Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:52:59.501945Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Anti-Aesthetics: Protecting Facial Privacy against Customized Text-to-Image Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Caifeng Shan, Hao Sun, Ning Li, Shiqi Liu, Songping Wang, Tong Tong, Yueming Lyu","submitted_at":"2025-04-16T14:44:00Z","abstract_excerpt":"The rise of customized diffusion models has spurred a boom in personalized visual content creation, but also poses risks of malicious misuse, severely threatening personal privacy and copyright protection. Some studies show that the aesthetic properties of images are highly positively correlated with human perception of image quality. Inspired by this, we approach the problem from a novel and intriguing aesthetic perspective to degrade the generation quality of maliciously customized models, thereby achieving better protection of facial identity. Specifically, we propose a Hierarchical Anti-Ae"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.12129","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/2504.12129/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":"2504.12129","created_at":"2026-07-05T10:52:59.502000+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.12129v2","created_at":"2026-07-05T10:52:59.502000+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.12129","created_at":"2026-07-05T10:52:59.502000+00:00"},{"alias_kind":"pith_short_12","alias_value":"TLGZLP5XXHIM","created_at":"2026-07-05T10:52:59.502000+00:00"},{"alias_kind":"pith_short_16","alias_value":"TLGZLP5XXHIMW4N5","created_at":"2026-07-05T10:52:59.502000+00:00"},{"alias_kind":"pith_short_8","alias_value":"TLGZLP5X","created_at":"2026-07-05T10:52:59.502000+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.09345","citing_title":"An Effective End-to-End Solution for Multimodal Action Recognition","ref_index":28,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TLGZLP5XXHIMW4N5VT66S4VDOT","json":"https://pith.science/pith/TLGZLP5XXHIMW4N5VT66S4VDOT.json","graph_json":"https://pith.science/api/pith-number/TLGZLP5XXHIMW4N5VT66S4VDOT/graph.json","events_json":"https://pith.science/api/pith-number/TLGZLP5XXHIMW4N5VT66S4VDOT/events.json","paper":"https://pith.science/paper/TLGZLP5X"},"agent_actions":{"view_html":"https://pith.science/pith/TLGZLP5XXHIMW4N5VT66S4VDOT","download_json":"https://pith.science/pith/TLGZLP5XXHIMW4N5VT66S4VDOT.json","view_paper":"https://pith.science/paper/TLGZLP5X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.12129&json=true","fetch_graph":"https://pith.science/api/pith-number/TLGZLP5XXHIMW4N5VT66S4VDOT/graph.json","fetch_events":"https://pith.science/api/pith-number/TLGZLP5XXHIMW4N5VT66S4VDOT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TLGZLP5XXHIMW4N5VT66S4VDOT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TLGZLP5XXHIMW4N5VT66S4VDOT/action/storage_attestation","attest_author":"https://pith.science/pith/TLGZLP5XXHIMW4N5VT66S4VDOT/action/author_attestation","sign_citation":"https://pith.science/pith/TLGZLP5XXHIMW4N5VT66S4VDOT/action/citation_signature","submit_replication":"https://pith.science/pith/TLGZLP5XXHIMW4N5VT66S4VDOT/action/replication_record"}},"created_at":"2026-07-05T10:52:59.502000+00:00","updated_at":"2026-07-05T10:52:59.502000+00:00"}