{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:A4HFRK5KWGJLHTWFBAUJW7MPC2","short_pith_number":"pith:A4HFRK5K","schema_version":"1.0","canonical_sha256":"070e58abaab192b3cec508289b7d8f16beb2d76041fa05e883c27d2ca90c901a","source":{"kind":"arxiv","id":"2411.11688","version":3},"attestation_state":"computed","paper":{"title":"Watermarking Visual Concepts for Diffusion Models","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI","cs.MM"],"primary_cat":"cs.CR","authors_text":"Jing Yu, Keke Gai, Liangqi Lei, Liehuang Zhu, Qi Wu","submitted_at":"2024-11-18T16:11:25Z","abstract_excerpt":"The personalization techniques of diffusion models succeed in generating images with specific concepts. This ability also poses great threats to copyright protection and network security since malicious users can generate unauthorized content and disinformation relevant to a target concept. Model watermarking is an effective solution to trace the malicious generated images and safeguard their copyright. However, existing model watermarking techniques merely achieve image-level tracing without concept traceability. When tracing infringing or harmful concepts, current approaches execute image co"},"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":"2411.11688","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CR","submitted_at":"2024-11-18T16:11:25Z","cross_cats_sorted":["cs.AI","cs.MM"],"title_canon_sha256":"3a8589b7017ca4facb7117457a6952c829e869d6719b8e2f1e7e81f0578ae8f3","abstract_canon_sha256":"570bf790e97c90b0d10ae6a0820961bfe6f6477312d68a510e293f313b7af9cb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:57:53.683675Z","signature_b64":"PPaBwBLgeys/5cA2MxJcHyY9qHhIFR5QLhqQU2Cm9coIL6uGroIobpu4UmmkTPqZMa2PHZGPV0Pmjz7ntnANCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"070e58abaab192b3cec508289b7d8f16beb2d76041fa05e883c27d2ca90c901a","last_reissued_at":"2026-07-05T11:57:53.683177Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:57:53.683177Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Watermarking Visual Concepts for Diffusion Models","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI","cs.MM"],"primary_cat":"cs.CR","authors_text":"Jing Yu, Keke Gai, Liangqi Lei, Liehuang Zhu, Qi Wu","submitted_at":"2024-11-18T16:11:25Z","abstract_excerpt":"The personalization techniques of diffusion models succeed in generating images with specific concepts. This ability also poses great threats to copyright protection and network security since malicious users can generate unauthorized content and disinformation relevant to a target concept. Model watermarking is an effective solution to trace the malicious generated images and safeguard their copyright. However, existing model watermarking techniques merely achieve image-level tracing without concept traceability. When tracing infringing or harmful concepts, current approaches execute image co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.11688","kind":"arxiv","version":3},"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/2411.11688/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":"2411.11688","created_at":"2026-07-05T11:57:53.683235+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.11688v3","created_at":"2026-07-05T11:57:53.683235+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.11688","created_at":"2026-07-05T11:57:53.683235+00:00"},{"alias_kind":"pith_short_12","alias_value":"A4HFRK5KWGJL","created_at":"2026-07-05T11:57:53.683235+00:00"},{"alias_kind":"pith_short_16","alias_value":"A4HFRK5KWGJLHTWF","created_at":"2026-07-05T11:57:53.683235+00:00"},{"alias_kind":"pith_short_8","alias_value":"A4HFRK5K","created_at":"2026-07-05T11:57:53.683235+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.04314","citing_title":"Adversarial Attacks for Good: A Survey of Proactive Protection across the Visual Content Lifecycle","ref_index":172,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/A4HFRK5KWGJLHTWFBAUJW7MPC2","json":"https://pith.science/pith/A4HFRK5KWGJLHTWFBAUJW7MPC2.json","graph_json":"https://pith.science/api/pith-number/A4HFRK5KWGJLHTWFBAUJW7MPC2/graph.json","events_json":"https://pith.science/api/pith-number/A4HFRK5KWGJLHTWFBAUJW7MPC2/events.json","paper":"https://pith.science/paper/A4HFRK5K"},"agent_actions":{"view_html":"https://pith.science/pith/A4HFRK5KWGJLHTWFBAUJW7MPC2","download_json":"https://pith.science/pith/A4HFRK5KWGJLHTWFBAUJW7MPC2.json","view_paper":"https://pith.science/paper/A4HFRK5K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.11688&json=true","fetch_graph":"https://pith.science/api/pith-number/A4HFRK5KWGJLHTWFBAUJW7MPC2/graph.json","fetch_events":"https://pith.science/api/pith-number/A4HFRK5KWGJLHTWFBAUJW7MPC2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A4HFRK5KWGJLHTWFBAUJW7MPC2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A4HFRK5KWGJLHTWFBAUJW7MPC2/action/storage_attestation","attest_author":"https://pith.science/pith/A4HFRK5KWGJLHTWFBAUJW7MPC2/action/author_attestation","sign_citation":"https://pith.science/pith/A4HFRK5KWGJLHTWFBAUJW7MPC2/action/citation_signature","submit_replication":"https://pith.science/pith/A4HFRK5KWGJLHTWFBAUJW7MPC2/action/replication_record"}},"created_at":"2026-07-05T11:57:53.683235+00:00","updated_at":"2026-07-05T11:57:53.683235+00:00"}