{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:IP3UQGTJLAG664CKZGNBC3FQ6O","short_pith_number":"pith:IP3UQGTJ","schema_version":"1.0","canonical_sha256":"43f7481a69580def704ac99a116cb0f3a1446a14b2c2d316d6c69c364fddf421","source":{"kind":"arxiv","id":"2410.22445","version":1},"attestation_state":"computed","paper":{"title":"Embedding Watermarks in Diffusion Process for Model Intellectual Property Protection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.CV","authors_text":"Jijia Yang, Sen Peng, Xiaohua Jia","submitted_at":"2024-10-29T18:27:10Z","abstract_excerpt":"In practical application, the widespread deployment of diffusion models often necessitates substantial investment in training. As diffusion models find increasingly diverse applications, concerns about potential misuse highlight the imperative for robust intellectual property protection. Current protection strategies either employ backdoor-based methods, integrating a watermark task as a simpler training objective with the main model task, or embedding watermarks directly into the final output samples. However, the former approach is fragile compared to existing backdoor defense techniques, wh"},"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":"2410.22445","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-29T18:27:10Z","cross_cats_sorted":["cs.CR"],"title_canon_sha256":"f6e01fa995edc6fdd98a3af1b5a611edd05fb24ba4b3070e77878dee79e6d81b","abstract_canon_sha256":"3062211da567853a2238b323f61419a1f5c9f61789b6e74c684f1d003bc8f448"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:28:16.624058Z","signature_b64":"iNOnfJULZqmQi3QwU+G1Ll00uz2cYf96NF8t/gR0hpgJAzDiYviDkmXLKs7gKddJJjfMSgdmaA88YFk3pyg+Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"43f7481a69580def704ac99a116cb0f3a1446a14b2c2d316d6c69c364fddf421","last_reissued_at":"2026-07-05T09:28:16.623594Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:28:16.623594Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Embedding Watermarks in Diffusion Process for Model Intellectual Property Protection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.CV","authors_text":"Jijia Yang, Sen Peng, Xiaohua Jia","submitted_at":"2024-10-29T18:27:10Z","abstract_excerpt":"In practical application, the widespread deployment of diffusion models often necessitates substantial investment in training. As diffusion models find increasingly diverse applications, concerns about potential misuse highlight the imperative for robust intellectual property protection. Current protection strategies either employ backdoor-based methods, integrating a watermark task as a simpler training objective with the main model task, or embedding watermarks directly into the final output samples. However, the former approach is fragile compared to existing backdoor defense techniques, wh"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.22445","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/2410.22445/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":"2410.22445","created_at":"2026-07-05T09:28:16.623650+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.22445v1","created_at":"2026-07-05T09:28:16.623650+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.22445","created_at":"2026-07-05T09:28:16.623650+00:00"},{"alias_kind":"pith_short_12","alias_value":"IP3UQGTJLAG6","created_at":"2026-07-05T09:28:16.623650+00:00"},{"alias_kind":"pith_short_16","alias_value":"IP3UQGTJLAG664CK","created_at":"2026-07-05T09:28:16.623650+00:00"},{"alias_kind":"pith_short_8","alias_value":"IP3UQGTJ","created_at":"2026-07-05T09:28:16.623650+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.29759","citing_title":"GoodDiffusion: Proactive Copyright Protection for Diffusion Bridge Models via Learnable Sample-specific Signatures","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IP3UQGTJLAG664CKZGNBC3FQ6O","json":"https://pith.science/pith/IP3UQGTJLAG664CKZGNBC3FQ6O.json","graph_json":"https://pith.science/api/pith-number/IP3UQGTJLAG664CKZGNBC3FQ6O/graph.json","events_json":"https://pith.science/api/pith-number/IP3UQGTJLAG664CKZGNBC3FQ6O/events.json","paper":"https://pith.science/paper/IP3UQGTJ"},"agent_actions":{"view_html":"https://pith.science/pith/IP3UQGTJLAG664CKZGNBC3FQ6O","download_json":"https://pith.science/pith/IP3UQGTJLAG664CKZGNBC3FQ6O.json","view_paper":"https://pith.science/paper/IP3UQGTJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.22445&json=true","fetch_graph":"https://pith.science/api/pith-number/IP3UQGTJLAG664CKZGNBC3FQ6O/graph.json","fetch_events":"https://pith.science/api/pith-number/IP3UQGTJLAG664CKZGNBC3FQ6O/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IP3UQGTJLAG664CKZGNBC3FQ6O/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IP3UQGTJLAG664CKZGNBC3FQ6O/action/storage_attestation","attest_author":"https://pith.science/pith/IP3UQGTJLAG664CKZGNBC3FQ6O/action/author_attestation","sign_citation":"https://pith.science/pith/IP3UQGTJLAG664CKZGNBC3FQ6O/action/citation_signature","submit_replication":"https://pith.science/pith/IP3UQGTJLAG664CKZGNBC3FQ6O/action/replication_record"}},"created_at":"2026-07-05T09:28:16.623650+00:00","updated_at":"2026-07-05T09:28:16.623650+00:00"}