{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:GCG5QXJXV2HZ7UCXIIZL76YR5C","short_pith_number":"pith:GCG5QXJX","schema_version":"1.0","canonical_sha256":"308dd85d37ae8f9fd0574232bffb11e88dea124ccf718f2ba00af70296efd656","source":{"kind":"arxiv","id":"2506.11444","version":1},"attestation_state":"computed","paper":{"title":"GaussMarker: Robust Dual-Domain Watermark for Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CR","authors_text":"Cheng Hong, Kecen Li, Xinwen Hou, Zhicong Huang","submitted_at":"2025-06-13T03:45:15Z","abstract_excerpt":"As Diffusion Models (DM) generate increasingly realistic images, related issues such as copyright and misuse have become a growing concern. Watermarking is one of the promising solutions. Existing methods inject the watermark into the single-domain of initial Gaussian noise for generation, which suffers from unsatisfactory robustness. This paper presents the first dual-domain DM watermarking approach using a pipelined injector to consistently embed watermarks in both the spatial and frequency domains. To further boost robustness against certain image manipulations and advanced attacks, we intr"},"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":"2506.11444","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2025-06-13T03:45:15Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"3786a3d0facfeee6b78ac88bb2e8df5067d0f211bda803da26cdaf8db343b82b","abstract_canon_sha256":"8c1df5253923b9a63e443ea78b2977b9deac81a82aa5af5ee20ce279ff0adaa8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:21:04.621534Z","signature_b64":"rvcJibbz4bwPOfd8nJ9rS5LvIJjEl7qI4e/ryXpH4QtmfBol0r4mqToIFsQwJ7KsTrGw+6p1zCoHxBfOR+KBAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"308dd85d37ae8f9fd0574232bffb11e88dea124ccf718f2ba00af70296efd656","last_reissued_at":"2026-07-05T11:21:04.621056Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:21:04.621056Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GaussMarker: Robust Dual-Domain Watermark for Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CR","authors_text":"Cheng Hong, Kecen Li, Xinwen Hou, Zhicong Huang","submitted_at":"2025-06-13T03:45:15Z","abstract_excerpt":"As Diffusion Models (DM) generate increasingly realistic images, related issues such as copyright and misuse have become a growing concern. Watermarking is one of the promising solutions. Existing methods inject the watermark into the single-domain of initial Gaussian noise for generation, which suffers from unsatisfactory robustness. This paper presents the first dual-domain DM watermarking approach using a pipelined injector to consistently embed watermarks in both the spatial and frequency domains. To further boost robustness against certain image manipulations and advanced attacks, we intr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.11444","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/2506.11444/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":"2506.11444","created_at":"2026-07-05T11:21:04.621111+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.11444v1","created_at":"2026-07-05T11:21:04.621111+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.11444","created_at":"2026-07-05T11:21:04.621111+00:00"},{"alias_kind":"pith_short_12","alias_value":"GCG5QXJXV2HZ","created_at":"2026-07-05T11:21:04.621111+00:00"},{"alias_kind":"pith_short_16","alias_value":"GCG5QXJXV2HZ7UCX","created_at":"2026-07-05T11:21:04.621111+00:00"},{"alias_kind":"pith_short_8","alias_value":"GCG5QXJX","created_at":"2026-07-05T11:21:04.621111+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.19402","citing_title":"High-Rate Public-Key Pseudorandom Codes for Edit Errors","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2512.06774","citing_title":"RDSplat: Robust Watermarking for 3D Gaussian Splatting Against 2D and 3D Diffusion Editing","ref_index":27,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GCG5QXJXV2HZ7UCXIIZL76YR5C","json":"https://pith.science/pith/GCG5QXJXV2HZ7UCXIIZL76YR5C.json","graph_json":"https://pith.science/api/pith-number/GCG5QXJXV2HZ7UCXIIZL76YR5C/graph.json","events_json":"https://pith.science/api/pith-number/GCG5QXJXV2HZ7UCXIIZL76YR5C/events.json","paper":"https://pith.science/paper/GCG5QXJX"},"agent_actions":{"view_html":"https://pith.science/pith/GCG5QXJXV2HZ7UCXIIZL76YR5C","download_json":"https://pith.science/pith/GCG5QXJXV2HZ7UCXIIZL76YR5C.json","view_paper":"https://pith.science/paper/GCG5QXJX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.11444&json=true","fetch_graph":"https://pith.science/api/pith-number/GCG5QXJXV2HZ7UCXIIZL76YR5C/graph.json","fetch_events":"https://pith.science/api/pith-number/GCG5QXJXV2HZ7UCXIIZL76YR5C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GCG5QXJXV2HZ7UCXIIZL76YR5C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GCG5QXJXV2HZ7UCXIIZL76YR5C/action/storage_attestation","attest_author":"https://pith.science/pith/GCG5QXJXV2HZ7UCXIIZL76YR5C/action/author_attestation","sign_citation":"https://pith.science/pith/GCG5QXJXV2HZ7UCXIIZL76YR5C/action/citation_signature","submit_replication":"https://pith.science/pith/GCG5QXJXV2HZ7UCXIIZL76YR5C/action/replication_record"}},"created_at":"2026-07-05T11:21:04.621111+00:00","updated_at":"2026-07-05T11:21:04.621111+00:00"}