{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:UDMPLZ2HWPXQFJDW75O4EH3DAC","short_pith_number":"pith:UDMPLZ2H","schema_version":"1.0","canonical_sha256":"a0d8f5e747b3ef02a476ff5dc21f6300b1932689c664a618adf927567c44faaa","source":{"kind":"arxiv","id":"2411.07795","version":2},"attestation_state":"computed","paper":{"title":"InvisMark: Invisible and Robust Watermarking for AI-generated Image Provenance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CR","authors_text":"Alex Deng, Alex Gorevski, David Lowe, Deren Lei, Emily Ching, Mengya Hu, Mingyu Wang, Rui Xu, Yaxi Li","submitted_at":"2024-11-10T16:22:22Z","abstract_excerpt":"The proliferation of AI-generated images has intensified the need for robust content authentication methods. We present InvisMark, a novel watermarking technique designed for high-resolution AI-generated images. Our approach leverages advanced neural network architectures and training strategies to embed imperceptible yet highly robust watermarks. InvisMark achieves state-of-the-art performance in imperceptibility (PSNR$\\sim$51, SSIM $\\sim$ 0.998) while maintaining over 97\\% bit accuracy across various image manipulations. Notably, we demonstrate the successful encoding of 256-bit watermarks, "},"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":"2411.07795","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2024-11-10T16:22:22Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"896bf4344b830721aab3932b560edadff5867f62cb45bd3242a931b6c3d4ad1c","abstract_canon_sha256":"c1711411b2d21e4d4cf054e65108be56c4e0383961f45964e36f3081ad1b68ab"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:37:58.160272Z","signature_b64":"hckyM7ovxrsNBxDyu21azohkBy7SgU/SWjS34EQFY+IDbvvY2WeFTjhA8yO8S6snuIGp7G8WhOCh3dnVlKF+Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a0d8f5e747b3ef02a476ff5dc21f6300b1932689c664a618adf927567c44faaa","last_reissued_at":"2026-07-05T09:37:58.159812Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:37:58.159812Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"InvisMark: Invisible and Robust Watermarking for AI-generated Image Provenance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CR","authors_text":"Alex Deng, Alex Gorevski, David Lowe, Deren Lei, Emily Ching, Mengya Hu, Mingyu Wang, Rui Xu, Yaxi Li","submitted_at":"2024-11-10T16:22:22Z","abstract_excerpt":"The proliferation of AI-generated images has intensified the need for robust content authentication methods. We present InvisMark, a novel watermarking technique designed for high-resolution AI-generated images. Our approach leverages advanced neural network architectures and training strategies to embed imperceptible yet highly robust watermarks. InvisMark achieves state-of-the-art performance in imperceptibility (PSNR$\\sim$51, SSIM $\\sim$ 0.998) while maintaining over 97\\% bit accuracy across various image manipulations. Notably, we demonstrate the successful encoding of 256-bit watermarks, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.07795","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/2411.07795/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":"2411.07795","created_at":"2026-07-05T09:37:58.159871+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.07795v2","created_at":"2026-07-05T09:37:58.159871+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.07795","created_at":"2026-07-05T09:37:58.159871+00:00"},{"alias_kind":"pith_short_12","alias_value":"UDMPLZ2HWPXQ","created_at":"2026-07-05T09:37:58.159871+00:00"},{"alias_kind":"pith_short_16","alias_value":"UDMPLZ2HWPXQFJDW","created_at":"2026-07-05T09:37:58.159871+00:00"},{"alias_kind":"pith_short_8","alias_value":"UDMPLZ2H","created_at":"2026-07-05T09:37:58.159871+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.23016","citing_title":"DeepSignature: Digitally Signed, Content-Encoding Watermarks for Robust and Transparent Image Authentication","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UDMPLZ2HWPXQFJDW75O4EH3DAC","json":"https://pith.science/pith/UDMPLZ2HWPXQFJDW75O4EH3DAC.json","graph_json":"https://pith.science/api/pith-number/UDMPLZ2HWPXQFJDW75O4EH3DAC/graph.json","events_json":"https://pith.science/api/pith-number/UDMPLZ2HWPXQFJDW75O4EH3DAC/events.json","paper":"https://pith.science/paper/UDMPLZ2H"},"agent_actions":{"view_html":"https://pith.science/pith/UDMPLZ2HWPXQFJDW75O4EH3DAC","download_json":"https://pith.science/pith/UDMPLZ2HWPXQFJDW75O4EH3DAC.json","view_paper":"https://pith.science/paper/UDMPLZ2H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.07795&json=true","fetch_graph":"https://pith.science/api/pith-number/UDMPLZ2HWPXQFJDW75O4EH3DAC/graph.json","fetch_events":"https://pith.science/api/pith-number/UDMPLZ2HWPXQFJDW75O4EH3DAC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UDMPLZ2HWPXQFJDW75O4EH3DAC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UDMPLZ2HWPXQFJDW75O4EH3DAC/action/storage_attestation","attest_author":"https://pith.science/pith/UDMPLZ2HWPXQFJDW75O4EH3DAC/action/author_attestation","sign_citation":"https://pith.science/pith/UDMPLZ2HWPXQFJDW75O4EH3DAC/action/citation_signature","submit_replication":"https://pith.science/pith/UDMPLZ2HWPXQFJDW75O4EH3DAC/action/replication_record"}},"created_at":"2026-07-05T09:37:58.159871+00:00","updated_at":"2026-07-05T09:37:58.159871+00:00"}