{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:CPSW6I2URDTQH6ABDNSZRZTDB7","short_pith_number":"pith:CPSW6I2U","schema_version":"1.0","canonical_sha256":"13e56f235488e703f8011b6598e6630ff4c7149bd886cf079e325e3f915dbc65","source":{"kind":"arxiv","id":"2403.15955","version":3},"attestation_state":"computed","paper":{"title":"Finding needles in a haystack: A Black-Box Approach to Invisible Watermark Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Lingjuan Lyu, Minzhou Pan, Vikash Sehwag, Xin Dong, Xue Lin, Zhenting Wang","submitted_at":"2024-03-23T23:22:54Z","abstract_excerpt":"In this paper, we propose WaterMark Detection (WMD), the first invisible watermark detection method under a black-box and annotation-free setting. WMD is capable of detecting arbitrary watermarks within a given reference dataset using a clean non-watermarked dataset as a reference, without relying on specific decoding methods or prior knowledge of the watermarking techniques. We develop WMD using foundations of offset learning, where a clean non-watermarked dataset enables us to isolate the influence of only watermarked samples in the reference dataset. Our comprehensive evaluations demonstrat"},"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":"2403.15955","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-23T23:22:54Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7f2606d111b7105e1847b4515990379a27e0161ec38b08b04863bffada739911","abstract_canon_sha256":"4c53417b8c084834fe2e3a7652ade9b7a11ec6c5774135747413b1fcf50ced18"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:02:25.493491Z","signature_b64":"9ee4p2DfFWpcvA0YL4dtC9VnZF0MoReQkTYJ19w0xznufPMAvimvkCWp1529YEQjd32YbiFVREULuRCX7yn6Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"13e56f235488e703f8011b6598e6630ff4c7149bd886cf079e325e3f915dbc65","last_reissued_at":"2026-07-05T08:02:25.492984Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:02:25.492984Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Finding needles in a haystack: A Black-Box Approach to Invisible Watermark Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Lingjuan Lyu, Minzhou Pan, Vikash Sehwag, Xin Dong, Xue Lin, Zhenting Wang","submitted_at":"2024-03-23T23:22:54Z","abstract_excerpt":"In this paper, we propose WaterMark Detection (WMD), the first invisible watermark detection method under a black-box and annotation-free setting. WMD is capable of detecting arbitrary watermarks within a given reference dataset using a clean non-watermarked dataset as a reference, without relying on specific decoding methods or prior knowledge of the watermarking techniques. We develop WMD using foundations of offset learning, where a clean non-watermarked dataset enables us to isolate the influence of only watermarked samples in the reference dataset. Our comprehensive evaluations demonstrat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.15955","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/2403.15955/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":"2403.15955","created_at":"2026-07-05T08:02:25.493056+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.15955v3","created_at":"2026-07-05T08:02:25.493056+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.15955","created_at":"2026-07-05T08:02:25.493056+00:00"},{"alias_kind":"pith_short_12","alias_value":"CPSW6I2URDTQ","created_at":"2026-07-05T08:02:25.493056+00:00"},{"alias_kind":"pith_short_16","alias_value":"CPSW6I2URDTQH6AB","created_at":"2026-07-05T08:02:25.493056+00:00"},{"alias_kind":"pith_short_8","alias_value":"CPSW6I2U","created_at":"2026-07-05T08:02:25.493056+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.11478","citing_title":"SoK: On the Role and Future of AIGC Watermarking in the Era of Gen-AI","ref_index":126,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CPSW6I2URDTQH6ABDNSZRZTDB7","json":"https://pith.science/pith/CPSW6I2URDTQH6ABDNSZRZTDB7.json","graph_json":"https://pith.science/api/pith-number/CPSW6I2URDTQH6ABDNSZRZTDB7/graph.json","events_json":"https://pith.science/api/pith-number/CPSW6I2URDTQH6ABDNSZRZTDB7/events.json","paper":"https://pith.science/paper/CPSW6I2U"},"agent_actions":{"view_html":"https://pith.science/pith/CPSW6I2URDTQH6ABDNSZRZTDB7","download_json":"https://pith.science/pith/CPSW6I2URDTQH6ABDNSZRZTDB7.json","view_paper":"https://pith.science/paper/CPSW6I2U","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.15955&json=true","fetch_graph":"https://pith.science/api/pith-number/CPSW6I2URDTQH6ABDNSZRZTDB7/graph.json","fetch_events":"https://pith.science/api/pith-number/CPSW6I2URDTQH6ABDNSZRZTDB7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CPSW6I2URDTQH6ABDNSZRZTDB7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CPSW6I2URDTQH6ABDNSZRZTDB7/action/storage_attestation","attest_author":"https://pith.science/pith/CPSW6I2URDTQH6ABDNSZRZTDB7/action/author_attestation","sign_citation":"https://pith.science/pith/CPSW6I2URDTQH6ABDNSZRZTDB7/action/citation_signature","submit_replication":"https://pith.science/pith/CPSW6I2URDTQH6ABDNSZRZTDB7/action/replication_record"}},"created_at":"2026-07-05T08:02:25.493056+00:00","updated_at":"2026-07-05T08:02:25.493056+00:00"}