{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:65T6JXFIENCXVVMPDGU3ZBCL7R","short_pith_number":"pith:65T6JXFI","schema_version":"1.0","canonical_sha256":"f767e4dca823457ad58f19a9bc844bfc40e28056a77f54d252df016f2a90cfb1","source":{"kind":"arxiv","id":"2210.15745","version":2},"attestation_state":"computed","paper":{"title":"DICTION:DynamIC robusT whIte bOx watermarkiNg scheme for deep neural networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CR","authors_text":"Gouenou Coatrieux, Reda Bellafqira","submitted_at":"2022-10-27T19:48:26Z","abstract_excerpt":"Deep neural network (DNN) watermarking is a suitable method for protecting the ownership of deep learning (DL) models. It secretly embeds an identifier (watermark) within the model, which can be retrieved by the owner to prove ownership. In this paper, we first provide a unified framework for white box DNN watermarking schemes. It includes current state-of-the-art methods outlining their theoretical inter-connections. Next, we introduce DICTION, a new white-box Dynamic Robust watermarking scheme, we derived from this framework. Its main originality stands on a generative adversarial network (G"},"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":"2210.15745","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2022-10-27T19:48:26Z","cross_cats_sorted":[],"title_canon_sha256":"b5b1bdc72f279f1f211f9618588ddd6dd66b9babed1922140fe6720e703859aa","abstract_canon_sha256":"b457f1f711722da5634ce7dc1eba7ef5b52f8d664639e1fedf7d41f24279eba4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:04:33.426385Z","signature_b64":"e57e5Sr0gxiusdSogCE52J6TghQnn2jW9iCMAsHar81U+eub7VdJXOjJqwjhnT4UR1KjSMWDO5ZBnquK0tZMDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f767e4dca823457ad58f19a9bc844bfc40e28056a77f54d252df016f2a90cfb1","last_reissued_at":"2026-07-05T11:04:33.425956Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:04:33.425956Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DICTION:DynamIC robusT whIte bOx watermarkiNg scheme for deep neural networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CR","authors_text":"Gouenou Coatrieux, Reda Bellafqira","submitted_at":"2022-10-27T19:48:26Z","abstract_excerpt":"Deep neural network (DNN) watermarking is a suitable method for protecting the ownership of deep learning (DL) models. It secretly embeds an identifier (watermark) within the model, which can be retrieved by the owner to prove ownership. In this paper, we first provide a unified framework for white box DNN watermarking schemes. It includes current state-of-the-art methods outlining their theoretical inter-connections. Next, we introduce DICTION, a new white-box Dynamic Robust watermarking scheme, we derived from this framework. Its main originality stands on a generative adversarial network (G"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.15745","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/2210.15745/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":"2210.15745","created_at":"2026-07-05T11:04:33.426019+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.15745v2","created_at":"2026-07-05T11:04:33.426019+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.15745","created_at":"2026-07-05T11:04:33.426019+00:00"},{"alias_kind":"pith_short_12","alias_value":"65T6JXFIENCX","created_at":"2026-07-05T11:04:33.426019+00:00"},{"alias_kind":"pith_short_16","alias_value":"65T6JXFIENCXVVMP","created_at":"2026-07-05T11:04:33.426019+00:00"},{"alias_kind":"pith_short_8","alias_value":"65T6JXFI","created_at":"2026-07-05T11:04:33.426019+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.12123","citing_title":"FL-CLEANER: byzantine and backdoor defense by CLustering Errors of Activation maps in Non-iid fedErated leaRning","ref_index":51,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/65T6JXFIENCXVVMPDGU3ZBCL7R","json":"https://pith.science/pith/65T6JXFIENCXVVMPDGU3ZBCL7R.json","graph_json":"https://pith.science/api/pith-number/65T6JXFIENCXVVMPDGU3ZBCL7R/graph.json","events_json":"https://pith.science/api/pith-number/65T6JXFIENCXVVMPDGU3ZBCL7R/events.json","paper":"https://pith.science/paper/65T6JXFI"},"agent_actions":{"view_html":"https://pith.science/pith/65T6JXFIENCXVVMPDGU3ZBCL7R","download_json":"https://pith.science/pith/65T6JXFIENCXVVMPDGU3ZBCL7R.json","view_paper":"https://pith.science/paper/65T6JXFI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.15745&json=true","fetch_graph":"https://pith.science/api/pith-number/65T6JXFIENCXVVMPDGU3ZBCL7R/graph.json","fetch_events":"https://pith.science/api/pith-number/65T6JXFIENCXVVMPDGU3ZBCL7R/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/65T6JXFIENCXVVMPDGU3ZBCL7R/action/timestamp_anchor","attest_storage":"https://pith.science/pith/65T6JXFIENCXVVMPDGU3ZBCL7R/action/storage_attestation","attest_author":"https://pith.science/pith/65T6JXFIENCXVVMPDGU3ZBCL7R/action/author_attestation","sign_citation":"https://pith.science/pith/65T6JXFIENCXVVMPDGU3ZBCL7R/action/citation_signature","submit_replication":"https://pith.science/pith/65T6JXFIENCXVVMPDGU3ZBCL7R/action/replication_record"}},"created_at":"2026-07-05T11:04:33.426019+00:00","updated_at":"2026-07-05T11:04:33.426019+00:00"}