{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:O3JIEBP34LWIVEM7SDPJU55ZTU","short_pith_number":"pith:O3JIEBP3","schema_version":"1.0","canonical_sha256":"76d28205fbe2ec8a919f90de9a77b99d0585ad6eebdd4cabda0b3c914b36065e","source":{"kind":"arxiv","id":"1711.01894","version":2},"attestation_state":"computed","paper":{"title":"Adversarial Frontier Stitching for Remote Neural Network Watermarking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CR","authors_text":"Erwan Le Merrer, Gilles Tr\\'edan, Patrick Perez","submitted_at":"2017-11-06T13:57:08Z","abstract_excerpt":"The state of the art performance of deep learning models comes at a high cost for companies and institutions, due to the tedious data collection and the heavy processing requirements. Recently, [35, 22] proposed to watermark convolutional neural networks for image classification, by embedding information into their weights. While this is a clear progress towards model protection, this technique solely allows for extracting the watermark from a network that one accesses locally and entirely.\n  Instead, we aim at allowing the extraction of the watermark from a neural network (or any other machin"},"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":"1711.01894","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2017-11-06T13:57:08Z","cross_cats_sorted":[],"title_canon_sha256":"c536b2e6ae73e3c39b3f8e1df3074adee61349eead15432058cddbd6c0619be6","abstract_canon_sha256":"0447f37375fc0da2f06240c669d0b1f9b2eb7e7e05ef00df8b8d240bab7fe589"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:31:15.965883Z","signature_b64":"qm5F/8ycFR+8anvW89lp6LsnePyWQuMGfBNgR/jmfsNWQyBG38I2vBMpRMFLZWN60XJ465qkNGncMC507+SfAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"76d28205fbe2ec8a919f90de9a77b99d0585ad6eebdd4cabda0b3c914b36065e","last_reissued_at":"2026-07-05T02:31:15.965412Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:31:15.965412Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adversarial Frontier Stitching for Remote Neural Network Watermarking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CR","authors_text":"Erwan Le Merrer, Gilles Tr\\'edan, Patrick Perez","submitted_at":"2017-11-06T13:57:08Z","abstract_excerpt":"The state of the art performance of deep learning models comes at a high cost for companies and institutions, due to the tedious data collection and the heavy processing requirements. Recently, [35, 22] proposed to watermark convolutional neural networks for image classification, by embedding information into their weights. While this is a clear progress towards model protection, this technique solely allows for extracting the watermark from a network that one accesses locally and entirely.\n  Instead, we aim at allowing the extraction of the watermark from a neural network (or any other machin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.01894","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/1711.01894/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":"1711.01894","created_at":"2026-07-05T02:31:15.965476+00:00"},{"alias_kind":"arxiv_version","alias_value":"1711.01894v2","created_at":"2026-07-05T02:31:15.965476+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.01894","created_at":"2026-07-05T02:31:15.965476+00:00"},{"alias_kind":"pith_short_12","alias_value":"O3JIEBP34LWI","created_at":"2026-07-05T02:31:15.965476+00:00"},{"alias_kind":"pith_short_16","alias_value":"O3JIEBP34LWIVEM7","created_at":"2026-07-05T02:31:15.965476+00:00"},{"alias_kind":"pith_short_8","alias_value":"O3JIEBP3","created_at":"2026-07-05T02:31:15.965476+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.13494","citing_title":"Watermarking LLM-Generated Datasets in Downstream Tasks","ref_index":33,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/O3JIEBP34LWIVEM7SDPJU55ZTU","json":"https://pith.science/pith/O3JIEBP34LWIVEM7SDPJU55ZTU.json","graph_json":"https://pith.science/api/pith-number/O3JIEBP34LWIVEM7SDPJU55ZTU/graph.json","events_json":"https://pith.science/api/pith-number/O3JIEBP34LWIVEM7SDPJU55ZTU/events.json","paper":"https://pith.science/paper/O3JIEBP3"},"agent_actions":{"view_html":"https://pith.science/pith/O3JIEBP34LWIVEM7SDPJU55ZTU","download_json":"https://pith.science/pith/O3JIEBP34LWIVEM7SDPJU55ZTU.json","view_paper":"https://pith.science/paper/O3JIEBP3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1711.01894&json=true","fetch_graph":"https://pith.science/api/pith-number/O3JIEBP34LWIVEM7SDPJU55ZTU/graph.json","fetch_events":"https://pith.science/api/pith-number/O3JIEBP34LWIVEM7SDPJU55ZTU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/O3JIEBP34LWIVEM7SDPJU55ZTU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/O3JIEBP34LWIVEM7SDPJU55ZTU/action/storage_attestation","attest_author":"https://pith.science/pith/O3JIEBP34LWIVEM7SDPJU55ZTU/action/author_attestation","sign_citation":"https://pith.science/pith/O3JIEBP34LWIVEM7SDPJU55ZTU/action/citation_signature","submit_replication":"https://pith.science/pith/O3JIEBP34LWIVEM7SDPJU55ZTU/action/replication_record"}},"created_at":"2026-07-05T02:31:15.965476+00:00","updated_at":"2026-07-05T02:31:15.965476+00:00"}