{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:7O3GUZ374227USR7HFDXJJFCIS","short_pith_number":"pith:7O3GUZ37","schema_version":"1.0","canonical_sha256":"fbb66a677fe6b5fa4a3f394774a4a244a7f31da9a5aa3d4252761d65d373c897","source":{"kind":"arxiv","id":"2106.06916","version":2},"attestation_state":"computed","paper":{"title":"Non-Transferable Learning: A New Approach for Model Ownership Verification and Applicability Authorization","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Lixu Wang, Qi Zhu, Ruiqi Xu, Shichao Xu, Xiao Wang","submitted_at":"2021-06-13T04:57:16Z","abstract_excerpt":"As Artificial Intelligence as a Service gains popularity, protecting well-trained models as intellectual property is becoming increasingly important. There are two common types of protection methods: ownership verification and usage authorization. In this paper, we propose Non-Transferable Learning (NTL), a novel approach that captures the exclusive data representation in the learned model and restricts the model generalization ability to certain domains. This approach provides effective solutions to both model verification and authorization. Specifically: 1) For ownership verification, waterm"},"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":"2106.06916","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-13T04:57:16Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"9dead41a9b3197423fbe71e6e50c5b0508b8f0d22b986ef34ef3a8d9c470a41b","abstract_canon_sha256":"da68ffedf8ce00b6d4b4b45acd1c0a47c62a7978656dc2e70ddffa2a8acc12cb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:00:15.199397Z","signature_b64":"WJ2B7xCjsCgUk9VtkHjtUQ/Ukr/TRnLNNhCUEwSbHpAwMwKSBebNSRXmAF3vb6UTptpGFsSjRY8LZOhdGpN4BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fbb66a677fe6b5fa4a3f394774a4a244a7f31da9a5aa3d4252761d65d373c897","last_reissued_at":"2026-07-05T04:00:15.199015Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:00:15.199015Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Non-Transferable Learning: A New Approach for Model Ownership Verification and Applicability Authorization","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Lixu Wang, Qi Zhu, Ruiqi Xu, Shichao Xu, Xiao Wang","submitted_at":"2021-06-13T04:57:16Z","abstract_excerpt":"As Artificial Intelligence as a Service gains popularity, protecting well-trained models as intellectual property is becoming increasingly important. There are two common types of protection methods: ownership verification and usage authorization. In this paper, we propose Non-Transferable Learning (NTL), a novel approach that captures the exclusive data representation in the learned model and restricts the model generalization ability to certain domains. This approach provides effective solutions to both model verification and authorization. Specifically: 1) For ownership verification, waterm"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.06916","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/2106.06916/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":"2106.06916","created_at":"2026-07-05T04:00:15.199065+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.06916v2","created_at":"2026-07-05T04:00:15.199065+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.06916","created_at":"2026-07-05T04:00:15.199065+00:00"},{"alias_kind":"pith_short_12","alias_value":"7O3GUZ374227","created_at":"2026-07-05T04:00:15.199065+00:00"},{"alias_kind":"pith_short_16","alias_value":"7O3GUZ374227USR7","created_at":"2026-07-05T04:00:15.199065+00:00"},{"alias_kind":"pith_short_8","alias_value":"7O3GUZ37","created_at":"2026-07-05T04:00:15.199065+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2512.06774","citing_title":"RDSplat: Robust Watermarking for 3D Gaussian Splatting Against 2D and 3D Diffusion Editing","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09688","citing_title":"Immunizing 3D Gaussian Generative Models Against Unauthorized Fine-Tuning via Attribute-Space Traps","ref_index":30,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7O3GUZ374227USR7HFDXJJFCIS","json":"https://pith.science/pith/7O3GUZ374227USR7HFDXJJFCIS.json","graph_json":"https://pith.science/api/pith-number/7O3GUZ374227USR7HFDXJJFCIS/graph.json","events_json":"https://pith.science/api/pith-number/7O3GUZ374227USR7HFDXJJFCIS/events.json","paper":"https://pith.science/paper/7O3GUZ37"},"agent_actions":{"view_html":"https://pith.science/pith/7O3GUZ374227USR7HFDXJJFCIS","download_json":"https://pith.science/pith/7O3GUZ374227USR7HFDXJJFCIS.json","view_paper":"https://pith.science/paper/7O3GUZ37","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.06916&json=true","fetch_graph":"https://pith.science/api/pith-number/7O3GUZ374227USR7HFDXJJFCIS/graph.json","fetch_events":"https://pith.science/api/pith-number/7O3GUZ374227USR7HFDXJJFCIS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7O3GUZ374227USR7HFDXJJFCIS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7O3GUZ374227USR7HFDXJJFCIS/action/storage_attestation","attest_author":"https://pith.science/pith/7O3GUZ374227USR7HFDXJJFCIS/action/author_attestation","sign_citation":"https://pith.science/pith/7O3GUZ374227USR7HFDXJJFCIS/action/citation_signature","submit_replication":"https://pith.science/pith/7O3GUZ374227USR7HFDXJJFCIS/action/replication_record"}},"created_at":"2026-07-05T04:00:15.199065+00:00","updated_at":"2026-07-05T04:00:15.199065+00:00"}