{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:6LRW7JXUW2B3POXEPGBZN5DXGT","short_pith_number":"pith:6LRW7JXU","schema_version":"1.0","canonical_sha256":"f2e36fa6f4b683b7bae4798396f47734c46f067200f6304f1fee7e8d17aebecf","source":{"kind":"arxiv","id":"2212.11133","version":1},"attestation_state":"computed","paper":{"title":"Device-Bind Key-Storageless Hardware AI Model IP Protection: A PUF and Permute-Diffusion Encryption-Enabled Approach","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CR","authors_text":"Jun Wu, Kaoru Ota, Mianxiong Dong, Qianqian Pan","submitted_at":"2022-12-21T15:58:42Z","abstract_excerpt":"Machine learning as a service (MLaaS) framework provides intelligent services or well-trained artificial intelligence (AI) models for local devices. However, in the process of model transmission and deployment, there are security issues, i.e. AI model leakage due to the unreliable transmission environments and illegal abuse at local devices without permission. Although existing works study the intellectual property (IP) protection of AI models, they mainly focus on the watermark-based and encryption-based methods and have the following problems: (i) The watermark-based methods only provide pas"},"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":"2212.11133","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2022-12-21T15:58:42Z","cross_cats_sorted":[],"title_canon_sha256":"ef7e0795b8a6b99840fe2a5d55e869104e48c9434cc8356422718aeee5a8bea9","abstract_canon_sha256":"692ae37494a6844552582e13c75f336cd472c5779e40961004f36eef16c0349a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:27:27.636095Z","signature_b64":"6MkIszXdYaYzPDloDieGmiY/XYEq6w1dV24eOva+q5YlPHRyng8q+70dPzNjGaAE/+HqS0UUKSt+v+hry9ICDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f2e36fa6f4b683b7bae4798396f47734c46f067200f6304f1fee7e8d17aebecf","last_reissued_at":"2026-07-05T05:27:27.635611Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:27:27.635611Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Device-Bind Key-Storageless Hardware AI Model IP Protection: A PUF and Permute-Diffusion Encryption-Enabled Approach","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CR","authors_text":"Jun Wu, Kaoru Ota, Mianxiong Dong, Qianqian Pan","submitted_at":"2022-12-21T15:58:42Z","abstract_excerpt":"Machine learning as a service (MLaaS) framework provides intelligent services or well-trained artificial intelligence (AI) models for local devices. However, in the process of model transmission and deployment, there are security issues, i.e. AI model leakage due to the unreliable transmission environments and illegal abuse at local devices without permission. Although existing works study the intellectual property (IP) protection of AI models, they mainly focus on the watermark-based and encryption-based methods and have the following problems: (i) The watermark-based methods only provide pas"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.11133","kind":"arxiv","version":1},"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/2212.11133/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":"2212.11133","created_at":"2026-07-05T05:27:27.635674+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.11133v1","created_at":"2026-07-05T05:27:27.635674+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.11133","created_at":"2026-07-05T05:27:27.635674+00:00"},{"alias_kind":"pith_short_12","alias_value":"6LRW7JXUW2B3","created_at":"2026-07-05T05:27:27.635674+00:00"},{"alias_kind":"pith_short_16","alias_value":"6LRW7JXUW2B3POXE","created_at":"2026-07-05T05:27:27.635674+00:00"},{"alias_kind":"pith_short_8","alias_value":"6LRW7JXU","created_at":"2026-07-05T05:27:27.635674+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2504.12914","citing_title":"In Which Areas of Technical AI Safety Could Geopolitical Rivals Cooperate?","ref_index":81,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6LRW7JXUW2B3POXEPGBZN5DXGT","json":"https://pith.science/pith/6LRW7JXUW2B3POXEPGBZN5DXGT.json","graph_json":"https://pith.science/api/pith-number/6LRW7JXUW2B3POXEPGBZN5DXGT/graph.json","events_json":"https://pith.science/api/pith-number/6LRW7JXUW2B3POXEPGBZN5DXGT/events.json","paper":"https://pith.science/paper/6LRW7JXU"},"agent_actions":{"view_html":"https://pith.science/pith/6LRW7JXUW2B3POXEPGBZN5DXGT","download_json":"https://pith.science/pith/6LRW7JXUW2B3POXEPGBZN5DXGT.json","view_paper":"https://pith.science/paper/6LRW7JXU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.11133&json=true","fetch_graph":"https://pith.science/api/pith-number/6LRW7JXUW2B3POXEPGBZN5DXGT/graph.json","fetch_events":"https://pith.science/api/pith-number/6LRW7JXUW2B3POXEPGBZN5DXGT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6LRW7JXUW2B3POXEPGBZN5DXGT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6LRW7JXUW2B3POXEPGBZN5DXGT/action/storage_attestation","attest_author":"https://pith.science/pith/6LRW7JXUW2B3POXEPGBZN5DXGT/action/author_attestation","sign_citation":"https://pith.science/pith/6LRW7JXUW2B3POXEPGBZN5DXGT/action/citation_signature","submit_replication":"https://pith.science/pith/6LRW7JXUW2B3POXEPGBZN5DXGT/action/replication_record"}},"created_at":"2026-07-05T05:27:27.635674+00:00","updated_at":"2026-07-05T05:27:27.635674+00:00"}