{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:S7F66G2KUHMFPDHSOOBTFAPLHN","short_pith_number":"pith:S7F66G2K","schema_version":"1.0","canonical_sha256":"97cbef1b4aa1d8578cf273833281eb3b6444775bbd7c2029c2b51552d01c57a0","source":{"kind":"arxiv","id":"2201.09186","version":3},"attestation_state":"computed","paper":{"title":"pvCNN: Privacy-Preserving and Verifiable Convolutional Neural Network Testing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CR","authors_text":"Anjia Yang, Gui Tang, Jia-Nan Liu, Jian Weng, Jiasi Weng, Ming Li","submitted_at":"2022-01-23T05:33:49Z","abstract_excerpt":"This paper proposes a new approach for privacy-preserving and verifiable convolutional neural network (CNN) testing, enabling a CNN model developer to convince a user of the truthful CNN performance over non-public data from multiple testers, while respecting model privacy. To balance the security and efficiency issues, three new efforts are done by appropriately integrating homomorphic encryption (HE) and zero-knowledge succinct non-interactive argument of knowledge (zk-SNARK) primitives with the CNN testing. First, a CNN model to be tested is strategically partitioned into a private part kep"},"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":"2201.09186","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2022-01-23T05:33:49Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"6e6165b3b37962666574a60e5e46c81406456e43cdb54e9b073d9ac7f2ac341f","abstract_canon_sha256":"e74d203f83ba6b4a17ef1130efbe8fc4e41193b4e6628c3198ecc48a438ae64e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:14:33.764394Z","signature_b64":"AXp0zidG187batpsXh3gLUAdAJEY4TLoHZHLKWoC6datq2eJWkmQ2v/2+++p1BwEGKUcN8oAg/MKsLTJPt2KCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"97cbef1b4aa1d8578cf273833281eb3b6444775bbd7c2029c2b51552d01c57a0","last_reissued_at":"2026-07-05T06:14:33.763957Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:14:33.763957Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"pvCNN: Privacy-Preserving and Verifiable Convolutional Neural Network Testing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CR","authors_text":"Anjia Yang, Gui Tang, Jia-Nan Liu, Jian Weng, Jiasi Weng, Ming Li","submitted_at":"2022-01-23T05:33:49Z","abstract_excerpt":"This paper proposes a new approach for privacy-preserving and verifiable convolutional neural network (CNN) testing, enabling a CNN model developer to convince a user of the truthful CNN performance over non-public data from multiple testers, while respecting model privacy. To balance the security and efficiency issues, three new efforts are done by appropriately integrating homomorphic encryption (HE) and zero-knowledge succinct non-interactive argument of knowledge (zk-SNARK) primitives with the CNN testing. First, a CNN model to be tested is strategically partitioned into a private part kep"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.09186","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/2201.09186/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":"2201.09186","created_at":"2026-07-05T06:14:33.764020+00:00"},{"alias_kind":"arxiv_version","alias_value":"2201.09186v3","created_at":"2026-07-05T06:14:33.764020+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.09186","created_at":"2026-07-05T06:14:33.764020+00:00"},{"alias_kind":"pith_short_12","alias_value":"S7F66G2KUHMF","created_at":"2026-07-05T06:14:33.764020+00:00"},{"alias_kind":"pith_short_16","alias_value":"S7F66G2KUHMFPDHS","created_at":"2026-07-05T06:14:33.764020+00:00"},{"alias_kind":"pith_short_8","alias_value":"S7F66G2K","created_at":"2026-07-05T06:14:33.764020+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/S7F66G2KUHMFPDHSOOBTFAPLHN","json":"https://pith.science/pith/S7F66G2KUHMFPDHSOOBTFAPLHN.json","graph_json":"https://pith.science/api/pith-number/S7F66G2KUHMFPDHSOOBTFAPLHN/graph.json","events_json":"https://pith.science/api/pith-number/S7F66G2KUHMFPDHSOOBTFAPLHN/events.json","paper":"https://pith.science/paper/S7F66G2K"},"agent_actions":{"view_html":"https://pith.science/pith/S7F66G2KUHMFPDHSOOBTFAPLHN","download_json":"https://pith.science/pith/S7F66G2KUHMFPDHSOOBTFAPLHN.json","view_paper":"https://pith.science/paper/S7F66G2K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2201.09186&json=true","fetch_graph":"https://pith.science/api/pith-number/S7F66G2KUHMFPDHSOOBTFAPLHN/graph.json","fetch_events":"https://pith.science/api/pith-number/S7F66G2KUHMFPDHSOOBTFAPLHN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/S7F66G2KUHMFPDHSOOBTFAPLHN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/S7F66G2KUHMFPDHSOOBTFAPLHN/action/storage_attestation","attest_author":"https://pith.science/pith/S7F66G2KUHMFPDHSOOBTFAPLHN/action/author_attestation","sign_citation":"https://pith.science/pith/S7F66G2KUHMFPDHSOOBTFAPLHN/action/citation_signature","submit_replication":"https://pith.science/pith/S7F66G2KUHMFPDHSOOBTFAPLHN/action/replication_record"}},"created_at":"2026-07-05T06:14:33.764020+00:00","updated_at":"2026-07-05T06:14:33.764020+00:00"}