{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:7Q4WRIJLQLQUH6ED54TBI5KSRP","short_pith_number":"pith:7Q4WRIJL","schema_version":"1.0","canonical_sha256":"fc3968a12b82e143f883ef261475528bc19bb2a5acd5db131ca463951f8dac9a","source":{"kind":"arxiv","id":"2011.05530","version":4},"attestation_state":"computed","paper":{"title":"On Polynomial Approximations for Privacy-Preserving and Verifiable ReLU Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","cs.IT","math.IT"],"primary_cat":"cs.LG","authors_text":"A. Salman Avestimehr, Jinhyun So, Ramy E. Ali","submitted_at":"2020-11-11T03:32:22Z","abstract_excerpt":"Outsourcing deep neural networks (DNNs) inference tasks to an untrusted cloud raises data privacy and integrity concerns. While there are many techniques to ensure privacy and integrity for polynomial-based computations, DNNs involve non-polynomial computations. To address these challenges, several privacy-preserving and verifiable inference techniques have been proposed based on replacing the non-polynomial activation functions such as the rectified linear unit (ReLU) function with polynomial activation functions. Such techniques usually require polynomials with integer coefficients or polyno"},"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":"2011.05530","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-11-11T03:32:22Z","cross_cats_sorted":["cs.CR","cs.IT","math.IT"],"title_canon_sha256":"8145da8dae802dbce9fdcb4fa60d8173b346686634c5f658edb5f25a2db40e91","abstract_canon_sha256":"85d3c36e9cc9bed833c5f314b0869411255c9f9e4076ddc10a816312bd76bd7d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:41:35.251069Z","signature_b64":"p/688RZ0I2UysrgL2HUvDkIXRW319ytczF/sztOt1zMizW8l3z3P4o09ITHIqyPTYPgnTlJCBRdiyMVQUnd4Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fc3968a12b82e143f883ef261475528bc19bb2a5acd5db131ca463951f8dac9a","last_reissued_at":"2026-07-05T07:41:35.250675Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:41:35.250675Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On Polynomial Approximations for Privacy-Preserving and Verifiable ReLU Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","cs.IT","math.IT"],"primary_cat":"cs.LG","authors_text":"A. Salman Avestimehr, Jinhyun So, Ramy E. Ali","submitted_at":"2020-11-11T03:32:22Z","abstract_excerpt":"Outsourcing deep neural networks (DNNs) inference tasks to an untrusted cloud raises data privacy and integrity concerns. While there are many techniques to ensure privacy and integrity for polynomial-based computations, DNNs involve non-polynomial computations. To address these challenges, several privacy-preserving and verifiable inference techniques have been proposed based on replacing the non-polynomial activation functions such as the rectified linear unit (ReLU) function with polynomial activation functions. Such techniques usually require polynomials with integer coefficients or polyno"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.05530","kind":"arxiv","version":4},"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/2011.05530/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":"2011.05530","created_at":"2026-07-05T07:41:35.250724+00:00"},{"alias_kind":"arxiv_version","alias_value":"2011.05530v4","created_at":"2026-07-05T07:41:35.250724+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.05530","created_at":"2026-07-05T07:41:35.250724+00:00"},{"alias_kind":"pith_short_12","alias_value":"7Q4WRIJLQLQU","created_at":"2026-07-05T07:41:35.250724+00:00"},{"alias_kind":"pith_short_16","alias_value":"7Q4WRIJLQLQUH6ED","created_at":"2026-07-05T07:41:35.250724+00:00"},{"alias_kind":"pith_short_8","alias_value":"7Q4WRIJL","created_at":"2026-07-05T07:41:35.250724+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.02068","citing_title":"Robust and Secure Code Watermarking for Large Language Models via ML/Crypto Codesign","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7Q4WRIJLQLQUH6ED54TBI5KSRP","json":"https://pith.science/pith/7Q4WRIJLQLQUH6ED54TBI5KSRP.json","graph_json":"https://pith.science/api/pith-number/7Q4WRIJLQLQUH6ED54TBI5KSRP/graph.json","events_json":"https://pith.science/api/pith-number/7Q4WRIJLQLQUH6ED54TBI5KSRP/events.json","paper":"https://pith.science/paper/7Q4WRIJL"},"agent_actions":{"view_html":"https://pith.science/pith/7Q4WRIJLQLQUH6ED54TBI5KSRP","download_json":"https://pith.science/pith/7Q4WRIJLQLQUH6ED54TBI5KSRP.json","view_paper":"https://pith.science/paper/7Q4WRIJL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2011.05530&json=true","fetch_graph":"https://pith.science/api/pith-number/7Q4WRIJLQLQUH6ED54TBI5KSRP/graph.json","fetch_events":"https://pith.science/api/pith-number/7Q4WRIJLQLQUH6ED54TBI5KSRP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7Q4WRIJLQLQUH6ED54TBI5KSRP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7Q4WRIJLQLQUH6ED54TBI5KSRP/action/storage_attestation","attest_author":"https://pith.science/pith/7Q4WRIJLQLQUH6ED54TBI5KSRP/action/author_attestation","sign_citation":"https://pith.science/pith/7Q4WRIJLQLQUH6ED54TBI5KSRP/action/citation_signature","submit_replication":"https://pith.science/pith/7Q4WRIJLQLQUH6ED54TBI5KSRP/action/replication_record"}},"created_at":"2026-07-05T07:41:35.250724+00:00","updated_at":"2026-07-05T07:41:35.250724+00:00"}