{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:4VR7LNNMSCLN3UT6KQWHT6NVET","short_pith_number":"pith:4VR7LNNM","schema_version":"1.0","canonical_sha256":"e563f5b5ac9096ddd27e542c79f9b524c760e787d6a5d128ba91f058c9dc888f","source":{"kind":"arxiv","id":"1801.05507","version":1},"attestation_state":"computed","paper":{"title":"Gazelle: A Low Latency Framework for Secure Neural Network Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CR","authors_text":"Anantha Chandrakasan, Chiraag Juvekar, Vinod Vaikuntanathan","submitted_at":"2018-01-16T23:58:47Z","abstract_excerpt":"The growing popularity of cloud-based machine learning raises a natural question about the privacy guarantees that can be provided in such a setting. Our work tackles this problem in the context where a client wishes to classify private images using a convolutional neural network (CNN) trained by a server. Our goal is to build efficient protocols whereby the client can acquire the classification result without revealing their input to the server, while guaranteeing the privacy of the server's neural network.\n  To this end, we design Gazelle, a scalable and low-latency system for secure neural "},"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":"1801.05507","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2018-01-16T23:58:47Z","cross_cats_sorted":[],"title_canon_sha256":"d1812d8969e802f0de27374d492920044e481286c5c252fbc5d1dd958bc25813","abstract_canon_sha256":"9b5226149328aea5a4b370b1fa08144ca1b726a9c335618a1a26bdd8679a5cec"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:25:41.074976Z","signature_b64":"HcaxIzkJNuXD8RPeizQJWG2/kC0PTnrphTpTLSlfdGhkPAavHZv3vrdisedN36HREfJckyQJ9u75kAF2KCyCDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e563f5b5ac9096ddd27e542c79f9b524c760e787d6a5d128ba91f058c9dc888f","last_reissued_at":"2026-05-18T00:25:41.074441Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:25:41.074441Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Gazelle: A Low Latency Framework for Secure Neural Network Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CR","authors_text":"Anantha Chandrakasan, Chiraag Juvekar, Vinod Vaikuntanathan","submitted_at":"2018-01-16T23:58:47Z","abstract_excerpt":"The growing popularity of cloud-based machine learning raises a natural question about the privacy guarantees that can be provided in such a setting. Our work tackles this problem in the context where a client wishes to classify private images using a convolutional neural network (CNN) trained by a server. Our goal is to build efficient protocols whereby the client can acquire the classification result without revealing their input to the server, while guaranteeing the privacy of the server's neural network.\n  To this end, we design Gazelle, a scalable and low-latency system for secure neural "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1801.05507","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":""},"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":"1801.05507","created_at":"2026-05-18T00:25:41.074522+00:00"},{"alias_kind":"arxiv_version","alias_value":"1801.05507v1","created_at":"2026-05-18T00:25:41.074522+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1801.05507","created_at":"2026-05-18T00:25:41.074522+00:00"},{"alias_kind":"pith_short_12","alias_value":"4VR7LNNMSCLN","created_at":"2026-05-18T12:32:05.422762+00:00"},{"alias_kind":"pith_short_16","alias_value":"4VR7LNNMSCLN3UT6","created_at":"2026-05-18T12:32:05.422762+00:00"},{"alias_kind":"pith_short_8","alias_value":"4VR7LNNM","created_at":"2026-05-18T12:32:05.422762+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.07047","citing_title":"Leveraging ASIC AI Chips for Homomorphic Encryption","ref_index":39,"is_internal_anchor":true},{"citing_arxiv_id":"2605.03213","citing_title":"When Agents Handle Secrets: A Survey of Confidential Computing for Agentic AI","ref_index":65,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17476","citing_title":"Privatar: Scalable Privacy-preserving Multi-user VR via Secure Offloading","ref_index":168,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03213","citing_title":"When Agents Handle Secrets: A Survey of Confidential Computing for Agentic AI","ref_index":65,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4VR7LNNMSCLN3UT6KQWHT6NVET","json":"https://pith.science/pith/4VR7LNNMSCLN3UT6KQWHT6NVET.json","graph_json":"https://pith.science/api/pith-number/4VR7LNNMSCLN3UT6KQWHT6NVET/graph.json","events_json":"https://pith.science/api/pith-number/4VR7LNNMSCLN3UT6KQWHT6NVET/events.json","paper":"https://pith.science/paper/4VR7LNNM"},"agent_actions":{"view_html":"https://pith.science/pith/4VR7LNNMSCLN3UT6KQWHT6NVET","download_json":"https://pith.science/pith/4VR7LNNMSCLN3UT6KQWHT6NVET.json","view_paper":"https://pith.science/paper/4VR7LNNM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1801.05507&json=true","fetch_graph":"https://pith.science/api/pith-number/4VR7LNNMSCLN3UT6KQWHT6NVET/graph.json","fetch_events":"https://pith.science/api/pith-number/4VR7LNNMSCLN3UT6KQWHT6NVET/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4VR7LNNMSCLN3UT6KQWHT6NVET/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4VR7LNNMSCLN3UT6KQWHT6NVET/action/storage_attestation","attest_author":"https://pith.science/pith/4VR7LNNMSCLN3UT6KQWHT6NVET/action/author_attestation","sign_citation":"https://pith.science/pith/4VR7LNNMSCLN3UT6KQWHT6NVET/action/citation_signature","submit_replication":"https://pith.science/pith/4VR7LNNMSCLN3UT6KQWHT6NVET/action/replication_record"}},"created_at":"2026-05-18T00:25:41.074522+00:00","updated_at":"2026-05-18T00:25:41.074522+00:00"}