{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:F45FKOCEVWZG5WTEFPQFOAOUJJ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"9567344f3d28f5f8e04eb5d5be321f068f4aed12e794b500d17ccd273c1b7cd4","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2022-08-26T09:42:21Z","title_canon_sha256":"8c4a5b9c234d155460adc2a56029e0a65ec0062f68e2f5f6fdb48d015b3b1fc1"},"schema_version":"1.0","source":{"id":"2209.00411","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.00411","created_at":"2026-07-05T04:54:04Z"},{"alias_kind":"arxiv_version","alias_value":"2209.00411v2","created_at":"2026-07-05T04:54:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.00411","created_at":"2026-07-05T04:54:04Z"},{"alias_kind":"pith_short_12","alias_value":"F45FKOCEVWZG","created_at":"2026-07-05T04:54:04Z"},{"alias_kind":"pith_short_16","alias_value":"F45FKOCEVWZG5WTE","created_at":"2026-07-05T04:54:04Z"},{"alias_kind":"pith_short_8","alias_value":"F45FKOCE","created_at":"2026-07-05T04:54:04Z"}],"graph_snapshots":[{"event_id":"sha256:375d72d1c56fbaa0c537f490d71272f2e8035fb4c479c8f4044ea2455ab47470","target":"graph","created_at":"2026-07-05T04:54:04Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2209.00411/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"ML-as-a-service continues to grow, and so does the need for very strong privacy guarantees. Secure inference has emerged as a potential solution, wherein cryptographic primitives allow inference without revealing users' inputs to a model provider or model's weights to a user. For instance, the model provider could be a diagnostics company that has trained a state-of-the-art DenseNet-121 model for interpreting a chest X-ray and the user could be a patient at a hospital. While secure inference is in principle feasible for this setting, there are no existing techniques that make it practical at s","authors_text":"Anwesh Bhattacharya, Divya Gupta, Nishanth Chandran, Pratyush Kumar, Rahul Sharma, Vinod Ganesan","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2022-08-26T09:42:21Z","title":"Efficient ML Models for Practical Secure Inference"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.00411","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:6bcf290fb87d543ab5772b58ddbb7325a6377b6aebe21115e5053472c2494931","target":"record","created_at":"2026-07-05T04:54:04Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"9567344f3d28f5f8e04eb5d5be321f068f4aed12e794b500d17ccd273c1b7cd4","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2022-08-26T09:42:21Z","title_canon_sha256":"8c4a5b9c234d155460adc2a56029e0a65ec0062f68e2f5f6fdb48d015b3b1fc1"},"schema_version":"1.0","source":{"id":"2209.00411","kind":"arxiv","version":2}},"canonical_sha256":"2f3a553844adb26eda642be05701d44a7346d2b59cc28f147b1bbe5218e758ab","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2f3a553844adb26eda642be05701d44a7346d2b59cc28f147b1bbe5218e758ab","first_computed_at":"2026-07-05T04:54:04.799096Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:54:04.799096Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KFSwgPOZqIIqh99d/oGFz2aYzC4EUiayRuHjKgMiEiXwV1EgFVLFDIcdR71xcm9/p9sb6kuwX9scbC9UtjPjDw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:54:04.799497Z","signed_message":"canonical_sha256_bytes"},"source_id":"2209.00411","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6bcf290fb87d543ab5772b58ddbb7325a6377b6aebe21115e5053472c2494931","sha256:375d72d1c56fbaa0c537f490d71272f2e8035fb4c479c8f4044ea2455ab47470"],"state_sha256":"63fa0613ae166493d58d8ddaa8c506b33b1cc12ad2a1d8a80ea743787da58f47"}