{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:M7UKSEUMP77X6SEO5MUE3T4557","short_pith_number":"pith:M7UKSEUM","schema_version":"1.0","canonical_sha256":"67e8a9128c7fff7f488eeb284dcf9defef999f3a0f7833550184c439cf68e779","source":{"kind":"arxiv","id":"2205.03040","version":5},"attestation_state":"computed","paper":{"title":"Fusion: Efficient and Secure Inference Resilient to Malicious Servers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CR","authors_text":"Anjia Yang, Caiqin Dong, Jia-Nan Liu, Jian Weng, Shun Hu, Yao Tong, Yudan Cheng, Yue Zhang","submitted_at":"2022-05-06T06:42:48Z","abstract_excerpt":"In secure machine learning inference, most of the schemes assume that the server is semi-honest (honestly following the protocol but attempting to infer additional information). However, the server may be malicious (e.g., using a low-quality model or deviating from the protocol) in the real world. Although a few studies have considered a malicious server that deviates from the protocol, they ignore the verification of model accuracy (where the malicious server uses a low-quality model) meanwhile preserving the privacy of both the server's model and the client's inputs. To address these issues,"},"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":"2205.03040","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2022-05-06T06:42:48Z","cross_cats_sorted":[],"title_canon_sha256":"05e2bfca6e803570f8d13deaa690723a334593a07b3161f05804674d62555868","abstract_canon_sha256":"20185f48e5d855f35dfdcf0d017e92079468ec8501c5d6e60ab9006e444c001d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:19:15.678676Z","signature_b64":"VULTS9eosyzjyse92Fco70BUPx3UXYSxvR0WdcngZIbeiSnkrN88VNbk7e6+8BKyJF+S6hEY62/dThV6+u7iAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"67e8a9128c7fff7f488eeb284dcf9defef999f3a0f7833550184c439cf68e779","last_reissued_at":"2026-07-05T06:19:15.678211Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:19:15.678211Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fusion: Efficient and Secure Inference Resilient to Malicious Servers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CR","authors_text":"Anjia Yang, Caiqin Dong, Jia-Nan Liu, Jian Weng, Shun Hu, Yao Tong, Yudan Cheng, Yue Zhang","submitted_at":"2022-05-06T06:42:48Z","abstract_excerpt":"In secure machine learning inference, most of the schemes assume that the server is semi-honest (honestly following the protocol but attempting to infer additional information). However, the server may be malicious (e.g., using a low-quality model or deviating from the protocol) in the real world. Although a few studies have considered a malicious server that deviates from the protocol, they ignore the verification of model accuracy (where the malicious server uses a low-quality model) meanwhile preserving the privacy of both the server's model and the client's inputs. To address these issues,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.03040","kind":"arxiv","version":5},"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/2205.03040/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":"2205.03040","created_at":"2026-07-05T06:19:15.678267+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.03040v5","created_at":"2026-07-05T06:19:15.678267+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.03040","created_at":"2026-07-05T06:19:15.678267+00:00"},{"alias_kind":"pith_short_12","alias_value":"M7UKSEUMP77X","created_at":"2026-07-05T06:19:15.678267+00:00"},{"alias_kind":"pith_short_16","alias_value":"M7UKSEUMP77X6SEO","created_at":"2026-07-05T06:19:15.678267+00:00"},{"alias_kind":"pith_short_8","alias_value":"M7UKSEUM","created_at":"2026-07-05T06:19:15.678267+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/M7UKSEUMP77X6SEO5MUE3T4557","json":"https://pith.science/pith/M7UKSEUMP77X6SEO5MUE3T4557.json","graph_json":"https://pith.science/api/pith-number/M7UKSEUMP77X6SEO5MUE3T4557/graph.json","events_json":"https://pith.science/api/pith-number/M7UKSEUMP77X6SEO5MUE3T4557/events.json","paper":"https://pith.science/paper/M7UKSEUM"},"agent_actions":{"view_html":"https://pith.science/pith/M7UKSEUMP77X6SEO5MUE3T4557","download_json":"https://pith.science/pith/M7UKSEUMP77X6SEO5MUE3T4557.json","view_paper":"https://pith.science/paper/M7UKSEUM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.03040&json=true","fetch_graph":"https://pith.science/api/pith-number/M7UKSEUMP77X6SEO5MUE3T4557/graph.json","fetch_events":"https://pith.science/api/pith-number/M7UKSEUMP77X6SEO5MUE3T4557/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M7UKSEUMP77X6SEO5MUE3T4557/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M7UKSEUMP77X6SEO5MUE3T4557/action/storage_attestation","attest_author":"https://pith.science/pith/M7UKSEUMP77X6SEO5MUE3T4557/action/author_attestation","sign_citation":"https://pith.science/pith/M7UKSEUMP77X6SEO5MUE3T4557/action/citation_signature","submit_replication":"https://pith.science/pith/M7UKSEUMP77X6SEO5MUE3T4557/action/replication_record"}},"created_at":"2026-07-05T06:19:15.678267+00:00","updated_at":"2026-07-05T06:19:15.678267+00:00"}