{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:7REQXKBWXHXRBTFFGUUSG2TJ26","short_pith_number":"pith:7REQXKBW","schema_version":"1.0","canonical_sha256":"fc490ba836b9ef10cca53529236a69d7ac39689a6f143fe7e49a3149fcc6c30c","source":{"kind":"arxiv","id":"2306.07973","version":1},"attestation_state":"computed","paper":{"title":"PrivaScissors: Enhance the Privacy of Collaborative Inference through the Lens of Mutual Information","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CR","authors_text":"Jingwei Sun, Lin Duan, Maria Gorlatova, Yiran Chen","submitted_at":"2023-05-17T20:15:26Z","abstract_excerpt":"Edge-cloud collaborative inference empowers resource-limited IoT devices to support deep learning applications without disclosing their raw data to the cloud server, thus preserving privacy. Nevertheless, prior research has shown that collaborative inference still results in the exposure of data and predictions from edge devices. To enhance the privacy of collaborative inference, we introduce a defense strategy called PrivaScissors, which is designed to reduce the mutual information between a model's intermediate outcomes and the device's data and predictions. We evaluate PrivaScissors's perfo"},"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":"2306.07973","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CR","submitted_at":"2023-05-17T20:15:26Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"df8c1433a3749d7d23633df5e5551c389a00e13d13877e442a9505fadeb5a757","abstract_canon_sha256":"5ed2c66062d52bd8bdf7295c62289cad861e69dad8bc5393d59bdb01e31533db"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:20:45.938365Z","signature_b64":"qf6zwt0w03x2rVgJI+elWcMfx+SCEgGKrM/sbsAdHV2txh86NejY4UCGcX5JBiv2XeCqh7KVAggC7iduaDE2Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fc490ba836b9ef10cca53529236a69d7ac39689a6f143fe7e49a3149fcc6c30c","last_reissued_at":"2026-07-05T06:20:45.937891Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:20:45.937891Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PrivaScissors: Enhance the Privacy of Collaborative Inference through the Lens of Mutual Information","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CR","authors_text":"Jingwei Sun, Lin Duan, Maria Gorlatova, Yiran Chen","submitted_at":"2023-05-17T20:15:26Z","abstract_excerpt":"Edge-cloud collaborative inference empowers resource-limited IoT devices to support deep learning applications without disclosing their raw data to the cloud server, thus preserving privacy. Nevertheless, prior research has shown that collaborative inference still results in the exposure of data and predictions from edge devices. To enhance the privacy of collaborative inference, we introduce a defense strategy called PrivaScissors, which is designed to reduce the mutual information between a model's intermediate outcomes and the device's data and predictions. We evaluate PrivaScissors's perfo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.07973","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2306.07973/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":"2306.07973","created_at":"2026-07-05T06:20:45.937949+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.07973v1","created_at":"2026-07-05T06:20:45.937949+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.07973","created_at":"2026-07-05T06:20:45.937949+00:00"},{"alias_kind":"pith_short_12","alias_value":"7REQXKBWXHXR","created_at":"2026-07-05T06:20:45.937949+00:00"},{"alias_kind":"pith_short_16","alias_value":"7REQXKBWXHXRBTFF","created_at":"2026-07-05T06:20:45.937949+00:00"},{"alias_kind":"pith_short_8","alias_value":"7REQXKBW","created_at":"2026-07-05T06:20:45.937949+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2506.15412","citing_title":"Partitioning for Intrinsic Model Inversion Resistance in Collaborative Inference","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7REQXKBWXHXRBTFFGUUSG2TJ26","json":"https://pith.science/pith/7REQXKBWXHXRBTFFGUUSG2TJ26.json","graph_json":"https://pith.science/api/pith-number/7REQXKBWXHXRBTFFGUUSG2TJ26/graph.json","events_json":"https://pith.science/api/pith-number/7REQXKBWXHXRBTFFGUUSG2TJ26/events.json","paper":"https://pith.science/paper/7REQXKBW"},"agent_actions":{"view_html":"https://pith.science/pith/7REQXKBWXHXRBTFFGUUSG2TJ26","download_json":"https://pith.science/pith/7REQXKBWXHXRBTFFGUUSG2TJ26.json","view_paper":"https://pith.science/paper/7REQXKBW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.07973&json=true","fetch_graph":"https://pith.science/api/pith-number/7REQXKBWXHXRBTFFGUUSG2TJ26/graph.json","fetch_events":"https://pith.science/api/pith-number/7REQXKBWXHXRBTFFGUUSG2TJ26/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7REQXKBWXHXRBTFFGUUSG2TJ26/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7REQXKBWXHXRBTFFGUUSG2TJ26/action/storage_attestation","attest_author":"https://pith.science/pith/7REQXKBWXHXRBTFFGUUSG2TJ26/action/author_attestation","sign_citation":"https://pith.science/pith/7REQXKBWXHXRBTFFGUUSG2TJ26/action/citation_signature","submit_replication":"https://pith.science/pith/7REQXKBWXHXRBTFFGUUSG2TJ26/action/replication_record"}},"created_at":"2026-07-05T06:20:45.937949+00:00","updated_at":"2026-07-05T06:20:45.937949+00:00"}