{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:HBKOHLDB62SXCWJGEI4TX5JVYA","short_pith_number":"pith:HBKOHLDB","schema_version":"1.0","canonical_sha256":"3854e3ac61f6a571592622393bf535c033148fcc14eae7f380bb9e38b60cd688","source":{"kind":"arxiv","id":"2603.03711","version":3},"attestation_state":"computed","paper":{"title":"LDP-Slicing: Local Differential Privacy for Images via Randomized Bit-Plane Slicing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chengqi Li, Wenbo He, Yuanming Cao","submitted_at":"2026-03-04T04:25:41Z","abstract_excerpt":"Local Differential Privacy (LDP) is the gold standard trust model for privacy-preserving machine learning by guaranteeing privacy at the data source. However, its application to image data has long been considered impractical due to the high dimensionality of pixel space. Canonical LDP mechanisms are designed for low-dimensional data, resulting in severe utility degradation when applied to high-dimensional pixel spaces. This paper demonstrates that this utility loss is not inherent to LDP, but from its application to an inappropriate data representation. We introduce LDP-Slicing, a lightweight"},"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":"2603.03711","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-03-04T04:25:41Z","cross_cats_sorted":[],"title_canon_sha256":"b6b4d6479670e0be3fb7113a9afe6ef7fd68cead0df5e7858863b1e796a1b3de","abstract_canon_sha256":"465a45fa0fb4ce778bbfb7219448426309a81d38baec3ca247546e46a3fd49ae"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-27T01:04:56.819414Z","signature_b64":"hc7Tj/jYZb1kbWIOht8zfWCVzAlWTrPyLS4ELZs18FP9XWB3R5LwBm8LJrczeT3rFz4t2zlA5vRFpTchKEcFCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3854e3ac61f6a571592622393bf535c033148fcc14eae7f380bb9e38b60cd688","last_reissued_at":"2026-05-27T01:04:56.818572Z","signature_status":"signed_v1","first_computed_at":"2026-05-27T01:04:56.818572Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LDP-Slicing: Local Differential Privacy for Images via Randomized Bit-Plane Slicing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chengqi Li, Wenbo He, Yuanming Cao","submitted_at":"2026-03-04T04:25:41Z","abstract_excerpt":"Local Differential Privacy (LDP) is the gold standard trust model for privacy-preserving machine learning by guaranteeing privacy at the data source. However, its application to image data has long been considered impractical due to the high dimensionality of pixel space. Canonical LDP mechanisms are designed for low-dimensional data, resulting in severe utility degradation when applied to high-dimensional pixel spaces. This paper demonstrates that this utility loss is not inherent to LDP, but from its application to an inappropriate data representation. We introduce LDP-Slicing, a lightweight"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.03711","kind":"arxiv","version":3},"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/2603.03711/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":"2603.03711","created_at":"2026-05-27T01:04:56.818683+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.03711v3","created_at":"2026-05-27T01:04:56.818683+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.03711","created_at":"2026-05-27T01:04:56.818683+00:00"},{"alias_kind":"pith_short_12","alias_value":"HBKOHLDB62SX","created_at":"2026-05-27T01:04:56.818683+00:00"},{"alias_kind":"pith_short_16","alias_value":"HBKOHLDB62SXCWJG","created_at":"2026-05-27T01:04:56.818683+00:00"},{"alias_kind":"pith_short_8","alias_value":"HBKOHLDB","created_at":"2026-05-27T01:04:56.818683+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.08343","citing_title":"Private Vertical Federated Inference for Time-Series","ref_index":38,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HBKOHLDB62SXCWJGEI4TX5JVYA","json":"https://pith.science/pith/HBKOHLDB62SXCWJGEI4TX5JVYA.json","graph_json":"https://pith.science/api/pith-number/HBKOHLDB62SXCWJGEI4TX5JVYA/graph.json","events_json":"https://pith.science/api/pith-number/HBKOHLDB62SXCWJGEI4TX5JVYA/events.json","paper":"https://pith.science/paper/HBKOHLDB"},"agent_actions":{"view_html":"https://pith.science/pith/HBKOHLDB62SXCWJGEI4TX5JVYA","download_json":"https://pith.science/pith/HBKOHLDB62SXCWJGEI4TX5JVYA.json","view_paper":"https://pith.science/paper/HBKOHLDB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.03711&json=true","fetch_graph":"https://pith.science/api/pith-number/HBKOHLDB62SXCWJGEI4TX5JVYA/graph.json","fetch_events":"https://pith.science/api/pith-number/HBKOHLDB62SXCWJGEI4TX5JVYA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HBKOHLDB62SXCWJGEI4TX5JVYA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HBKOHLDB62SXCWJGEI4TX5JVYA/action/storage_attestation","attest_author":"https://pith.science/pith/HBKOHLDB62SXCWJGEI4TX5JVYA/action/author_attestation","sign_citation":"https://pith.science/pith/HBKOHLDB62SXCWJGEI4TX5JVYA/action/citation_signature","submit_replication":"https://pith.science/pith/HBKOHLDB62SXCWJGEI4TX5JVYA/action/replication_record"}},"created_at":"2026-05-27T01:04:56.818683+00:00","updated_at":"2026-05-27T01:04:56.818683+00:00"}