{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:HILMIW236WOLCNK6EWGHVKUGLP","short_pith_number":"pith:HILMIW23","schema_version":"1.0","canonical_sha256":"3a16c45b5bf59cb1355e258c7aaa865bf36de548361549c0933f8810548a43ea","source":{"kind":"arxiv","id":"2503.03454","version":2},"attestation_state":"computed","paper":{"title":"Data Poisoning Attacks to Locally Differentially Private Range Query Protocols","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CR","authors_text":"Chia-Mu Yu, Chih-Hsun Lin, Chun-Ying Huang, Hiroaki Kikuchi, Jun Sakuma, Takao Murakami, Ting-Wei Liao, Yu-Lin Tsai","submitted_at":"2025-03-05T12:40:34Z","abstract_excerpt":"Local Differential Privacy (LDP) has been widely adopted to protect user privacy in decentralized data collection. However, recent studies have revealed that LDP protocols are vulnerable to data poisoning attacks, where malicious users manipulate their reported data to distort aggregated results. In this work, we present the first study on data poisoning attacks targeting LDP range query protocols, focusing on both tree-based and grid-based approaches. We identify three key challenges in executing such attacks, including crafting consistent and effective fake data, maintaining data consistency"},"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":"2503.03454","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2025-03-05T12:40:34Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"0e75aed87c2267723bcdbcb53a845aca2ad57c66b8e2bc7817ae83ec784cf7ed","abstract_canon_sha256":"ab0af65290d4f7058959960c49c7b6ec1406a8437056a0513bd44833f87f3f4e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:25:20.089499Z","signature_b64":"1cClyMYGKe1RigcGoRknixlPWP3HuZUivrc0D0PbvPSuTf5asDSXSLrfEm7cfOxluU+s+gnyar33XQZHTlXUAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3a16c45b5bf59cb1355e258c7aaa865bf36de548361549c0933f8810548a43ea","last_reissued_at":"2026-07-05T10:25:20.089040Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:25:20.089040Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Data Poisoning Attacks to Locally Differentially Private Range Query Protocols","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CR","authors_text":"Chia-Mu Yu, Chih-Hsun Lin, Chun-Ying Huang, Hiroaki Kikuchi, Jun Sakuma, Takao Murakami, Ting-Wei Liao, Yu-Lin Tsai","submitted_at":"2025-03-05T12:40:34Z","abstract_excerpt":"Local Differential Privacy (LDP) has been widely adopted to protect user privacy in decentralized data collection. However, recent studies have revealed that LDP protocols are vulnerable to data poisoning attacks, where malicious users manipulate their reported data to distort aggregated results. In this work, we present the first study on data poisoning attacks targeting LDP range query protocols, focusing on both tree-based and grid-based approaches. We identify three key challenges in executing such attacks, including crafting consistent and effective fake data, maintaining data consistency"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.03454","kind":"arxiv","version":2},"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/2503.03454/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":"2503.03454","created_at":"2026-07-05T10:25:20.089096+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.03454v2","created_at":"2026-07-05T10:25:20.089096+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.03454","created_at":"2026-07-05T10:25:20.089096+00:00"},{"alias_kind":"pith_short_12","alias_value":"HILMIW236WOL","created_at":"2026-07-05T10:25:20.089096+00:00"},{"alias_kind":"pith_short_16","alias_value":"HILMIW236WOLCNK6","created_at":"2026-07-05T10:25:20.089096+00:00"},{"alias_kind":"pith_short_8","alias_value":"HILMIW23","created_at":"2026-07-05T10:25:20.089096+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.02004","citing_title":"Augmented Shuffle Differential Privacy Protocols for Large-Domain Categorical and Key-Value Data","ref_index":68,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HILMIW236WOLCNK6EWGHVKUGLP","json":"https://pith.science/pith/HILMIW236WOLCNK6EWGHVKUGLP.json","graph_json":"https://pith.science/api/pith-number/HILMIW236WOLCNK6EWGHVKUGLP/graph.json","events_json":"https://pith.science/api/pith-number/HILMIW236WOLCNK6EWGHVKUGLP/events.json","paper":"https://pith.science/paper/HILMIW23"},"agent_actions":{"view_html":"https://pith.science/pith/HILMIW236WOLCNK6EWGHVKUGLP","download_json":"https://pith.science/pith/HILMIW236WOLCNK6EWGHVKUGLP.json","view_paper":"https://pith.science/paper/HILMIW23","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.03454&json=true","fetch_graph":"https://pith.science/api/pith-number/HILMIW236WOLCNK6EWGHVKUGLP/graph.json","fetch_events":"https://pith.science/api/pith-number/HILMIW236WOLCNK6EWGHVKUGLP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HILMIW236WOLCNK6EWGHVKUGLP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HILMIW236WOLCNK6EWGHVKUGLP/action/storage_attestation","attest_author":"https://pith.science/pith/HILMIW236WOLCNK6EWGHVKUGLP/action/author_attestation","sign_citation":"https://pith.science/pith/HILMIW236WOLCNK6EWGHVKUGLP/action/citation_signature","submit_replication":"https://pith.science/pith/HILMIW236WOLCNK6EWGHVKUGLP/action/replication_record"}},"created_at":"2026-07-05T10:25:20.089096+00:00","updated_at":"2026-07-05T10:25:20.089096+00:00"}