{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:4A25BCJ3UPVQ5YSZAIUO5K6XKZ","short_pith_number":"pith:4A25BCJ3","schema_version":"1.0","canonical_sha256":"e035d0893ba3eb0ee2590228eeabd75657f66bd33c366510ccf873e947cc7c9b","source":{"kind":"arxiv","id":"2507.06262","version":1},"attestation_state":"computed","paper":{"title":"Q-Detection: A Quantum-Classical Hybrid Poisoning Attack Detection Method","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","quant-ph"],"primary_cat":"cs.CR","authors_text":"Haoqi He, Jiancai Chen, Xiaokai Lin, Yan Xiao","submitted_at":"2025-07-07T18:43:34Z","abstract_excerpt":"Data poisoning attacks pose significant threats to machine learning models by introducing malicious data into the training process, thereby degrading model performance or manipulating predictions. Detecting and sifting out poisoned data is an important method to prevent data poisoning attacks. Limited by classical computation frameworks, upcoming larger-scale and more complex datasets may pose difficulties for detection. We introduce the unique speedup of quantum computing for the first time in the task of detecting data poisoning. We present Q-Detection, a quantum-classical hybrid defense met"},"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":"2507.06262","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CR","submitted_at":"2025-07-07T18:43:34Z","cross_cats_sorted":["cs.AI","cs.LG","quant-ph"],"title_canon_sha256":"0f6974ddec386e17a110e09627ec74c448544aed2e7f2f583c0b231844c1f96c","abstract_canon_sha256":"8f6d7fa840e2e2e43c8304c733adce1491f9313778e15bfb81598efe759a55e8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:34:12.764048Z","signature_b64":"eS20U1mui7lTq7jzMnsMwfUK47o/Vhfsf8Drv05/Auo/MqV8E2XnYsG5XVgO9JN+y4d3P5HQFQi1nLHi85aNAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e035d0893ba3eb0ee2590228eeabd75657f66bd33c366510ccf873e947cc7c9b","last_reissued_at":"2026-07-05T11:34:12.763503Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:34:12.763503Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Q-Detection: A Quantum-Classical Hybrid Poisoning Attack Detection Method","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","quant-ph"],"primary_cat":"cs.CR","authors_text":"Haoqi He, Jiancai Chen, Xiaokai Lin, Yan Xiao","submitted_at":"2025-07-07T18:43:34Z","abstract_excerpt":"Data poisoning attacks pose significant threats to machine learning models by introducing malicious data into the training process, thereby degrading model performance or manipulating predictions. Detecting and sifting out poisoned data is an important method to prevent data poisoning attacks. Limited by classical computation frameworks, upcoming larger-scale and more complex datasets may pose difficulties for detection. We introduce the unique speedup of quantum computing for the first time in the task of detecting data poisoning. We present Q-Detection, a quantum-classical hybrid defense met"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.06262","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/2507.06262/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":"2507.06262","created_at":"2026-07-05T11:34:12.763567+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.06262v1","created_at":"2026-07-05T11:34:12.763567+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.06262","created_at":"2026-07-05T11:34:12.763567+00:00"},{"alias_kind":"pith_short_12","alias_value":"4A25BCJ3UPVQ","created_at":"2026-07-05T11:34:12.763567+00:00"},{"alias_kind":"pith_short_16","alias_value":"4A25BCJ3UPVQ5YSZ","created_at":"2026-07-05T11:34:12.763567+00:00"},{"alias_kind":"pith_short_8","alias_value":"4A25BCJ3","created_at":"2026-07-05T11:34:12.763567+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.18821","citing_title":"Quantum Adversarial Machine Learning: From Classical Adaptations to Quantum-Native Methods","ref_index":119,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15488","citing_title":"FineSteer: A Unified Framework for Fine-Grained Inference-Time Steering in Large Language Models","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4A25BCJ3UPVQ5YSZAIUO5K6XKZ","json":"https://pith.science/pith/4A25BCJ3UPVQ5YSZAIUO5K6XKZ.json","graph_json":"https://pith.science/api/pith-number/4A25BCJ3UPVQ5YSZAIUO5K6XKZ/graph.json","events_json":"https://pith.science/api/pith-number/4A25BCJ3UPVQ5YSZAIUO5K6XKZ/events.json","paper":"https://pith.science/paper/4A25BCJ3"},"agent_actions":{"view_html":"https://pith.science/pith/4A25BCJ3UPVQ5YSZAIUO5K6XKZ","download_json":"https://pith.science/pith/4A25BCJ3UPVQ5YSZAIUO5K6XKZ.json","view_paper":"https://pith.science/paper/4A25BCJ3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.06262&json=true","fetch_graph":"https://pith.science/api/pith-number/4A25BCJ3UPVQ5YSZAIUO5K6XKZ/graph.json","fetch_events":"https://pith.science/api/pith-number/4A25BCJ3UPVQ5YSZAIUO5K6XKZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4A25BCJ3UPVQ5YSZAIUO5K6XKZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4A25BCJ3UPVQ5YSZAIUO5K6XKZ/action/storage_attestation","attest_author":"https://pith.science/pith/4A25BCJ3UPVQ5YSZAIUO5K6XKZ/action/author_attestation","sign_citation":"https://pith.science/pith/4A25BCJ3UPVQ5YSZAIUO5K6XKZ/action/citation_signature","submit_replication":"https://pith.science/pith/4A25BCJ3UPVQ5YSZAIUO5K6XKZ/action/replication_record"}},"created_at":"2026-07-05T11:34:12.763567+00:00","updated_at":"2026-07-05T11:34:12.763567+00:00"}