{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3OHMIFU4MHZN4VXQFWHPU2NQKE","short_pith_number":"pith:3OHMIFU4","schema_version":"1.0","canonical_sha256":"db8ec4169c61f2de56f02d8efa69b0510a8f18e463815a39c3d45e976bb17b90","source":{"kind":"arxiv","id":"2404.16154","version":1},"attestation_state":"computed","paper":{"title":"A Comparative Analysis of Adversarial Robustness for Quantum and Classical Machine Learning Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR","quant-ph"],"primary_cat":"cs.LG","authors_text":"Kilian Tscharke, Maximilian Wendlinger, Pascal Debus","submitted_at":"2024-04-24T19:20:15Z","abstract_excerpt":"Quantum machine learning (QML) continues to be an area of tremendous interest from research and industry. While QML models have been shown to be vulnerable to adversarial attacks much in the same manner as classical machine learning models, it is still largely unknown how to compare adversarial attacks on quantum versus classical models. In this paper, we show how to systematically investigate the similarities and differences in adversarial robustness of classical and quantum models using transfer attacks, perturbation patterns and Lipschitz bounds. More specifically, we focus on classificatio"},"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":"2404.16154","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-04-24T19:20:15Z","cross_cats_sorted":["cs.CR","quant-ph"],"title_canon_sha256":"39a6ce23dada46c00190424ff91b8b5f2c010a968b51b0d28fe305f00994393c","abstract_canon_sha256":"5da6513cf4a3a4dfffb6b93bd04f69e35084ddae046fe7943ce4ed35c61caee1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:12:01.970995Z","signature_b64":"FalHlBH3AtZgh+M/gIUhP6JigKvoWPtP2nMhvUf+NPVmRimxatQRphnLGcuQCDOZQV43Ld8Wv4MecWghRx4hDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"db8ec4169c61f2de56f02d8efa69b0510a8f18e463815a39c3d45e976bb17b90","last_reissued_at":"2026-07-05T08:12:01.970565Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:12:01.970565Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Comparative Analysis of Adversarial Robustness for Quantum and Classical Machine Learning Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR","quant-ph"],"primary_cat":"cs.LG","authors_text":"Kilian Tscharke, Maximilian Wendlinger, Pascal Debus","submitted_at":"2024-04-24T19:20:15Z","abstract_excerpt":"Quantum machine learning (QML) continues to be an area of tremendous interest from research and industry. While QML models have been shown to be vulnerable to adversarial attacks much in the same manner as classical machine learning models, it is still largely unknown how to compare adversarial attacks on quantum versus classical models. In this paper, we show how to systematically investigate the similarities and differences in adversarial robustness of classical and quantum models using transfer attacks, perturbation patterns and Lipschitz bounds. More specifically, we focus on classificatio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.16154","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/2404.16154/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":"2404.16154","created_at":"2026-07-05T08:12:01.970622+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.16154v1","created_at":"2026-07-05T08:12:01.970622+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.16154","created_at":"2026-07-05T08:12:01.970622+00:00"},{"alias_kind":"pith_short_12","alias_value":"3OHMIFU4MHZN","created_at":"2026-07-05T08:12:01.970622+00:00"},{"alias_kind":"pith_short_16","alias_value":"3OHMIFU4MHZN4VXQ","created_at":"2026-07-05T08:12:01.970622+00:00"},{"alias_kind":"pith_short_8","alias_value":"3OHMIFU4","created_at":"2026-07-05T08:12:01.970622+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.06866","citing_title":"A hardware efficient quantum residual neural network without post-selection","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06866","citing_title":"A hardware efficient quantum residual neural network without post-selection","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3OHMIFU4MHZN4VXQFWHPU2NQKE","json":"https://pith.science/pith/3OHMIFU4MHZN4VXQFWHPU2NQKE.json","graph_json":"https://pith.science/api/pith-number/3OHMIFU4MHZN4VXQFWHPU2NQKE/graph.json","events_json":"https://pith.science/api/pith-number/3OHMIFU4MHZN4VXQFWHPU2NQKE/events.json","paper":"https://pith.science/paper/3OHMIFU4"},"agent_actions":{"view_html":"https://pith.science/pith/3OHMIFU4MHZN4VXQFWHPU2NQKE","download_json":"https://pith.science/pith/3OHMIFU4MHZN4VXQFWHPU2NQKE.json","view_paper":"https://pith.science/paper/3OHMIFU4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.16154&json=true","fetch_graph":"https://pith.science/api/pith-number/3OHMIFU4MHZN4VXQFWHPU2NQKE/graph.json","fetch_events":"https://pith.science/api/pith-number/3OHMIFU4MHZN4VXQFWHPU2NQKE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3OHMIFU4MHZN4VXQFWHPU2NQKE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3OHMIFU4MHZN4VXQFWHPU2NQKE/action/storage_attestation","attest_author":"https://pith.science/pith/3OHMIFU4MHZN4VXQFWHPU2NQKE/action/author_attestation","sign_citation":"https://pith.science/pith/3OHMIFU4MHZN4VXQFWHPU2NQKE/action/citation_signature","submit_replication":"https://pith.science/pith/3OHMIFU4MHZN4VXQFWHPU2NQKE/action/replication_record"}},"created_at":"2026-07-05T08:12:01.970622+00:00","updated_at":"2026-07-05T08:12:01.970622+00:00"}