{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:AKGXVIW4LHULPIBU6Y7J3O7Z7K","short_pith_number":"pith:AKGXVIW4","schema_version":"1.0","canonical_sha256":"028d7aa2dc59e8b7a034f63e9dbbf9faba0bf7a92126f7e9c1150b11e095b866","source":{"kind":"arxiv","id":"2504.17690","version":1},"attestation_state":"computed","paper":{"title":"On the Generalization of Adversarially Trained Quantum Classifiers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"quant-ph","authors_text":"Aaron Mark Thomas, Osvaldo Simeone, Petros Georgiou, Sharu Theresa Jose","submitted_at":"2025-04-24T15:59:55Z","abstract_excerpt":"Quantum classifiers are vulnerable to adversarial attacks that manipulate their input classical or quantum data. A promising countermeasure is adversarial training, where quantum classifiers are trained by using an attack-aware, adversarial loss function. This work establishes novel bounds on the generalization error of adversarially trained quantum classifiers when tested in the presence of perturbation-constrained adversaries. The bounds quantify the excess generalization error incurred to ensure robustness to adversarial attacks as scaling with the training sample size $m$ as $1/\\sqrt{m}$, "},"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":"2504.17690","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"quant-ph","submitted_at":"2025-04-24T15:59:55Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"032173c7a6f77b3494e4b32353df75431046ba9ea00bc2c7431191feffec91f7","abstract_canon_sha256":"52da07edc25e1d5b49a1158ab7b06e0b45d0d26f7de28035d71e7d6b716442f8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:53:34.132064Z","signature_b64":"JHw5+dka8H5ZusAF0nnde7TwZP/1V2vUWP258nD9F+x/k4BAV7mENUX8f2PuvUqUqdAnDdUMqaXT2+MrIGivCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"028d7aa2dc59e8b7a034f63e9dbbf9faba0bf7a92126f7e9c1150b11e095b866","last_reissued_at":"2026-07-05T10:53:34.131526Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:53:34.131526Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the Generalization of Adversarially Trained Quantum Classifiers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"quant-ph","authors_text":"Aaron Mark Thomas, Osvaldo Simeone, Petros Georgiou, Sharu Theresa Jose","submitted_at":"2025-04-24T15:59:55Z","abstract_excerpt":"Quantum classifiers are vulnerable to adversarial attacks that manipulate their input classical or quantum data. A promising countermeasure is adversarial training, where quantum classifiers are trained by using an attack-aware, adversarial loss function. This work establishes novel bounds on the generalization error of adversarially trained quantum classifiers when tested in the presence of perturbation-constrained adversaries. The bounds quantify the excess generalization error incurred to ensure robustness to adversarial attacks as scaling with the training sample size $m$ as $1/\\sqrt{m}$, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.17690","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/2504.17690/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":"2504.17690","created_at":"2026-07-05T10:53:34.131594+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.17690v1","created_at":"2026-07-05T10:53:34.131594+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.17690","created_at":"2026-07-05T10:53:34.131594+00:00"},{"alias_kind":"pith_short_12","alias_value":"AKGXVIW4LHUL","created_at":"2026-07-05T10:53:34.131594+00:00"},{"alias_kind":"pith_short_16","alias_value":"AKGXVIW4LHULPIBU","created_at":"2026-07-05T10:53:34.131594+00:00"},{"alias_kind":"pith_short_8","alias_value":"AKGXVIW4","created_at":"2026-07-05T10:53:34.131594+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.08455","citing_title":"The interplay of robustness and generalization in quantum machine learning","ref_index":58,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AKGXVIW4LHULPIBU6Y7J3O7Z7K","json":"https://pith.science/pith/AKGXVIW4LHULPIBU6Y7J3O7Z7K.json","graph_json":"https://pith.science/api/pith-number/AKGXVIW4LHULPIBU6Y7J3O7Z7K/graph.json","events_json":"https://pith.science/api/pith-number/AKGXVIW4LHULPIBU6Y7J3O7Z7K/events.json","paper":"https://pith.science/paper/AKGXVIW4"},"agent_actions":{"view_html":"https://pith.science/pith/AKGXVIW4LHULPIBU6Y7J3O7Z7K","download_json":"https://pith.science/pith/AKGXVIW4LHULPIBU6Y7J3O7Z7K.json","view_paper":"https://pith.science/paper/AKGXVIW4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.17690&json=true","fetch_graph":"https://pith.science/api/pith-number/AKGXVIW4LHULPIBU6Y7J3O7Z7K/graph.json","fetch_events":"https://pith.science/api/pith-number/AKGXVIW4LHULPIBU6Y7J3O7Z7K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AKGXVIW4LHULPIBU6Y7J3O7Z7K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AKGXVIW4LHULPIBU6Y7J3O7Z7K/action/storage_attestation","attest_author":"https://pith.science/pith/AKGXVIW4LHULPIBU6Y7J3O7Z7K/action/author_attestation","sign_citation":"https://pith.science/pith/AKGXVIW4LHULPIBU6Y7J3O7Z7K/action/citation_signature","submit_replication":"https://pith.science/pith/AKGXVIW4LHULPIBU6Y7J3O7Z7K/action/replication_record"}},"created_at":"2026-07-05T10:53:34.131594+00:00","updated_at":"2026-07-05T10:53:34.131594+00:00"}