{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:EKTWWPGWEC6KCZYVU2G3YIRBSI","short_pith_number":"pith:EKTWWPGW","schema_version":"1.0","canonical_sha256":"22a76b3cd620bca16715a68dbc22219224e44d7692bab81a101e7d612524a661","source":{"kind":"arxiv","id":"2410.09402","version":2},"attestation_state":"computed","paper":{"title":"Minimax rates of convergence for nonparametric regression under adversarial attacks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML","stat.TH"],"primary_cat":"math.ST","authors_text":"Jingfu Peng, Yuhong Yang","submitted_at":"2024-10-12T07:11:38Z","abstract_excerpt":"Recent research shows the susceptibility of machine learning models to adversarial attacks, wherein minor but maliciously chosen perturbations of the input can significantly degrade model performance. In this paper, we theoretically analyse the limits of robustness against such adversarial attacks in a nonparametric regression setting, by examining the minimax rates of convergence in an adversarial sup-norm. Our work reveals that the minimax rate under adversarial attacks in the input is the same as sum of two terms: one represents the minimax rate in the standard setting without adversarial a"},"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":"2410.09402","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2024-10-12T07:11:38Z","cross_cats_sorted":["stat.ML","stat.TH"],"title_canon_sha256":"25f0fb6fb71d1a3d0583118ddadca92d5c8649b9c222b3622b6829417e263ed9","abstract_canon_sha256":"a64be22f38875f8ac17624ed077a9b5407a7e437724b52c5320ce997e941634f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:02:13.491625Z","signature_b64":"+vehZB3hFs58a+tWmP1DNykKKtdKbsQmboz5Q5KXwEWqG+eOQnsyt5g62lZ72x0Lm7QBIfVR8DzS3WSRvyHeBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"22a76b3cd620bca16715a68dbc22219224e44d7692bab81a101e7d612524a661","last_reissued_at":"2026-07-05T11:02:13.491110Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:02:13.491110Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Minimax rates of convergence for nonparametric regression under adversarial attacks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML","stat.TH"],"primary_cat":"math.ST","authors_text":"Jingfu Peng, Yuhong Yang","submitted_at":"2024-10-12T07:11:38Z","abstract_excerpt":"Recent research shows the susceptibility of machine learning models to adversarial attacks, wherein minor but maliciously chosen perturbations of the input can significantly degrade model performance. In this paper, we theoretically analyse the limits of robustness against such adversarial attacks in a nonparametric regression setting, by examining the minimax rates of convergence in an adversarial sup-norm. Our work reveals that the minimax rate under adversarial attacks in the input is the same as sum of two terms: one represents the minimax rate in the standard setting without adversarial a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.09402","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/2410.09402/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":"2410.09402","created_at":"2026-07-05T11:02:13.491171+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.09402v2","created_at":"2026-07-05T11:02:13.491171+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.09402","created_at":"2026-07-05T11:02:13.491171+00:00"},{"alias_kind":"pith_short_12","alias_value":"EKTWWPGWEC6K","created_at":"2026-07-05T11:02:13.491171+00:00"},{"alias_kind":"pith_short_16","alias_value":"EKTWWPGWEC6KCZYV","created_at":"2026-07-05T11:02:13.491171+00:00"},{"alias_kind":"pith_short_8","alias_value":"EKTWWPGW","created_at":"2026-07-05T11:02:13.491171+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.25965","citing_title":"Adversarial Robustness of NTK Neural Networks","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2604.25965","citing_title":"Adversarial Robustness of NTK Neural Networks","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EKTWWPGWEC6KCZYVU2G3YIRBSI","json":"https://pith.science/pith/EKTWWPGWEC6KCZYVU2G3YIRBSI.json","graph_json":"https://pith.science/api/pith-number/EKTWWPGWEC6KCZYVU2G3YIRBSI/graph.json","events_json":"https://pith.science/api/pith-number/EKTWWPGWEC6KCZYVU2G3YIRBSI/events.json","paper":"https://pith.science/paper/EKTWWPGW"},"agent_actions":{"view_html":"https://pith.science/pith/EKTWWPGWEC6KCZYVU2G3YIRBSI","download_json":"https://pith.science/pith/EKTWWPGWEC6KCZYVU2G3YIRBSI.json","view_paper":"https://pith.science/paper/EKTWWPGW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.09402&json=true","fetch_graph":"https://pith.science/api/pith-number/EKTWWPGWEC6KCZYVU2G3YIRBSI/graph.json","fetch_events":"https://pith.science/api/pith-number/EKTWWPGWEC6KCZYVU2G3YIRBSI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EKTWWPGWEC6KCZYVU2G3YIRBSI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EKTWWPGWEC6KCZYVU2G3YIRBSI/action/storage_attestation","attest_author":"https://pith.science/pith/EKTWWPGWEC6KCZYVU2G3YIRBSI/action/author_attestation","sign_citation":"https://pith.science/pith/EKTWWPGWEC6KCZYVU2G3YIRBSI/action/citation_signature","submit_replication":"https://pith.science/pith/EKTWWPGWEC6KCZYVU2G3YIRBSI/action/replication_record"}},"created_at":"2026-07-05T11:02:13.491171+00:00","updated_at":"2026-07-05T11:02:13.491171+00:00"}