{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:LQJYYVVT73LVI3NADB4XYYVAUW","short_pith_number":"pith:LQJYYVVT","schema_version":"1.0","canonical_sha256":"5c138c56b3fed7546da018797c62a0a5960d4b17a32da68b189f6d9df52b2f19","source":{"kind":"arxiv","id":"2502.00834","version":1},"attestation_state":"computed","paper":{"title":"Boosting Adversarial Robustness and Generalization with Structural Prior","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","cs.NE"],"primary_cat":"cs.LG","authors_text":"Hamid Krim, Weizhi Gao, Xiaorui Liu, Zhichao Hou","submitted_at":"2025-02-02T16:15:10Z","abstract_excerpt":"This work investigates a novel approach to boost adversarial robustness and generalization by incorporating structural prior into the design of deep learning models. Specifically, our study surprisingly reveals that existing dictionary learning-inspired convolutional neural networks (CNNs) provide a false sense of security against adversarial attacks. To address this, we propose Elastic Dictionary Learning Networks (EDLNets), a novel ResNet architecture that significantly enhances adversarial robustness and generalization. This novel and effective approach is supported by a theoretical robustn"},"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":"2502.00834","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-02T16:15:10Z","cross_cats_sorted":["cs.CR","cs.NE"],"title_canon_sha256":"24dcf5bce0533b238a53eda9a2aa226e8b7a53a17c6bffd7f1b7c737ad0f96ff","abstract_canon_sha256":"a730430bc5c25105b4e0682007ab748fea3803060f7b9e15c59509bc90cb93f9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:08:39.064244Z","signature_b64":"Q/PPL6jpW8ZFRw0ljEyCS4jmlXYGdjZczHTSxfYLoli6UTcgTlMJolntUYWSt0CsRJtrRAp+Nhq8l6rkhOnTBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5c138c56b3fed7546da018797c62a0a5960d4b17a32da68b189f6d9df52b2f19","last_reissued_at":"2026-07-05T10:08:39.063822Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:08:39.063822Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Boosting Adversarial Robustness and Generalization with Structural Prior","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","cs.NE"],"primary_cat":"cs.LG","authors_text":"Hamid Krim, Weizhi Gao, Xiaorui Liu, Zhichao Hou","submitted_at":"2025-02-02T16:15:10Z","abstract_excerpt":"This work investigates a novel approach to boost adversarial robustness and generalization by incorporating structural prior into the design of deep learning models. Specifically, our study surprisingly reveals that existing dictionary learning-inspired convolutional neural networks (CNNs) provide a false sense of security against adversarial attacks. To address this, we propose Elastic Dictionary Learning Networks (EDLNets), a novel ResNet architecture that significantly enhances adversarial robustness and generalization. This novel and effective approach is supported by a theoretical robustn"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.00834","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/2502.00834/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":"2502.00834","created_at":"2026-07-05T10:08:39.063875+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.00834v1","created_at":"2026-07-05T10:08:39.063875+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.00834","created_at":"2026-07-05T10:08:39.063875+00:00"},{"alias_kind":"pith_short_12","alias_value":"LQJYYVVT73LV","created_at":"2026-07-05T10:08:39.063875+00:00"},{"alias_kind":"pith_short_16","alias_value":"LQJYYVVT73LVI3NA","created_at":"2026-07-05T10:08:39.063875+00:00"},{"alias_kind":"pith_short_8","alias_value":"LQJYYVVT","created_at":"2026-07-05T10:08:39.063875+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LQJYYVVT73LVI3NADB4XYYVAUW","json":"https://pith.science/pith/LQJYYVVT73LVI3NADB4XYYVAUW.json","graph_json":"https://pith.science/api/pith-number/LQJYYVVT73LVI3NADB4XYYVAUW/graph.json","events_json":"https://pith.science/api/pith-number/LQJYYVVT73LVI3NADB4XYYVAUW/events.json","paper":"https://pith.science/paper/LQJYYVVT"},"agent_actions":{"view_html":"https://pith.science/pith/LQJYYVVT73LVI3NADB4XYYVAUW","download_json":"https://pith.science/pith/LQJYYVVT73LVI3NADB4XYYVAUW.json","view_paper":"https://pith.science/paper/LQJYYVVT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.00834&json=true","fetch_graph":"https://pith.science/api/pith-number/LQJYYVVT73LVI3NADB4XYYVAUW/graph.json","fetch_events":"https://pith.science/api/pith-number/LQJYYVVT73LVI3NADB4XYYVAUW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LQJYYVVT73LVI3NADB4XYYVAUW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LQJYYVVT73LVI3NADB4XYYVAUW/action/storage_attestation","attest_author":"https://pith.science/pith/LQJYYVVT73LVI3NADB4XYYVAUW/action/author_attestation","sign_citation":"https://pith.science/pith/LQJYYVVT73LVI3NADB4XYYVAUW/action/citation_signature","submit_replication":"https://pith.science/pith/LQJYYVVT73LVI3NADB4XYYVAUW/action/replication_record"}},"created_at":"2026-07-05T10:08:39.063875+00:00","updated_at":"2026-07-05T10:08:39.063875+00:00"}