{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:UYGSW2SRZUTT3BLMSRPPZZ253Q","short_pith_number":"pith:UYGSW2SR","schema_version":"1.0","canonical_sha256":"a60d2b6a51cd273d856c945efce75ddc14c0f8b159d7af70625c04a04ad8c3b3","source":{"kind":"arxiv","id":"2412.19947","version":1},"attestation_state":"computed","paper":{"title":"Standard-Deviation-Inspired Regularization for Improving Adversarial Robustness","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CR","cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Jin Tian, Modeste Atsague, Olukorede Fakorede","submitted_at":"2024-12-27T22:59:21Z","abstract_excerpt":"Adversarial Training (AT) has been demonstrated to improve the robustness of deep neural networks (DNNs) against adversarial attacks. AT is a min-max optimization procedure where in adversarial examples are generated to train a more robust DNN. The inner maximization step of AT increases the losses of inputs with respect to their actual classes. The outer minimization involves minimizing the losses on the adversarial examples obtained from the inner maximization. This work proposes a standard-deviation-inspired (SDI) regularization term to improve adversarial robustness and generalization. We "},"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":"2412.19947","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-27T22:59:21Z","cross_cats_sorted":["cs.AI","cs.CR","cs.CV","stat.ML"],"title_canon_sha256":"b3630b097ae6d754577105f29f1a7e515e78d9a2a1b76fd7eed6b47cf99d9cc4","abstract_canon_sha256":"017cd46024096297315676e649b0b471095f699ff2a901b1b7303b25b0159bb2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:54:52.163122Z","signature_b64":"WZHN+INMKyuF76yhALwJVD5o7TEfXy7JnhEYnvmHTlI1YdrFf5+zwSr9TcklwLEYrGfm9FTf8UZKJg+mpsTiBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a60d2b6a51cd273d856c945efce75ddc14c0f8b159d7af70625c04a04ad8c3b3","last_reissued_at":"2026-07-05T09:54:52.162727Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:54:52.162727Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Standard-Deviation-Inspired Regularization for Improving Adversarial Robustness","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CR","cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Jin Tian, Modeste Atsague, Olukorede Fakorede","submitted_at":"2024-12-27T22:59:21Z","abstract_excerpt":"Adversarial Training (AT) has been demonstrated to improve the robustness of deep neural networks (DNNs) against adversarial attacks. AT is a min-max optimization procedure where in adversarial examples are generated to train a more robust DNN. The inner maximization step of AT increases the losses of inputs with respect to their actual classes. The outer minimization involves minimizing the losses on the adversarial examples obtained from the inner maximization. This work proposes a standard-deviation-inspired (SDI) regularization term to improve adversarial robustness and generalization. We "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.19947","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/2412.19947/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":"2412.19947","created_at":"2026-07-05T09:54:52.162783+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.19947v1","created_at":"2026-07-05T09:54:52.162783+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.19947","created_at":"2026-07-05T09:54:52.162783+00:00"},{"alias_kind":"pith_short_12","alias_value":"UYGSW2SRZUTT","created_at":"2026-07-05T09:54:52.162783+00:00"},{"alias_kind":"pith_short_16","alias_value":"UYGSW2SRZUTT3BLM","created_at":"2026-07-05T09:54:52.162783+00:00"},{"alias_kind":"pith_short_8","alias_value":"UYGSW2SR","created_at":"2026-07-05T09:54:52.162783+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/UYGSW2SRZUTT3BLMSRPPZZ253Q","json":"https://pith.science/pith/UYGSW2SRZUTT3BLMSRPPZZ253Q.json","graph_json":"https://pith.science/api/pith-number/UYGSW2SRZUTT3BLMSRPPZZ253Q/graph.json","events_json":"https://pith.science/api/pith-number/UYGSW2SRZUTT3BLMSRPPZZ253Q/events.json","paper":"https://pith.science/paper/UYGSW2SR"},"agent_actions":{"view_html":"https://pith.science/pith/UYGSW2SRZUTT3BLMSRPPZZ253Q","download_json":"https://pith.science/pith/UYGSW2SRZUTT3BLMSRPPZZ253Q.json","view_paper":"https://pith.science/paper/UYGSW2SR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.19947&json=true","fetch_graph":"https://pith.science/api/pith-number/UYGSW2SRZUTT3BLMSRPPZZ253Q/graph.json","fetch_events":"https://pith.science/api/pith-number/UYGSW2SRZUTT3BLMSRPPZZ253Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UYGSW2SRZUTT3BLMSRPPZZ253Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UYGSW2SRZUTT3BLMSRPPZZ253Q/action/storage_attestation","attest_author":"https://pith.science/pith/UYGSW2SRZUTT3BLMSRPPZZ253Q/action/author_attestation","sign_citation":"https://pith.science/pith/UYGSW2SRZUTT3BLMSRPPZZ253Q/action/citation_signature","submit_replication":"https://pith.science/pith/UYGSW2SRZUTT3BLMSRPPZZ253Q/action/replication_record"}},"created_at":"2026-07-05T09:54:52.162783+00:00","updated_at":"2026-07-05T09:54:52.162783+00:00"}