{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:HS4P4SGCA2LSE2XDQJAGDARACK","short_pith_number":"pith:HS4P4SGC","schema_version":"1.0","canonical_sha256":"3cb8fe48c20697226ae3824061822012937bc9b86a8bc5b7613f31ee46095a2c","source":{"kind":"arxiv","id":"2407.13646","version":1},"attestation_state":"computed","paper":{"title":"Beyond Dropout: Robust Convolutional Neural Networks Based on Local Feature Masking","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chuangliang Zhang, Lifei Chen, Min Jiang, Yongjie Hou, Yunpeng Gong","submitted_at":"2024-07-18T16:25:16Z","abstract_excerpt":"In the contemporary of deep learning, where models often grapple with the challenge of simultaneously achieving robustness against adversarial attacks and strong generalization capabilities, this study introduces an innovative Local Feature Masking (LFM) strategy aimed at fortifying the performance of Convolutional Neural Networks (CNNs) on both fronts. During the training phase, we strategically incorporate random feature masking in the shallow layers of CNNs, effectively alleviating overfitting issues, thereby enhancing the model's generalization ability and bolstering its resilience to adve"},"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":"2407.13646","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-18T16:25:16Z","cross_cats_sorted":[],"title_canon_sha256":"01fd72af2818b68c81d8c92f1b2bd75b39e1c0d35ad872116f9c179b0dcc1909","abstract_canon_sha256":"6458707249d48fa5c0b65bfbf338d79578383d9fc07ab40b8235ad7ea4f845ab"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:45:41.892983Z","signature_b64":"EATIhtJTexwbIirJnrZA/hA+/VsNgL3HfGlqbz0BFFHMZaso5d4R116Gxroz7SqRUfjQahna+1bI+xLP4+IGDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3cb8fe48c20697226ae3824061822012937bc9b86a8bc5b7613f31ee46095a2c","last_reissued_at":"2026-07-05T08:45:41.892520Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:45:41.892520Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Beyond Dropout: Robust Convolutional Neural Networks Based on Local Feature Masking","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chuangliang Zhang, Lifei Chen, Min Jiang, Yongjie Hou, Yunpeng Gong","submitted_at":"2024-07-18T16:25:16Z","abstract_excerpt":"In the contemporary of deep learning, where models often grapple with the challenge of simultaneously achieving robustness against adversarial attacks and strong generalization capabilities, this study introduces an innovative Local Feature Masking (LFM) strategy aimed at fortifying the performance of Convolutional Neural Networks (CNNs) on both fronts. During the training phase, we strategically incorporate random feature masking in the shallow layers of CNNs, effectively alleviating overfitting issues, thereby enhancing the model's generalization ability and bolstering its resilience to adve"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.13646","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/2407.13646/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":"2407.13646","created_at":"2026-07-05T08:45:41.892575+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.13646v1","created_at":"2026-07-05T08:45:41.892575+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.13646","created_at":"2026-07-05T08:45:41.892575+00:00"},{"alias_kind":"pith_short_12","alias_value":"HS4P4SGCA2LS","created_at":"2026-07-05T08:45:41.892575+00:00"},{"alias_kind":"pith_short_16","alias_value":"HS4P4SGCA2LSE2XD","created_at":"2026-07-05T08:45:41.892575+00:00"},{"alias_kind":"pith_short_8","alias_value":"HS4P4SGC","created_at":"2026-07-05T08:45:41.892575+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.00341","citing_title":"Fusing Physics-Driven Strategies and Cross-Modal Adversarial Learning: Toward Multi-Domain Applications","ref_index":12,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HS4P4SGCA2LSE2XDQJAGDARACK","json":"https://pith.science/pith/HS4P4SGCA2LSE2XDQJAGDARACK.json","graph_json":"https://pith.science/api/pith-number/HS4P4SGCA2LSE2XDQJAGDARACK/graph.json","events_json":"https://pith.science/api/pith-number/HS4P4SGCA2LSE2XDQJAGDARACK/events.json","paper":"https://pith.science/paper/HS4P4SGC"},"agent_actions":{"view_html":"https://pith.science/pith/HS4P4SGCA2LSE2XDQJAGDARACK","download_json":"https://pith.science/pith/HS4P4SGCA2LSE2XDQJAGDARACK.json","view_paper":"https://pith.science/paper/HS4P4SGC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.13646&json=true","fetch_graph":"https://pith.science/api/pith-number/HS4P4SGCA2LSE2XDQJAGDARACK/graph.json","fetch_events":"https://pith.science/api/pith-number/HS4P4SGCA2LSE2XDQJAGDARACK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HS4P4SGCA2LSE2XDQJAGDARACK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HS4P4SGCA2LSE2XDQJAGDARACK/action/storage_attestation","attest_author":"https://pith.science/pith/HS4P4SGCA2LSE2XDQJAGDARACK/action/author_attestation","sign_citation":"https://pith.science/pith/HS4P4SGCA2LSE2XDQJAGDARACK/action/citation_signature","submit_replication":"https://pith.science/pith/HS4P4SGCA2LSE2XDQJAGDARACK/action/replication_record"}},"created_at":"2026-07-05T08:45:41.892575+00:00","updated_at":"2026-07-05T08:45:41.892575+00:00"}