{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:WRM44VSDOP5UVKWOM22RCA6DLE","short_pith_number":"pith:WRM44VSD","schema_version":"1.0","canonical_sha256":"b459ce564373fb4aaace66b51103c3592487cd1e5ee054b72b22067a0c011b98","source":{"kind":"arxiv","id":"1906.09072","version":1},"attestation_state":"computed","paper":{"title":"Evolution Attack On Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"RuiJia Yang, Wei Sha, WeiYi Ding, YiGui Luo, YiSi Wang, YouTeng Sun","submitted_at":"2019-06-21T11:22:03Z","abstract_excerpt":"Many studies have been done to prove the vulnerability of neural networks to adversarial example. A trained and well-behaved model can be fooled by a visually imperceptible perturbation, i.e., an originally correctly classified image could be misclassified after a slight perturbation. In this paper, we propose a black-box strategy to attack such networks using an evolution algorithm. First, we formalize the generation of an adversarial example into the optimization problem of perturbations that represent the noise added to an original image at each pixel. To solve this optimization problem in "},"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":"1906.09072","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-06-21T11:22:03Z","cross_cats_sorted":[],"title_canon_sha256":"4bbbf0735159780030a15e8ea618225891d949e9aee72e763cf0322206ab0624","abstract_canon_sha256":"351ec8c8a07ca4ff60dacc43018aa3e51a2ae375fa7a5c48525e088c36b629f8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:42:44.669375Z","signature_b64":"TKtESjiUx+uiupRSrWG3TZqUVKGC3Dpbgl50non9DnCqMiD7Usi5FQuMJSGWbo9EerLs32mX7V/9HPBI5C1nDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b459ce564373fb4aaace66b51103c3592487cd1e5ee054b72b22067a0c011b98","last_reissued_at":"2026-05-17T23:42:44.668778Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:42:44.668778Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Evolution Attack On Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"RuiJia Yang, Wei Sha, WeiYi Ding, YiGui Luo, YiSi Wang, YouTeng Sun","submitted_at":"2019-06-21T11:22:03Z","abstract_excerpt":"Many studies have been done to prove the vulnerability of neural networks to adversarial example. A trained and well-behaved model can be fooled by a visually imperceptible perturbation, i.e., an originally correctly classified image could be misclassified after a slight perturbation. In this paper, we propose a black-box strategy to attack such networks using an evolution algorithm. First, we formalize the generation of an adversarial example into the optimization problem of perturbations that represent the noise added to an original image at each pixel. To solve this optimization problem in "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.09072","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":""},"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":"1906.09072","created_at":"2026-05-17T23:42:44.668873+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.09072v1","created_at":"2026-05-17T23:42:44.668873+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.09072","created_at":"2026-05-17T23:42:44.668873+00:00"},{"alias_kind":"pith_short_12","alias_value":"WRM44VSDOP5U","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_16","alias_value":"WRM44VSDOP5UVKWO","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_8","alias_value":"WRM44VSD","created_at":"2026-05-18T12:33:30.264802+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/WRM44VSDOP5UVKWOM22RCA6DLE","json":"https://pith.science/pith/WRM44VSDOP5UVKWOM22RCA6DLE.json","graph_json":"https://pith.science/api/pith-number/WRM44VSDOP5UVKWOM22RCA6DLE/graph.json","events_json":"https://pith.science/api/pith-number/WRM44VSDOP5UVKWOM22RCA6DLE/events.json","paper":"https://pith.science/paper/WRM44VSD"},"agent_actions":{"view_html":"https://pith.science/pith/WRM44VSDOP5UVKWOM22RCA6DLE","download_json":"https://pith.science/pith/WRM44VSDOP5UVKWOM22RCA6DLE.json","view_paper":"https://pith.science/paper/WRM44VSD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.09072&json=true","fetch_graph":"https://pith.science/api/pith-number/WRM44VSDOP5UVKWOM22RCA6DLE/graph.json","fetch_events":"https://pith.science/api/pith-number/WRM44VSDOP5UVKWOM22RCA6DLE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WRM44VSDOP5UVKWOM22RCA6DLE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WRM44VSDOP5UVKWOM22RCA6DLE/action/storage_attestation","attest_author":"https://pith.science/pith/WRM44VSDOP5UVKWOM22RCA6DLE/action/author_attestation","sign_citation":"https://pith.science/pith/WRM44VSDOP5UVKWOM22RCA6DLE/action/citation_signature","submit_replication":"https://pith.science/pith/WRM44VSDOP5UVKWOM22RCA6DLE/action/replication_record"}},"created_at":"2026-05-17T23:42:44.668873+00:00","updated_at":"2026-05-17T23:42:44.668873+00:00"}