{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:B67E3KNT6VCCJILE3TRB5AZ3FR","short_pith_number":"pith:B67E3KNT","schema_version":"1.0","canonical_sha256":"0fbe4da9b3f54424a164dce21e833b2c457af6dc4dfec74d9f42d963b5508236","source":{"kind":"arxiv","id":"1804.07062","version":1},"attestation_state":"computed","paper":{"title":"Attacking Convolutional Neural Network using Differential Evolution","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Danilo Vasconcellos Vargas, Jiawei Su, Kouichi Sakurai","submitted_at":"2018-04-19T10:05:52Z","abstract_excerpt":"The output of Convolutional Neural Networks (CNN) has been shown to be discontinuous which can make the CNN image classifier vulnerable to small well-tuned artificial perturbations. That is, images modified by adding such perturbations(i.e. adversarial perturbations) that make little difference to human eyes, can completely alter the CNN classification results. In this paper, we propose a practical attack using differential evolution(DE) for generating effective adversarial perturbations. We comprehensively evaluate the effectiveness of different types of DEs for conducting the attack on diffe"},"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":"1804.07062","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-04-19T10:05:52Z","cross_cats_sorted":[],"title_canon_sha256":"a7b6c18793db18ba90d100b5b5e0fbf97558443549786f4873206acb54dd04d7","abstract_canon_sha256":"2ab4592ba1391e0d441693842eec430af3a9c3234f32aecd4894ee720e66c2f5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:18:01.601253Z","signature_b64":"Vm+IvOoqsCmiUCr/vB7pZ/Xeh7qUuk2tJiU6YNYftVITBMbNfPqs6oc9Psj4CbCOx5xmxjLl2DKQOXOqgZY+Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0fbe4da9b3f54424a164dce21e833b2c457af6dc4dfec74d9f42d963b5508236","last_reissued_at":"2026-05-18T00:18:01.600609Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:18:01.600609Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Attacking Convolutional Neural Network using Differential Evolution","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Danilo Vasconcellos Vargas, Jiawei Su, Kouichi Sakurai","submitted_at":"2018-04-19T10:05:52Z","abstract_excerpt":"The output of Convolutional Neural Networks (CNN) has been shown to be discontinuous which can make the CNN image classifier vulnerable to small well-tuned artificial perturbations. That is, images modified by adding such perturbations(i.e. adversarial perturbations) that make little difference to human eyes, can completely alter the CNN classification results. In this paper, we propose a practical attack using differential evolution(DE) for generating effective adversarial perturbations. We comprehensively evaluate the effectiveness of different types of DEs for conducting the attack on diffe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.07062","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":"1804.07062","created_at":"2026-05-18T00:18:01.600708+00:00"},{"alias_kind":"arxiv_version","alias_value":"1804.07062v1","created_at":"2026-05-18T00:18:01.600708+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.07062","created_at":"2026-05-18T00:18:01.600708+00:00"},{"alias_kind":"pith_short_12","alias_value":"B67E3KNT6VCC","created_at":"2026-05-18T12:32:13.499390+00:00"},{"alias_kind":"pith_short_16","alias_value":"B67E3KNT6VCCJILE","created_at":"2026-05-18T12:32:13.499390+00:00"},{"alias_kind":"pith_short_8","alias_value":"B67E3KNT","created_at":"2026-05-18T12:32:13.499390+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/B67E3KNT6VCCJILE3TRB5AZ3FR","json":"https://pith.science/pith/B67E3KNT6VCCJILE3TRB5AZ3FR.json","graph_json":"https://pith.science/api/pith-number/B67E3KNT6VCCJILE3TRB5AZ3FR/graph.json","events_json":"https://pith.science/api/pith-number/B67E3KNT6VCCJILE3TRB5AZ3FR/events.json","paper":"https://pith.science/paper/B67E3KNT"},"agent_actions":{"view_html":"https://pith.science/pith/B67E3KNT6VCCJILE3TRB5AZ3FR","download_json":"https://pith.science/pith/B67E3KNT6VCCJILE3TRB5AZ3FR.json","view_paper":"https://pith.science/paper/B67E3KNT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1804.07062&json=true","fetch_graph":"https://pith.science/api/pith-number/B67E3KNT6VCCJILE3TRB5AZ3FR/graph.json","fetch_events":"https://pith.science/api/pith-number/B67E3KNT6VCCJILE3TRB5AZ3FR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B67E3KNT6VCCJILE3TRB5AZ3FR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B67E3KNT6VCCJILE3TRB5AZ3FR/action/storage_attestation","attest_author":"https://pith.science/pith/B67E3KNT6VCCJILE3TRB5AZ3FR/action/author_attestation","sign_citation":"https://pith.science/pith/B67E3KNT6VCCJILE3TRB5AZ3FR/action/citation_signature","submit_replication":"https://pith.science/pith/B67E3KNT6VCCJILE3TRB5AZ3FR/action/replication_record"}},"created_at":"2026-05-18T00:18:01.600708+00:00","updated_at":"2026-05-18T00:18:01.600708+00:00"}