{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:LH7PVHOFWEFCX4E2LFRA3Y3TMP","short_pith_number":"pith:LH7PVHOF","schema_version":"1.0","canonical_sha256":"59fefa9dc5b10a2bf09a59620de37363fc78423c5ddce853575377ff85113307","source":{"kind":"arxiv","id":"2007.15310","version":1},"attestation_state":"computed","paper":{"title":"Black-box Adversarial Sample Generation Based on Differential Evolution","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Junyu Lin, Lei Xu, Xiangyu Zhang, Yingqi Liu","submitted_at":"2020-07-30T08:43:45Z","abstract_excerpt":"Deep Neural Networks (DNNs) are being used in various daily tasks such as object detection, speech processing, and machine translation. However, it is known that DNNs suffer from robustness problems -- perturbed inputs called adversarial samples leading to misbehaviors of DNNs. In this paper, we propose a black-box technique called Black-box Momentum Iterative Fast Gradient Sign Method (BMI-FGSM) to test the robustness of DNN models. The technique does not require any knowledge of the structure or weights of the target DNN. Compared to existing white-box testing techniques that require accessi"},"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":"2007.15310","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-30T08:43:45Z","cross_cats_sorted":["cs.CR","cs.CV","stat.ML"],"title_canon_sha256":"23d35f7864676724f0a23fe2fabc179e941dddbaea54489fdc0a09c8ea066eb1","abstract_canon_sha256":"6499f37fdd7bf145245154102366ac77dbe11ecdfc3907c7758c6859b0890ad4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:23:29.524841Z","signature_b64":"33yua6uuIX0o7gLEyaefXQw9h6nywVg24j530p2LBa1NHOQR9c7SEAdBOrIOOCFh+Fq1RUEIMqLHwo8gADwTBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"59fefa9dc5b10a2bf09a59620de37363fc78423c5ddce853575377ff85113307","last_reissued_at":"2026-07-05T01:23:29.524409Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:23:29.524409Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Black-box Adversarial Sample Generation Based on Differential Evolution","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Junyu Lin, Lei Xu, Xiangyu Zhang, Yingqi Liu","submitted_at":"2020-07-30T08:43:45Z","abstract_excerpt":"Deep Neural Networks (DNNs) are being used in various daily tasks such as object detection, speech processing, and machine translation. However, it is known that DNNs suffer from robustness problems -- perturbed inputs called adversarial samples leading to misbehaviors of DNNs. In this paper, we propose a black-box technique called Black-box Momentum Iterative Fast Gradient Sign Method (BMI-FGSM) to test the robustness of DNN models. The technique does not require any knowledge of the structure or weights of the target DNN. Compared to existing white-box testing techniques that require accessi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.15310","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/2007.15310/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":"2007.15310","created_at":"2026-07-05T01:23:29.524464+00:00"},{"alias_kind":"arxiv_version","alias_value":"2007.15310v1","created_at":"2026-07-05T01:23:29.524464+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.15310","created_at":"2026-07-05T01:23:29.524464+00:00"},{"alias_kind":"pith_short_12","alias_value":"LH7PVHOFWEFC","created_at":"2026-07-05T01:23:29.524464+00:00"},{"alias_kind":"pith_short_16","alias_value":"LH7PVHOFWEFCX4E2","created_at":"2026-07-05T01:23:29.524464+00:00"},{"alias_kind":"pith_short_8","alias_value":"LH7PVHOF","created_at":"2026-07-05T01:23:29.524464+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.15042","citing_title":"DeRAG: Black-box Adversarial Attacks on Multiple Retrieval-Augmented Generation Applications via Prompt Injection","ref_index":28,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LH7PVHOFWEFCX4E2LFRA3Y3TMP","json":"https://pith.science/pith/LH7PVHOFWEFCX4E2LFRA3Y3TMP.json","graph_json":"https://pith.science/api/pith-number/LH7PVHOFWEFCX4E2LFRA3Y3TMP/graph.json","events_json":"https://pith.science/api/pith-number/LH7PVHOFWEFCX4E2LFRA3Y3TMP/events.json","paper":"https://pith.science/paper/LH7PVHOF"},"agent_actions":{"view_html":"https://pith.science/pith/LH7PVHOFWEFCX4E2LFRA3Y3TMP","download_json":"https://pith.science/pith/LH7PVHOFWEFCX4E2LFRA3Y3TMP.json","view_paper":"https://pith.science/paper/LH7PVHOF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2007.15310&json=true","fetch_graph":"https://pith.science/api/pith-number/LH7PVHOFWEFCX4E2LFRA3Y3TMP/graph.json","fetch_events":"https://pith.science/api/pith-number/LH7PVHOFWEFCX4E2LFRA3Y3TMP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LH7PVHOFWEFCX4E2LFRA3Y3TMP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LH7PVHOFWEFCX4E2LFRA3Y3TMP/action/storage_attestation","attest_author":"https://pith.science/pith/LH7PVHOFWEFCX4E2LFRA3Y3TMP/action/author_attestation","sign_citation":"https://pith.science/pith/LH7PVHOFWEFCX4E2LFRA3Y3TMP/action/citation_signature","submit_replication":"https://pith.science/pith/LH7PVHOFWEFCX4E2LFRA3Y3TMP/action/replication_record"}},"created_at":"2026-07-05T01:23:29.524464+00:00","updated_at":"2026-07-05T01:23:29.524464+00:00"}