{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:LVUHUTYTEX6A72JIQRQAVKLDPC","short_pith_number":"pith:LVUHUTYT","schema_version":"1.0","canonical_sha256":"5d687a4f1325fc0fe92884600aa96378be4f8c2a89cb32e214d5d5f157e92b68","source":{"kind":"arxiv","id":"1910.02244","version":2},"attestation_state":"computed","paper":{"title":"Yet another but more efficient black-box adversarial attack: tiling and evolution strategies","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.NE"],"primary_cat":"cs.LG","authors_text":"Jamal Atif, Laurent Meunier, Olivier Teytaud","submitted_at":"2019-10-05T10:36:47Z","abstract_excerpt":"We introduce a new black-box attack achieving state of the art performances. Our approach is based on a new objective function, borrowing ideas from $\\ell_\\infty$-white box attacks, and particularly designed to fit derivative-free optimization requirements. It only requires to have access to the logits of the classifier without any other information which is a more realistic scenario. Not only we introduce a new objective function, we extend previous works on black box adversarial attacks to a larger spectrum of evolution strategies and other derivative-free optimization methods. We also highl"},"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":"1910.02244","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-05T10:36:47Z","cross_cats_sorted":["cs.AI","cs.CV","cs.NE"],"title_canon_sha256":"be8d440ca7d05d3a58801f3222c239a417efc9dad68d7c8a3d1f4626fbe59a1e","abstract_canon_sha256":"8e7ed109447369dd31f02c0f82e9de5642a14a5b99c5d6762c6c44acc2e448e1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:23:07.859939Z","signature_b64":"Dci2ykI3WAXsNBm+zFtupqe9d5rrlrC9DHAoVNJ2VUTv/7DyN3VmgZL8yEg3klnGm+F+6tH5OvOosCEj2AMGDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5d687a4f1325fc0fe92884600aa96378be4f8c2a89cb32e214d5d5f157e92b68","last_reissued_at":"2026-07-05T00:23:07.859585Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:23:07.859585Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Yet another but more efficient black-box adversarial attack: tiling and evolution strategies","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.NE"],"primary_cat":"cs.LG","authors_text":"Jamal Atif, Laurent Meunier, Olivier Teytaud","submitted_at":"2019-10-05T10:36:47Z","abstract_excerpt":"We introduce a new black-box attack achieving state of the art performances. Our approach is based on a new objective function, borrowing ideas from $\\ell_\\infty$-white box attacks, and particularly designed to fit derivative-free optimization requirements. It only requires to have access to the logits of the classifier without any other information which is a more realistic scenario. Not only we introduce a new objective function, we extend previous works on black box adversarial attacks to a larger spectrum of evolution strategies and other derivative-free optimization methods. We also highl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.02244","kind":"arxiv","version":2},"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/1910.02244/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":"1910.02244","created_at":"2026-07-05T00:23:07.859642+00:00"},{"alias_kind":"arxiv_version","alias_value":"1910.02244v2","created_at":"2026-07-05T00:23:07.859642+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.02244","created_at":"2026-07-05T00:23:07.859642+00:00"},{"alias_kind":"pith_short_12","alias_value":"LVUHUTYTEX6A","created_at":"2026-07-05T00:23:07.859642+00:00"},{"alias_kind":"pith_short_16","alias_value":"LVUHUTYTEX6A72JI","created_at":"2026-07-05T00:23:07.859642+00:00"},{"alias_kind":"pith_short_8","alias_value":"LVUHUTYT","created_at":"2026-07-05T00:23:07.859642+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.24048","citing_title":"Consensus-based optimization for closed-box adversarial attacks and a connection to evolution strategies","ref_index":68,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LVUHUTYTEX6A72JIQRQAVKLDPC","json":"https://pith.science/pith/LVUHUTYTEX6A72JIQRQAVKLDPC.json","graph_json":"https://pith.science/api/pith-number/LVUHUTYTEX6A72JIQRQAVKLDPC/graph.json","events_json":"https://pith.science/api/pith-number/LVUHUTYTEX6A72JIQRQAVKLDPC/events.json","paper":"https://pith.science/paper/LVUHUTYT"},"agent_actions":{"view_html":"https://pith.science/pith/LVUHUTYTEX6A72JIQRQAVKLDPC","download_json":"https://pith.science/pith/LVUHUTYTEX6A72JIQRQAVKLDPC.json","view_paper":"https://pith.science/paper/LVUHUTYT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1910.02244&json=true","fetch_graph":"https://pith.science/api/pith-number/LVUHUTYTEX6A72JIQRQAVKLDPC/graph.json","fetch_events":"https://pith.science/api/pith-number/LVUHUTYTEX6A72JIQRQAVKLDPC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LVUHUTYTEX6A72JIQRQAVKLDPC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LVUHUTYTEX6A72JIQRQAVKLDPC/action/storage_attestation","attest_author":"https://pith.science/pith/LVUHUTYTEX6A72JIQRQAVKLDPC/action/author_attestation","sign_citation":"https://pith.science/pith/LVUHUTYTEX6A72JIQRQAVKLDPC/action/citation_signature","submit_replication":"https://pith.science/pith/LVUHUTYTEX6A72JIQRQAVKLDPC/action/replication_record"}},"created_at":"2026-07-05T00:23:07.859642+00:00","updated_at":"2026-07-05T00:23:07.859642+00:00"}