{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:2IVXZLKSHD5O2UCRZLV2PWFE6B","short_pith_number":"pith:2IVXZLKS","schema_version":"1.0","canonical_sha256":"d22b7cad5238faed5051caeba7d8a4f06525868a94c1f228953a7591a1e19036","source":{"kind":"arxiv","id":"2506.24048","version":1},"attestation_state":"computed","paper":{"title":"Consensus-based optimization for closed-box adversarial attacks and a connection to evolution strategies","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"math.OC","authors_text":"Leon Bungert, Philipp Wacker, Tim Roith","submitted_at":"2025-06-30T16:54:44Z","abstract_excerpt":"Consensus-based optimization (CBO) has established itself as an efficient gradient-free optimization scheme, with attractive mathematical properties, such as mean-field convergence results for non-convex loss functions. In this work, we study CBO in the context of closed-box adversarial attacks, which are imperceptible input perturbations that aim to fool a classifier, without accessing its gradient. Our contribution is to establish a connection between the so-called consensus hopping as introduced by Riedl et al. and natural evolution strategies (NES) commonly applied in the context of advers"},"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":"2506.24048","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2025-06-30T16:54:44Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"0170dd70fa3f5a3ddf3a2b1eb3345340095f06d04e88f0589d03256a850d806e","abstract_canon_sha256":"f3e54818aefc29e7a871a9495e17b84e23225aabda269310faedf31df7a8eaba"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:29:32.329873Z","signature_b64":"lBDFXiiHWITPlF8oIw3Zakem+ZoyRQfWGqdHobjjCR8+Z+P32Z1yiQoIc8NAny68Yz0Pa4vqcnjPZV83Wgp4AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d22b7cad5238faed5051caeba7d8a4f06525868a94c1f228953a7591a1e19036","last_reissued_at":"2026-07-05T11:29:32.329324Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:29:32.329324Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Consensus-based optimization for closed-box adversarial attacks and a connection to evolution strategies","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"math.OC","authors_text":"Leon Bungert, Philipp Wacker, Tim Roith","submitted_at":"2025-06-30T16:54:44Z","abstract_excerpt":"Consensus-based optimization (CBO) has established itself as an efficient gradient-free optimization scheme, with attractive mathematical properties, such as mean-field convergence results for non-convex loss functions. In this work, we study CBO in the context of closed-box adversarial attacks, which are imperceptible input perturbations that aim to fool a classifier, without accessing its gradient. Our contribution is to establish a connection between the so-called consensus hopping as introduced by Riedl et al. and natural evolution strategies (NES) commonly applied in the context of advers"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.24048","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/2506.24048/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":"2506.24048","created_at":"2026-07-05T11:29:32.329388+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.24048v1","created_at":"2026-07-05T11:29:32.329388+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.24048","created_at":"2026-07-05T11:29:32.329388+00:00"},{"alias_kind":"pith_short_12","alias_value":"2IVXZLKSHD5O","created_at":"2026-07-05T11:29:32.329388+00:00"},{"alias_kind":"pith_short_16","alias_value":"2IVXZLKSHD5O2UCR","created_at":"2026-07-05T11:29:32.329388+00:00"},{"alias_kind":"pith_short_8","alias_value":"2IVXZLKS","created_at":"2026-07-05T11:29:32.329388+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.31565","citing_title":"A derivative-free particle method for optimization in Hilbert spaces","ref_index":62,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30371","citing_title":"From Mean-Field Limits to Semiclassical Concentration: Global Convergence of the Canonical Evolutionary Strategy","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19667","citing_title":"Convergence of Consensus-Based Particle Methods for Nonconvex Bi-Level Optimization","ref_index":177,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2IVXZLKSHD5O2UCRZLV2PWFE6B","json":"https://pith.science/pith/2IVXZLKSHD5O2UCRZLV2PWFE6B.json","graph_json":"https://pith.science/api/pith-number/2IVXZLKSHD5O2UCRZLV2PWFE6B/graph.json","events_json":"https://pith.science/api/pith-number/2IVXZLKSHD5O2UCRZLV2PWFE6B/events.json","paper":"https://pith.science/paper/2IVXZLKS"},"agent_actions":{"view_html":"https://pith.science/pith/2IVXZLKSHD5O2UCRZLV2PWFE6B","download_json":"https://pith.science/pith/2IVXZLKSHD5O2UCRZLV2PWFE6B.json","view_paper":"https://pith.science/paper/2IVXZLKS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.24048&json=true","fetch_graph":"https://pith.science/api/pith-number/2IVXZLKSHD5O2UCRZLV2PWFE6B/graph.json","fetch_events":"https://pith.science/api/pith-number/2IVXZLKSHD5O2UCRZLV2PWFE6B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2IVXZLKSHD5O2UCRZLV2PWFE6B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2IVXZLKSHD5O2UCRZLV2PWFE6B/action/storage_attestation","attest_author":"https://pith.science/pith/2IVXZLKSHD5O2UCRZLV2PWFE6B/action/author_attestation","sign_citation":"https://pith.science/pith/2IVXZLKSHD5O2UCRZLV2PWFE6B/action/citation_signature","submit_replication":"https://pith.science/pith/2IVXZLKSHD5O2UCRZLV2PWFE6B/action/replication_record"}},"created_at":"2026-07-05T11:29:32.329388+00:00","updated_at":"2026-07-05T11:29:32.329388+00:00"}