{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:3APCNZZCIGIWYITMR4IZVC3CLX","short_pith_number":"pith:3APCNZZC","schema_version":"1.0","canonical_sha256":"d81e26e72241916c226c8f119a8b625ddbce07ce872713873aaddc1d42715916","source":{"kind":"arxiv","id":"2606.30342","version":1},"attestation_state":"computed","paper":{"title":"A Classifier-Agnostic Zero-Shot Adversarial Attack Detection via CLIP","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Eyal Gofer, Guy Gilboa, Hodaya Krakover, Meir Yossef Levi","submitted_at":"2026-06-29T14:19:20Z","abstract_excerpt":"Adversarial attacks pose a challenge to the reliability of deep learning models, motivating effective detection methods. Existing techniques often rely on attack-specific assumptions, access to adversarial samples, or knowledge of the underlying classifier (white-box). We propose \\textit{$A^4D$ (\\textbf{A}ttack- and \\textbf{A}rchitecture-\\textbf{A}gnostic \\textbf{A}dversarial \\textbf{D}etector)}, a completely black-box, zero-shot adversarial attack detection framework that utilizes prompt-based similarity scores derived from CLIP. To the best of our knowledge this is the first attempt to utili"},"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":"2606.30342","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-29T14:19:20Z","cross_cats_sorted":[],"title_canon_sha256":"13b0bba7442c7bd1ea7714d9d8a969c0dee5d775f060d9bf6a82c01ed4b36a90","abstract_canon_sha256":"f8a645cc61313d8567d517878bcef082d8bd59f8ce2e99e1a6710111a488184c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T02:18:11.103388Z","signature_b64":"Dm8wb2v0VbOzxIg40uLVhRuiADz9zKEELXTjIutnYOnkOQaD6reB/a+T0hecAEeQTZuwIMjLVeJZsVcjAqQLDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d81e26e72241916c226c8f119a8b625ddbce07ce872713873aaddc1d42715916","last_reissued_at":"2026-06-30T02:18:11.102769Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T02:18:11.102769Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Classifier-Agnostic Zero-Shot Adversarial Attack Detection via CLIP","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Eyal Gofer, Guy Gilboa, Hodaya Krakover, Meir Yossef Levi","submitted_at":"2026-06-29T14:19:20Z","abstract_excerpt":"Adversarial attacks pose a challenge to the reliability of deep learning models, motivating effective detection methods. Existing techniques often rely on attack-specific assumptions, access to adversarial samples, or knowledge of the underlying classifier (white-box). We propose \\textit{$A^4D$ (\\textbf{A}ttack- and \\textbf{A}rchitecture-\\textbf{A}gnostic \\textbf{A}dversarial \\textbf{D}etector)}, a completely black-box, zero-shot adversarial attack detection framework that utilizes prompt-based similarity scores derived from CLIP. To the best of our knowledge this is the first attempt to utili"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.30342","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/2606.30342/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":"2606.30342","created_at":"2026-06-30T02:18:11.102853+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.30342v1","created_at":"2026-06-30T02:18:11.102853+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.30342","created_at":"2026-06-30T02:18:11.102853+00:00"},{"alias_kind":"pith_short_12","alias_value":"3APCNZZCIGIW","created_at":"2026-06-30T02:18:11.102853+00:00"},{"alias_kind":"pith_short_16","alias_value":"3APCNZZCIGIWYITM","created_at":"2026-06-30T02:18:11.102853+00:00"},{"alias_kind":"pith_short_8","alias_value":"3APCNZZC","created_at":"2026-06-30T02:18:11.102853+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/3APCNZZCIGIWYITMR4IZVC3CLX","json":"https://pith.science/pith/3APCNZZCIGIWYITMR4IZVC3CLX.json","graph_json":"https://pith.science/api/pith-number/3APCNZZCIGIWYITMR4IZVC3CLX/graph.json","events_json":"https://pith.science/api/pith-number/3APCNZZCIGIWYITMR4IZVC3CLX/events.json","paper":"https://pith.science/paper/3APCNZZC"},"agent_actions":{"view_html":"https://pith.science/pith/3APCNZZCIGIWYITMR4IZVC3CLX","download_json":"https://pith.science/pith/3APCNZZCIGIWYITMR4IZVC3CLX.json","view_paper":"https://pith.science/paper/3APCNZZC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.30342&json=true","fetch_graph":"https://pith.science/api/pith-number/3APCNZZCIGIWYITMR4IZVC3CLX/graph.json","fetch_events":"https://pith.science/api/pith-number/3APCNZZCIGIWYITMR4IZVC3CLX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3APCNZZCIGIWYITMR4IZVC3CLX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3APCNZZCIGIWYITMR4IZVC3CLX/action/storage_attestation","attest_author":"https://pith.science/pith/3APCNZZCIGIWYITMR4IZVC3CLX/action/author_attestation","sign_citation":"https://pith.science/pith/3APCNZZCIGIWYITMR4IZVC3CLX/action/citation_signature","submit_replication":"https://pith.science/pith/3APCNZZCIGIWYITMR4IZVC3CLX/action/replication_record"}},"created_at":"2026-06-30T02:18:11.102853+00:00","updated_at":"2026-06-30T02:18:11.102853+00:00"}