{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:FJOSTJVZRW52MFC3DMVKFN66VI","short_pith_number":"pith:FJOSTJVZ","schema_version":"1.0","canonical_sha256":"2a5d29a6b98dbba6145b1b2aa2b7deaa0d6b9c8c2b33e8a9f85ea65804280732","source":{"kind":"arxiv","id":"2307.06608","version":3},"attestation_state":"computed","paper":{"title":"MF-CLIP: Leveraging CLIP as Surrogate Models for No-box Adversarial Attacks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CR"],"primary_cat":"cs.LG","authors_text":"Changsheng Xu, Dit-Yan Yeung, Jiaming Zhang, Jitao Sang, Lingyu Qiu, Qi Yi, Yige Li","submitted_at":"2023-07-13T08:10:48Z","abstract_excerpt":"The vulnerability of Deep Neural Networks (DNNs) to adversarial attacks poses a significant challenge to their deployment in safety-critical applications. While extensive research has addressed various attack scenarios, the no-box attack setting where adversaries have no prior knowledge, including access to training data of the target model, remains relatively underexplored despite its practical relevance. This work presents a systematic investigation into leveraging large-scale Vision-Language Models (VLMs), particularly CLIP, as surrogate models for executing no-box attacks. Our theoretical "},"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":"2307.06608","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-07-13T08:10:48Z","cross_cats_sorted":["cs.AI","cs.CR"],"title_canon_sha256":"dd228c87241487f1660195295ac89e5a1bffe9d66b71558cb5047862374382ee","abstract_canon_sha256":"3059dfa10973f8a4cc47334d9cb2f2d1228ed5849a6c9ca3ca65496f14c18636"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:38:19.477946Z","signature_b64":"bPkX/mSWo0baccacftgOT7LWP2WM10vUIoptu7e/54fZUIemerOhpRQ/27jhkRLHzEM6v78yo2X/mz3XD9ZmCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2a5d29a6b98dbba6145b1b2aa2b7deaa0d6b9c8c2b33e8a9f85ea65804280732","last_reissued_at":"2026-07-05T10:38:19.477420Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:38:19.477420Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MF-CLIP: Leveraging CLIP as Surrogate Models for No-box Adversarial Attacks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CR"],"primary_cat":"cs.LG","authors_text":"Changsheng Xu, Dit-Yan Yeung, Jiaming Zhang, Jitao Sang, Lingyu Qiu, Qi Yi, Yige Li","submitted_at":"2023-07-13T08:10:48Z","abstract_excerpt":"The vulnerability of Deep Neural Networks (DNNs) to adversarial attacks poses a significant challenge to their deployment in safety-critical applications. While extensive research has addressed various attack scenarios, the no-box attack setting where adversaries have no prior knowledge, including access to training data of the target model, remains relatively underexplored despite its practical relevance. This work presents a systematic investigation into leveraging large-scale Vision-Language Models (VLMs), particularly CLIP, as surrogate models for executing no-box attacks. Our theoretical "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.06608","kind":"arxiv","version":3},"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/2307.06608/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":"2307.06608","created_at":"2026-07-05T10:38:19.477496+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.06608v3","created_at":"2026-07-05T10:38:19.477496+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.06608","created_at":"2026-07-05T10:38:19.477496+00:00"},{"alias_kind":"pith_short_12","alias_value":"FJOSTJVZRW52","created_at":"2026-07-05T10:38:19.477496+00:00"},{"alias_kind":"pith_short_16","alias_value":"FJOSTJVZRW52MFC3","created_at":"2026-07-05T10:38:19.477496+00:00"},{"alias_kind":"pith_short_8","alias_value":"FJOSTJVZ","created_at":"2026-07-05T10:38:19.477496+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/FJOSTJVZRW52MFC3DMVKFN66VI","json":"https://pith.science/pith/FJOSTJVZRW52MFC3DMVKFN66VI.json","graph_json":"https://pith.science/api/pith-number/FJOSTJVZRW52MFC3DMVKFN66VI/graph.json","events_json":"https://pith.science/api/pith-number/FJOSTJVZRW52MFC3DMVKFN66VI/events.json","paper":"https://pith.science/paper/FJOSTJVZ"},"agent_actions":{"view_html":"https://pith.science/pith/FJOSTJVZRW52MFC3DMVKFN66VI","download_json":"https://pith.science/pith/FJOSTJVZRW52MFC3DMVKFN66VI.json","view_paper":"https://pith.science/paper/FJOSTJVZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.06608&json=true","fetch_graph":"https://pith.science/api/pith-number/FJOSTJVZRW52MFC3DMVKFN66VI/graph.json","fetch_events":"https://pith.science/api/pith-number/FJOSTJVZRW52MFC3DMVKFN66VI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FJOSTJVZRW52MFC3DMVKFN66VI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FJOSTJVZRW52MFC3DMVKFN66VI/action/storage_attestation","attest_author":"https://pith.science/pith/FJOSTJVZRW52MFC3DMVKFN66VI/action/author_attestation","sign_citation":"https://pith.science/pith/FJOSTJVZRW52MFC3DMVKFN66VI/action/citation_signature","submit_replication":"https://pith.science/pith/FJOSTJVZRW52MFC3DMVKFN66VI/action/replication_record"}},"created_at":"2026-07-05T10:38:19.477496+00:00","updated_at":"2026-07-05T10:38:19.477496+00:00"}