{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:MHVTVNT3WP3RRWWTYVXZBXYUCI","short_pith_number":"pith:MHVTVNT3","schema_version":"1.0","canonical_sha256":"61eb3ab67bb3f718dad3c56f90df141204cec0680c27b89efcea6a5a3e00944d","source":{"kind":"arxiv","id":"2607.14974","version":1},"attestation_state":"computed","paper":{"title":"On Success and Simplicity: A Second Look at Transferable Vision-Language Attack Pipeline","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.CV","authors_text":"Bo Yang, Chao Shen, Chenhao Lin, Yuchen Ren, Zhengyu Zhao","submitted_at":"2026-07-16T13:28:59Z","abstract_excerpt":"Vision-Language Pre-training Models (VLPMs) are known to be vulnerable to adversarial attacks. Recent transferable attacks on VLPMs have followed a common pipeline with complicated loss functions or multi-stage text/image attacks. However, in this paper, we demonstrate that such a sophisticated attack pipeline can be simpler yet more successful. Specifically, we identify three previously overlooked issues caused by inappropriate cross-modal interactions and excessive operations. To address them, we propose the Simple Vision-Language Attack (SimVLA) pipeline, which observably improves transfera"},"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":"2607.14974","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-16T13:28:59Z","cross_cats_sorted":["cs.CR"],"title_canon_sha256":"4b39f522a49ab65377924f204fd57970052d025f6eec707027167f7ff8d27334","abstract_canon_sha256":"992b55bcb96178f9c2dea557038b6abefd42756c0d12d7de82236fbb53346eff"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-17T01:22:01.825143Z","signature_b64":"d3AduTiUaOB0lqIyJfhk9HUSmox2GsV4520khxDILOP6gnP1C06aKa1dfTHqqwizX1B02u8V/5bkOPcUwCm8AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"61eb3ab67bb3f718dad3c56f90df141204cec0680c27b89efcea6a5a3e00944d","last_reissued_at":"2026-07-17T01:22:01.824296Z","signature_status":"signed_v1","first_computed_at":"2026-07-17T01:22:01.824296Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On Success and Simplicity: A Second Look at Transferable Vision-Language Attack Pipeline","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.CV","authors_text":"Bo Yang, Chao Shen, Chenhao Lin, Yuchen Ren, Zhengyu Zhao","submitted_at":"2026-07-16T13:28:59Z","abstract_excerpt":"Vision-Language Pre-training Models (VLPMs) are known to be vulnerable to adversarial attacks. Recent transferable attacks on VLPMs have followed a common pipeline with complicated loss functions or multi-stage text/image attacks. However, in this paper, we demonstrate that such a sophisticated attack pipeline can be simpler yet more successful. Specifically, we identify three previously overlooked issues caused by inappropriate cross-modal interactions and excessive operations. To address them, we propose the Simple Vision-Language Attack (SimVLA) pipeline, which observably improves transfera"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.14974","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/2607.14974/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":"2607.14974","created_at":"2026-07-17T01:22:01.824742+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.14974v1","created_at":"2026-07-17T01:22:01.824742+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.14974","created_at":"2026-07-17T01:22:01.824742+00:00"},{"alias_kind":"pith_short_12","alias_value":"MHVTVNT3WP3R","created_at":"2026-07-17T01:22:01.824742+00:00"},{"alias_kind":"pith_short_16","alias_value":"MHVTVNT3WP3RRWWT","created_at":"2026-07-17T01:22:01.824742+00:00"},{"alias_kind":"pith_short_8","alias_value":"MHVTVNT3","created_at":"2026-07-17T01:22:01.824742+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/MHVTVNT3WP3RRWWTYVXZBXYUCI","json":"https://pith.science/pith/MHVTVNT3WP3RRWWTYVXZBXYUCI.json","graph_json":"https://pith.science/api/pith-number/MHVTVNT3WP3RRWWTYVXZBXYUCI/graph.json","events_json":"https://pith.science/api/pith-number/MHVTVNT3WP3RRWWTYVXZBXYUCI/events.json","paper":"https://pith.science/paper/MHVTVNT3"},"agent_actions":{"view_html":"https://pith.science/pith/MHVTVNT3WP3RRWWTYVXZBXYUCI","download_json":"https://pith.science/pith/MHVTVNT3WP3RRWWTYVXZBXYUCI.json","view_paper":"https://pith.science/paper/MHVTVNT3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.14974&json=true","fetch_graph":"https://pith.science/api/pith-number/MHVTVNT3WP3RRWWTYVXZBXYUCI/graph.json","fetch_events":"https://pith.science/api/pith-number/MHVTVNT3WP3RRWWTYVXZBXYUCI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MHVTVNT3WP3RRWWTYVXZBXYUCI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MHVTVNT3WP3RRWWTYVXZBXYUCI/action/storage_attestation","attest_author":"https://pith.science/pith/MHVTVNT3WP3RRWWTYVXZBXYUCI/action/author_attestation","sign_citation":"https://pith.science/pith/MHVTVNT3WP3RRWWTYVXZBXYUCI/action/citation_signature","submit_replication":"https://pith.science/pith/MHVTVNT3WP3RRWWTYVXZBXYUCI/action/replication_record"}},"created_at":"2026-07-17T01:22:01.824742+00:00","updated_at":"2026-07-17T01:22:01.824742+00:00"}