{"data":{"id":"1b667c72-0572-407c-83a7-fb3e97a8a901","title":"Textual Response-Aware Guidance for Zero-Shot Adversarial Robustness of Vision-Language Models","summary":"Researchers study zero-shot adversarial robustness of vision-language models, which remain vulnerable to adversarial attacks despite strong generalization. They analyze visual representation drift in two existing forms of pre-trained model guidance, feature matching and prediction-distribution matching, and find complementary limitations. They propose Textual Response-Aware Guidance (TRAG), which constrains visual representation drift using the pre-trained text encoder's responses to local input variations, and report state-of-the-art clean and robust performance across architectures and tasks.","solution":"N/A -- no mitigation discussed in source.","labels":["security","research"],"sourceUrl":"https://arxiv.org/abs/2610.40309v2","publishedAt":"2026-10-29T15:48:43.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":["model_evasion"],"issueType":"research","affectedPackages":null,"affectedPackageNames":null,"affectedPackageRefs":null,"affectedVendors":[],"affectedVendorsRaw":["vision-language models (VLMs)"],"classifierModel":"claude-haiku-5-5","classifierPromptVersion":"v4","summaryPromptVersion":"v2","headline":null,"headlinePromptVersion":null,"cvssVector":null,"attackVector":null,"attackComplexity":null,"privilegesRequired":null,"userInteraction":null,"exploitMaturity":null,"epssScore":null,"epssCheckedAt":null,"kevDateAdded":null,"advisoryAliases":null,"affectedPackagesSource":null,"affectedPackagesCheckedAt":null,"patchAvailable":null,"disclosureDate":"2026-10-29T15:48:43.000Z","fixReleasedAt":null,"daysToFix":null,"fixCheckedAt":null,"capecIds":null,"crossRefCount":0,"attackSophistication":"advanced","impactType":["integrity"],"aiComponentTargeted":"model","llmSpecific":false,"classifierConfidence":0.9,"researchCategory":"preprint","atlasIds":null}}