{"data":{"id":"d06af2f1-2e47-493c-9738-0f3ff7ceabfc","title":"DecisionRobust: Benchmarking Robustness for JEV Style Decision Models Across Text and Vision","summary":"DecisionRobust is a benchmark that evaluates the robustness of JEV-style decision models on text and vision tasks, using semantics-preserving text perturbations, image perturbations, and prompt injection in both modalities. The authors test 30 text and 17 vision model configurations, including held-out models excluded from candidate selection. They find that attacks expose vulnerabilities beyond the construction models, that resistance to input perturbation does not imply resistance to prompt injection, and that label-consistency checks substantially reduce measured attack success.","solution":"N/A -- no mitigation discussed in source.","labels":["security","research"],"sourceUrl":"https://arxiv.org/abs/2610.19118v1","publishedAt":"2026-10-13T19:52:14.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":["prompt_injection","model_evasion"],"issueType":"research","affectedPackages":null,"affectedPackageNames":null,"affectedPackageRefs":null,"affectedVendors":[],"affectedVendorsRaw":[],"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":"2026-10-13T19:52:14.000Z","capecIds":null,"crossRefCount":0,"attackSophistication":"moderate","impactType":["integrity","safety"],"aiComponentTargeted":"model","llmSpecific":false,"classifierConfidence":0.9,"researchCategory":"preprint","atlasIds":["AML.T0051"]}}