{"data":{"id":"72bde00b-9812-455f-ae13-c7a39dd621dc","title":"AI-Defined Vehicles: Securing the Decisions That Drive Vehicle Behavior","summary":"Researchers in the ReasonBreak study, published in May 2026, used corrupted textual inputs to manipulate trajectories generated by NVIDIA's Alpamayo driving models, increasing collision rates in closed-loop simulation. The source also describes a black-box adversarial patch study on vision-language driving models and a reflection-based backdoor study against DriveLM that increased inference latency. The authors frame these as research results rather than demonstrated exploits against production vehicles.","solution":"N/A -- no mitigation discussed in source.","labels":["security","research"],"sourceUrl":"https://vicone.com/blog/ai-defined-vehicles-securing-the-decisions-that-drive-vehicle-behavior/","publishedAt":"2026-11-19T10:14:00.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":["prompt_injection","model_poisoning"],"issueType":"news","affectedPackages":null,"affectedPackageNames":null,"affectedPackageRefs":null,"affectedVendors":[],"affectedVendorsRaw":["NVIDIA Alpamayo","Alpamayo 1","DriveLM","vision-language models"],"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":"2026-11-19T10:14:00.000Z","fixReleasedAt":null,"daysToFix":null,"fixCheckedAt":null,"capecIds":null,"crossRefCount":0,"attackSophistication":"advanced","impactType":["integrity","safety"],"aiComponentTargeted":"model","llmSpecific":true,"classifierConfidence":0.85,"researchCategory":null,"atlasIds":["AML.T0051"]}}