{"data":{"id":"8e3901db-d118-4272-9bce-2dbbe99e9b54","title":"Your Robot's Safety Functions Already Work. What If the Input Lies?","summary":"VicOne LAB R7 shows that robots can act on manipulated inputs while following their safety rules, and that safety functions depend on sensor readings, estimates and stop signals that can be wrong or spoofed. The blog cites research on adversarial images against vision-language-action models and reports its own tests in which text on a poster changed a robot dog's movement and inaudible crafted audio changed a hospital robot's simulated behavior. It recommends testing adversarial scenarios before deployment and revisiting safety evidence as software, models, sensors and conditions change.","solution":"Teams can test adversarial scenarios before deployment and revisit the evidence as software, models, sensors, and operating conditions change.","labels":["security","safety"],"sourceUrl":"https://vicone.com/blog/your-robots-safety-functions-already-work-what-if-the-input-lies-/","publishedAt":"2026-11-11T10:29:00.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"low","attackType":["model_evasion","prompt_injection"],"issueType":"news","affectedPackages":null,"affectedPackageNames":null,"affectedPackageRefs":null,"affectedVendors":["NVIDIA"],"affectedVendorsRaw":["Gemma 4 E4B","Nemotron","NVIDIA Jetson AGX Orin"],"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":"2026-11-11T10:29:00.000Z","fixReleasedAt":null,"daysToFix":null,"fixCheckedAt":null,"capecIds":null,"crossRefCount":0,"attackSophistication":"moderate","impactType":["integrity","safety"],"aiComponentTargeted":"agent","llmSpecific":true,"classifierConfidence":0.8,"researchCategory":null,"atlasIds":["AML.T0051"]}}