AI RESEARCH
If you're waiting for a sign... that might not be it! Mitigating Trust Boundary Confusion from Visual Injections on Vision-Language Agentic Systems
arXiv CS.CV
•
ArXi:2604.19844v1 Announce Type: new Recent advances in embodied Vision-Language Agentic Systems (VLAS), powered by large vision-language models (LVLMs), enable AI systems to perceive and reason over real-world scenes. Within this context, environmental signals such as traffic lights are essential in-band signals that can and should influence agent behavior. However, similar signals could also be crafted to operate as misleading visual injections, overriding user intent and posing security risks.