-
, designing protocols that detect and mitigate adversarial attempts to reconstruct model functionality or steal sequential reasoning paths during multi-agent interactions. Secure agentic AI, investigating how
-
exploited by intelligent physical systems, such as robots, vehicles, and distributed autonomous agents, to perceive and interpret their environment and support timely physical action. A central objective will
-
robots, autonomous vehicles, and drones, develop rich frameworks to interact with the world in real time? This is the main underlying theme to be explored within this postdoctoral position. The appointed
-
of autonomous mobile robots in dynamic human environments. The central objective is to enable robots to anticipate, interpret, and respond to human movement and interactions, thereby improving both safety and