Game-Theoretic Goal Recognition Models with Applications to Security Domains.

Motivated by the goal recognition (GR) and goal recognition design (GRD) problems in the artificial intelligence (AI) planning domain, we introduce and study two natural variants of the GR and GRD problems with strategic agents, respectively. More specifically, we consider game-theoretic (GT) scenarios where a malicious adversary aims to damage some target in an (physical or virtual) environment monitored by a defender. The adversary must take a sequence of actions in order to attack the intended target. In the GTGR and GTGRD settings, the defender attempts to identify the adversary’s intended target while observing the adversary’s available actions so that he/she can strengthens the target’s defense against the attack. In addition, in the GTGRD setting, the defender can alter the environment (e.g., adding roadblocks) in order to better distinguish the goal/target of the adversary.