Using game theory with intrinsic motivation to examine anti-hacking policies for autonomous systems

With the increasing excitement about the emergence of autonomous systems, there is also a level of caution associated with the possible vulnerabilities of such systems. As systems become more independent, it may become more difficult for humans to trust them, particularly in settings where they may be vulnerable to malicious behavior by others. This paper presents a game theoretic model for autonomous systems subject to hacking. We propose a hacking game that models the interaction between an autonomous system and a hacker. Simulations were conducted to examine the outcomes for the victims (rational autonomous agents) when attacked by humans with different motives. The implications of the results for the decision-making process of the players are discussed. This paper also explores how game theory can be used by policy makers to choose a policy when autonomous systems have been attacked.