Foiling AI hackers with counterfactual reasoning
Despite ongoing advances in the technologies used in self-driving vehicles and similar autonomous systems, they continue to be vulnerable to those capable of hacking the artificial intelligence, or AI, systems that control many autonomous systems. Yezhou Yang (pictured), a Fulton Schools assistant professor of computer science and engineering, as well as director of the ASU Active Perception Group, is among researchers working on defenses against these hackers. Among potential solutions are development of systems to thwart the specific types of complex hacking attacks aimed at taking control of the AI systems in autonomous vehicles. Yang’s efforts recently earned him an Amazon Research Award to support his research.