The last decade has shown that networked cyberphysical systems (NCPS) are the future of critical infrastructure such as transportation systems and energy production. However, they have introduced an uncharted territory of security vulnerabilities and a wider attack surface, mainly due to network openness and the deeply integrated physical and cyber spaces. On the other hand, relying on manual analysis of intrusion detection alarms might be effective in stopping run-of-the-mill automated probes but remain useless against the growing number of targeted, persistent, and often AI-enabled attacks on large-scale NCPS. Hence, there is a pressing need for new research directions to provide advanced protection. This paper introduces a novel security paradigm for emerging NCPS, namely Autonomous CyberPhysical Defense (ACPD). We lay out the theoretical foundations and describe the methods for building autonomous and stealthy cyber-physical defense agents that are able to dynamically hunt, detect, and respond to intelligent and sophisticated adversaries in real time without human intervention. By leveraging the power of game theory and multi-agent reinforcement learning, these selflearning agents will be able to deploy complex cyber-physical deception scenarios on the fly, generate optimal and adaptive security policies without prior knowledge of potential threats, and defend themselves against adversarial learning. Nonetheless, serious challenges including trustworthiness, scalability, and transfer learning are yet to be addressed for these autonomous agents to become the next-generation tools of cyber-physical defense.

The development of autonomous agents have gained renewed interest, largely due to the recent successes of machine learning. Social robots can be considered a special class of autonomous agents that are often intended to be integrated into sensitive environments. We present experiences from our work with two specific humanoid social service robots, and highlight how eschewing privacy and security by design principles leads to implementations with serious privacy and security flaws. The paper introduces the robots as platforms and their associated features, ecosystems and cloud platforms that are required for certain use cases or tasks. The paper encourages design aims for privacy and security, and then in this light studies the implementation from two different manufacturers. The results show a worrisome lack of design focus in handling privacy and security. The paper aims not to cover all the security flaws and possible mitigations, but does look closer into the use of the WebSocket protocol and it’s challenges when used for operational control. The conclusions of the paper provide insights on how manufacturers can rectify the discovered security flaws and presents key policies like accountability when it comes to implementing technical features of autonomous agents.