During the past two years, we have been hacking (and securing) industrial robots. They are complex cyber-physical systems, they are used in critical installations, and they entail almost every possible risk, from safety to economic damage.
In this talk, we will review the main results from our research: a complete attacker and threat model for industrial robots; robot-specific cyberattacks that violate the fundamental “laws of robotics” (a la Asimov); an assessment of robot deployments and their protection.
We will also glimpse at our current research on the security of robot programming languages and at our future perspectives, including hardware and architectural ideas to improve robot resilience to penetration.
