The Shear project creates a secure environment for the least-authority execution of over-privileged applications that may be exploited by adversaries to launch privileged attacks.

The AI Vault project designs and develops new trusted execution environments tailored to run artificial intelligence and machine learning programs confidentially on modern AI platforms end-to-end, including cloud, edge, and embedded devices.

The RoboInsight (formerly AutoInsight) project leverages advanced techniques in program analysis, control-system modeling, and software hardening to develop a novel framework to enhance the safety and security of modern autonomous robotic systems, including robotic arms, mobile robots, and autonomous vehicles.