My research focuses on the security, trustworthiness, and privacy-preserving aspect of AI, particularly in identifying vulnerabilities and designing robust, trustworthy systems.

I lead projects that explore AI robustness, neuromorphic computing, and energy-efficient AI. Our group combines theoretical and applied research, aiming to develop secure AI technologies that address complex, real-world threats.

PhD candidates will join a collaborative environment, working on cutting-edge challenges in AI security, privacy, and sustainable computing, with potential applications across critical industries.