
Dr Lichao Wu
BEng, MSc, PhD
Expertise
Current positions
Lecturer in Cyber Physical Systems Security
School of Computer Science
Contact
Press and media
Many of our academics speak to the media as experts in their field of research. If you are a journalist, please contact the University’s Media and PR Team:
Biography
Before joining UoB, I held postdoctoral positions in leading security groups in Europe. I was a postdoctoral researcher in the System Security Lab at TU Darmstadt, Germany, working with Prof. Dr.-Ing. Ahmad-Reza Sadeghi. Before that, I was a postdoctoral research fellow at Radboud University, led by Prof. Dr. Joan Daemen and Prof. Dr. Dr. Stjepan Picek. I obtained my Ph.D. from TU Delft, the Netherlands, in 2023, under the supervision of Prof. Dr. ir. Inald Lagendijk and Prof. Dr. Dr. Stjepan Picek.
Alongside my academic research, I worked as a Principal Security Evaluator at SGS Brightsight, the Netherlands (2017–2024). In this role, I led or was involved in several CC EAL5+ security evaluations from globally leading IC designers, focusing on their hardware and software implementation security. Additionally, I led R&D initiatives and collaborated with universities worldwide on research and innovation.
Research interests
My research spans two parts: hardware security and AI security.
In hardware security, I develop and analyse methods to uncover and mitigate vulnerabilities in pre-silicon and post-silicon haradware, including deep-learning enhanced side-channel analysis, hardware fuzzing, reinforcement-learning guided testing, and microcode-guided CPU evaluations.
In AI security, I investigate security and trustworthiness issues in modern artificial intelligence, including attacks and defenses on large language models and their deployment in safety-critical contexts, exploring both algorithmic and system-level threats.
Publications
Selected publications
12/08/2026GateBreaker
35th USENIX Security Symposium (USENIX Security 26)
GoldenFuzz
The Network and Distributed System Security (NDSS) Symposium 2026
NeuroStrike: Neuron-Level Attacks on Aligned LLMs
Fuzzilicon
GenHuzz
34th USENIX Security Symposium (USENIX Security 25)
Recent publications
23/02/2026GoldenFuzz
The Network and Distributed System Security (NDSS) Symposium 2026
I Know What Your Layers Did
IACR Communications in Cryptology
GateBreaker
35th USENIX Security Symposium (USENIX Security 26)
GenHuzz
34th USENIX Security Symposium (USENIX Security 25)
HFL
2025 Design, Automation Test in Europe Conference (DATE)