Qiushi Wu

Qiushi Wu is a Research Scientist at IBM Research, working on AI security and autonomous systems safety. His research interests include autonomous vulnerability detection, AI red-teaming, and building secure infrastructure for multi-agent AI systems.

Prior to IBM, Qiushi received his Ph.D. in Computer Science from the University of Minnesota. His doctoral research focused on systems security, developing precise and scalable program analysis techniques for detecting critical security vulnerabilities in OS kernels and foundational software. He received his B.S. from the University of Science and Technology of China (USTC).

Qiushi has published extensively at top security venues including IEEE S&P, USENIX Security, NDSS, and ACM CCS. His work on automated vulnerability detection has identified hundreds of security bugs in widely deployed open-source programs. He has served as a program committee member for USENIX Security, NDSS, IEEE S&P, among others.