Xiao Zhang

Xiao Zhang is a tenure-track faculty member at the CISPA Helmholtz Center for Information Security in Saarbrücken, Germany. He obtained his PhD in Computer Science from the University of Virginia in 2022, advised by Prof. David Evans, and holds an MS in Statistics from UVA and a BS in Mathematics from Tsinghua University. His research focuses on trustworthy machine learning, particularly adversarial robustness, security, and privacy-preserving techniques.

Zhang's research interests span:

• Adversarial machine learning and intrinsic robustness limitations
• Trustworthy AI systems for security-critical applications
• Statistical machine learning and optimization methods
• Privacy-preserving techniques and data poisoning defenses
• Robust representation learning and generative models

His recent publications (2022-2025) demonstrate a strong focus on:

• Developing new frameworks for adversarial robustness measurement
• Creating defenses against data poisoning and membership inference attacks
• Exploring fundamental limits of robust learning
• Applying diffusion models and generative approaches to security
• Advancing anti-facial recognition techniques

Zhang leads a research group at CISPA investigating robust machine learning systems and has presented work at top venues including NeurIPS, ICLR, ICML, and CCS. While no awards are mentioned in the source material, his research addresses critical challenges in AI security.