معرفی
Xiao Zhang is a tenure-track faculty member at the CISPA Helmholtz Center for Information Security and a member of the European Laboratory for Learning and Intelligent Systems (ELLIS). He obtained his Ph.D. in Computer Science from the University of Virginia in 2022 under Prof. David Evans, following an M.S. in Statistics from the same institution and a B.S. in Mathematics from Tsinghua University.
Research Focus
Zhang's research spans foundational and applied aspects of trustworthy machine learning, with emphasis on:
- Security vulnerabilities in ML systems (adversarial attacks, data poisoning)
- Robustness guarantees for learning algorithms
- Optimization methods for deep learning
- Privacy-preserving techniques
- Multimodal and physical-world applications
His recent work focuses on developing theoretically-grounded defenses against emerging threats to AI systems.
Publication Trends
Zhang's 15 most recent publications (2019-2025) demonstrate consistent focus on adversarial machine learning, with growing emphasis on: 1) Physical-world attacks/defenses, 2) Multimodal model security, and 3) Certified robustness guarantees. The work consistently appears at top-tier venues (NeurIPS, ICLR, CCS).
Academic Activities
He actively recruits students and collaborators for trustworthy ML research, with open positions for PhD candidates and research assistants. No awards or specific grant information is documented in the provided materials.
