Scholar
Xiao Zhang
Google Scholar ID: L-lz7CUAAAAJ
CISPA Helmholtz Center for Information Security
Citations & Impact
Citations
584
H-index
12
i10-index
12
Publications
20
Co-authors
30
list available
Resume (English only)
Academic Achievements
- - Publications:
- - "GASP: Efficient Black-Box Generation of Adversarial Suffixes for Jailbreaking LLMs" (NeurIPS 2025)
- - "DivTrackee versus DynTracker: Promoting Diversity in Anti-Facial Recognition against Dynamic FR Strategy" (CCS 2025, Distinguished Paper Award)
- - "Do Parameters Reveal More than Loss for Membership Inference?" (TMLR 2024)
- - "What Distributions are Robust to Indiscriminate Poisoning Attacks for Linear Learners?" (NeurIPS 2023)
- - "Understanding Intrinsic Robustness using Label Uncertainty" (ICLR 2022)
Research Experience
- Tenure-track faculty at CISPA Helmholtz Center for Information Security, leading the AIR-ML Lab. Previously, pursued a Ph.D. at the University of Virginia.
Education
- - Ph.D. in Computer Science from the University of Virginia, advised by Prof. David Evans
- - M.S. in Statistics from the University of Virginia
- - B.S. in Mathematics and Applied Mathematics from Tsinghua University
Background
- A tenure-track faculty member at CISPA Helmholtz Center for Information Security, leading the AIR-ML Lab. Research interests include machine learning (with a focus on trustworthy AI, robustness, safety, privacy, bias, and interpretability), deep learning theory, generative modeling, and optimization.
Miscellany
- Looking for self-motivated students interested in machine learning research, including PhD students, HiWis, interns, and visiting students. For more information, please visit our lab website.
