Faculty
Xiao Zhang ist Tenure-Track Faculty am CISPA Helmholtz-Zentrum für Informationssicherheit. Seine Forschung umfasst Themen wie Adversarial Machine Learning, Statistical Machine Learning und Optimierung. Im Besonderen ist er daran interessiert, das Fehlverhalten von maschinellen Lernmodellen gegenüber verschiedenen Angreifern zu verstehen und robuste Systeme für maschinelle Lernanwendungen zu entwickeln. 2022 schloss er seine Promotion in Informatik unter der Leitung von Prof. David Evans an der University of Virginia ab. Zuvor erwarb er seinen Master-Abschluss in Statistik an der University of Virginia und seinen Bachelor-Abschluss in Mathematik an der Tsinghua University. Er ist Mitglied des European Laboratory for Learning and Intelligent Systems (ELLIS).
Transactions of Machine Learning Research (TMLR)
ICML-Workshop (ICMLW)
Provably Robust Cost-Sensitive Learning via Randomized Smoothing
International Conference on Learning Representations (ICLR)
Improved Estimation of Concentration Under Lp-Norm Distance Metric Using Half Spaces
International Conference on Machine Learning (ICML)
Learning Adversarially Robust Representations via Worst-Case Mutual Information Maximization
International Conference on Artificial Intelligence and Statistics (AISTATS)
Understanding the intrinsic robustness of image distributions using conditional generative models
Conference on Neural Information Processing Systems (NeurIPS)
Empirically Measuring Concentration: Fundamental Limits to Intrinsic Robustness
International Conference on Learning Representations (ICLR)
Cost-Sensitive Robustness against Adversarial Examples
International Conference on Artificial Intelligence and Statistics (AISTATS)
Learning One-hidden-layer ReLU Networks via Gradient Descent
International Conference on Machine Learning (ICML)
Fast and Sample Efficient Inductive Matrix Completion via Multi-Phase Procrustes Flow
International Conference on Machine Learning (ICML)
A Primal-Dual Analysis of Global Optimality in Nonconvex Low-Rank Matrix Recovery