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).
Annual Meeting of the Association for Computational Linguistics (ACL)
IEEE Conference on Secure and Trustworthy Machine Learning (SaTML)
Efficient Semi-Supervised Adversarial Training via Latent Clustering-Based Data Reduction
Conference on Neural Information Processing Systems (NeurIPS)
GASP: Efficient Black-Box Generation of Adversarial Suffixes for Jailbreaking LLMs
IEEE International Conference on Computer Vision (ICCV)
IAP: Invisible Adversarial Patch Attack through Perceptibility-Aware Localization and Perturbation Optimization
ACM Conference on Computer and Communications Security (CCS)
DivTrackee versus DynTracker: Promoting Diversity in Anti-Facial Recognition against Dynamic FR Strategy
Workshop for Research on Agent Language Models at the 63rd Annual Meeting of the Association for Computational Linguistics (ACL)
Safe in Isolation, Dangerous Together: Agent-Driven Multi-Turn Decomposition Jailbreaks on LLMs
International Conference on Machine Learning (ICML)
Provably Cost-Sensitive Adversarial Defense via Randomized Smoothing
ICLR-Workshop (ICLRW)
PREDICTING TIME-VARYING METABOLIC DYNAMICS USING STRUCTURED NEURAL ODE PROCESSES
IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)
DiffPAD: Denoising Diffusion-Based Adversarial Patch Decontamination
Transactions on Machine Learning Research (TMLR)Do Parameters Reveal More than Loss for Membership Inference?