no code implementations • 20 Feb 2024 • Yujun Zhou, Yufei Han, Haomin Zhuang, Taicheng Guo, Kehan Guo, Zhenwen Liang, Hongyan Bao, Xiangliang Zhang
Large Language Models (LLMs) demonstrate remarkable capabilities across diverse applications.
no code implementations • 13 Dec 2022 • Hongyan Bao, Yufei Han, Yujun Zhou, Xin Gao, Xiangliang Zhang
Our work targets at searching feasible adversarial perturbation to attack a classifier with high-dimensional categorical inputs in a domain-agnostic setting.
no code implementations • 13 Dec 2022 • Helene Orsini, Hongyan Bao, Yujun Zhou, Xiangrui Xu, Yufei Han, Longyang Yi, Wei Wang, Xin Gao, Xiangliang Zhang
Machine Learning-as-a-Service systems (MLaaS) have been largely developed for cybersecurity-critical applications, such as detecting network intrusions and fake news campaigns.
no code implementations • ICLR 2022 • Hongyan Bao, Yufei Han, Yujun Zhou, Yun Shen, Xiangliang Zhang
Characterizing and assessing the adversarial vulnerability of classification models with categorical input has been a practically important, while rarely explored research problem.
no code implementations • 25 Aug 2020 • Zhize Li, Hongyan Bao, Xiangliang Zhang, Peter Richtárik
Then, we show that PAGE obtains the optimal convergence results $O(n+\frac{\sqrt{n}}{\epsilon^2})$ (finite-sum) and $O(b+\frac{\sqrt{b}}{\epsilon^2})$ (online) matching our lower bounds for both nonconvex finite-sum and online problems.