Dongxian WU

Enthusiast for building trustworthy AI systems

I am a Postdoctoral Researcher at the University of Tokyo, hosted by Prof. Masashi Sugiyama.

Before this, I got my PhD degree in the Department of Computer Science and Technology at Tsinghua University, co-advised by Prof. Shu-Tao Xia and Prof. Yisen Wang.

My research mainly focuses on trustworthy machine learning, especially adversarial learning and data security.

Email to:


Oct, 2021 I was invited to give an online talk at UT Austin [slide].
Sep, 2021 Our paper was accepted by NeurIPS 2021.
Aug, 2021 I became a Postdoctoral Researcher at UTokyo.
Jun, 2021 I received my PhD degree at Tsinghua University.

selected publications

  1. Adversarial Neuron Pruning Purifies Backdoored Deep Models
    Dongxian Wu, and Yisen Wang
    In NeurIPS, 2021
  2. Adversarial Weight Perturbation Helps Robust Generalization
    Dongxian Wu, Shu-Tao Xia, and Yisen Wang
    In NeurIPS, 2020
  3. Skip Connections Matter: On the Transferability of Adversarial Examples Generated with Resnets
    Dongxian Wu, Yisen Wang, Shu-Tao Xia, James Bailey, and Xingjun Ma
    In ICLR Spotlight, 2020