Skip to content
View csdongxian's full-sized avatar
💪
Be your own hero
💪
Be your own hero
75 followers · 25 following

Achievements

Achievement: Starstruckx2Achievement: Arctic Code Vault Contributor

Achievements

Achievement: Starstruckx2Achievement: Arctic Code Vault Contributor

Block or report csdongxian

Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
csdongxian/README.md

Hi there, I am Dongxian WU (吴栋贤 in Chinese) 👋

I am an enthusiast for building a trustworthy AI system. Currently, I am a Postdoctoral Researcher at the University of Tokyo, hosted by Prof. Masashi Sugiyama.

🔭 My research mainly focus on:

  • adversarial attacks and defenses
  • data security, especially backdoor attacks and defenses
  • weakly supervised learning, especially noisy labels

📫 Reach me by:

Pinned Loading

  1. skip-connections-matter skip-connections-matter Public

    Codes for ICLR 2020 paper "Skip Connections Matter: On the Transferability of Adversarial Examples Generated with ResNets"

    Python 70 9

  2. AWP AWP Public

    Codes for NeurIPS 2020 paper "Adversarial Weight Perturbation Helps Robust Generalization"

    Python 185 19

  3. ANP_backdoor ANP_backdoor Public

    Codes for NeurIPS 2021 paper "Adversarial Neuron Pruning Purifies Backdoored Deep Models"

    Python 59 13