Publications

Please refer to my Google Scholar for a complete publication list.

2025

  1. Understanding and Improving Adversarial Robustness of Neural Probabilistic Circuits
    Weixin Chen, and Han Zhao
    NeurIPS 2025
  2. Neural Probabilistic Circuits: Enabling Compositional and Interpretable Predictions through Logical Reasoning
    Weixin Chen*, Simon Yu*, Huajie Shao, and 2 more authors
    UAI Workshop 2025

2024

  1. GRATH: Gradual Self-Truthifying for Large Language Models
    Weixin Chen, Dawn Song, and Bo Li
    ICML 2024

2023

  1. DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models
    Boxin Wang*, Weixin Chen*, Hengzhi Pei*, and 8 more authors
    NeurIPS (Oral & Outstanding Paper Award) 2023
  2. TrojDiff: Trojan Attacks on Diffusion Models with Diverse Targets
    Weixin Chen, Dawn Song, and Bo Li
    CVPR 2023

2022

  1. Effective Backdoor Defense by Exploiting Sensitivity of Poisoned Samples
    Weixin Chen, Baoyuan Wu, and Haoqian Wang
    NeurIPS (Spotlight) 2022