publications

publications by categories in reversed chronological order. generated by jekyll-scholar.

2024

  1. Arxiv Preprint
    Defending LLMs against Jailbreaking Attacks via Backtranslation
    Yihan Wang*, Zhouxing Shi* , Andrew Bai , and Cho-Jui Hsieh
    arXiv preprint arXiv:2402.16459, 2024
    URL Code
  2. TACL
    Red teaming language model detectors with language models
    Zhouxing Shi* , Yihan Wang*, Fan Yin* , Xiangning Chen , Kai-Wei Chang , and Cho-Jui Hsieh
    Transactions of the Association for Computational Linguistics, 2024
    URL Code
  3. NeurIPS 2023
    Universality and limitations of prompt tuning
    Yihan Wang, Jatin Chauhan , Wei Wang , and Cho-Jui Hsieh
    Advances in Neural Information Processing Systems, 2024
    URL

2023

  1. ICLR 2024
    Two-stage LLM Fine-tuning with Less Specialization and More Generalization
    Yihan Wang, Si Si , Daliang Li , Michal Lukasik , Felix Yu , Cho-Jui Hsieh , Inderjit S Dhillon , and Sanjiv Kumar
    In The Twelfth International Conference on Learning Representations , 2023
    URL

2022

  1. NeurIPS 2022
    Efficiently computing local lipschitz constants of neural networks via bound propagation
    Zhouxing Shi , Yihan Wang, Huan Zhang , J Zico Kolter , and Cho-Jui Hsieh
    Advances in Neural Information Processing Systems, 2022
    URL
  2. ICML 2022
    A branch and bound framework for stronger adversarial attacks of ReLU networks
    Huan Zhang , Shiqi Wang , Kaidi Xu , Yihan Wang, Suman Jana , Cho-Jui Hsieh , and Zico Kolter
    In International Conference on Machine Learning , 2022
    URL

2021

  1. ICLR 2022
    On the Convergence of Certified Robust Training with Interval Bound Propagation
    Yihan Wang*, Zhouxing Shi* , Quanquan Gu , and Cho-Jui Hsieh
    In International Conference on Learning Representations , 2021
    URL
  2. NeurIPS 2021
    Fast certified robust training with short warmup
    Zhouxing Shi* , Yihan Wang*, Huan Zhang , Jinfeng Yi , and Cho-Jui Hsieh
    Advances in Neural Information Processing Systems, 2021
    URL Code

2020

  1. ICML 2021
    Fast and Complete: Enabling Complete Neural Network Verification with Rapid and Massively Parallel Incomplete Verifiers
    Kaidi Xu , Huan Zhang , Shiqi Wang , Yihan Wang, Suman Jana , Xue Lin , and Cho-Jui Hsieh
    In International Conference on Learning Representations , 2020
    URL Code
  2. ICML 2020
    On lp-norm robustness of ensemble decision stumps and trees
    Yihan Wang, Huan Zhang , Hongge Chen , Duane Boning , and Cho-Jui Hsieh
    In International Conference on Machine Learning , 2020
    URL Code
  3. NeurIPS 2020
    Automatic perturbation analysis for scalable certified robustness and beyond
    Kaidi Xu , Zhouxing Shi , Huan Zhang , Yihan Wang, Kai-Wei Chang , Minlie Huang , Bhavya Kailkhura , Xue Lin , and Cho-Jui Hsieh
    Advances in Neural Information Processing Systems, 2020
    URL Code