publications

(*) denotes equal contribution; (†) denotes corresponding author

2026

  1. Rethinking Faithfulness in LLMs: A Pairwise Context-Sensitive Perspective
    Zizhuo Zhang, Xiong Peng, Jingwei Sun, Rong Yao, Borui Jiang, and Bo Han
    arXiv preprint arXiv:2610.07894, 2026
  2. Test-time Calibration Learning for Large Language Model Reasoning
    Zizhuo Zhang*, Xiong Peng*, Jingwei Sun*, Rong Yao, Shixiong Kai, Mingxuan Yuan, and Bo Han
    arXiv preprint arXiv:2610.02695, 2026

2025

  1. Generative Model Inversion Through the Lens of the Manifold Hypothesis
    Xiong Peng, Bo Han†, Fengfei Yu, Tongliang Liu, Feng Liu, and Mingyuan Zhou
    In the 39th Conference on Neural Information Processing Systems, 2025
  2. TPAMI
    Unknown-Aware Bilateral Dependency Optimization for Defending Against Model Inversion Attacks
    Xiong Peng, Feng Liu, Nannan Wang, Long Lan, Tongliang Liu, Yiu-ming Cheung, and Bo Han†
    IEEE Transactions on Pattern Analysis and Machine Intelligence, 2025

2024

  1. Model Inversion Attacks: A Survey of Approaches and Countermeasures
    Zhanke Zhou*, Jianing Zhu*, Fengfei Yu*, Xuan Li, Xiong Peng, Tongliang Liu, and Bo Han†
    In arXiv, 2024
  2. Pseudo-Private Data Guided Model Inversion Attacks
    Xiong Peng, Bo Han†, Feng Liu, Tongliang Liu, and Mingyuan Zhou
    In the 38th Conference on Neural Information Processing Systems, 2024
  3. Preprint
    Single-Step Diffusion Model-Based Generative Model Inversion Attacks
    Xiong Peng, Bo Han, Fengfei Yu, Feng Liu, Tongliang Liu, and Mingyuan Zhou
    2024
    Preprint

2022

  1. KDD
    Bilateral dependency optimization: Defending against model-inversion attacks
    Xiong Peng*, Feng Liu*, Jingfeng Zhang, Long Lan, Junjie Ye, Tongliang Liu, and Bo Han†
    In the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2022