Publications

* indicates equal contribution.

Conferences & Journals

• Benign Overfitting in Adversarial Training for Vision Transformers
  [Link] [arXiv]
  Jiaming Zhang, Meng Ding, Shaopeng Fu, Jingfeng Zhang, and Di Wang
  ICML 2026

• Understanding Private Learning from Feature Perspective
  [arXiv]
  Meng Ding, Mingxi Lei, Shaopeng Fu, Shaowei Wang, Di Wang, and Jinhui Xu
  ICML 2026

• Understanding and Improving Continuous LLM Adversarial Training via In-Context Learning Theory
  [Link] [arXiv] [Code]
  Shaopeng Fu and Di Wang
  ICLR 2026

• Short-length Adversarial Training Helps LLMs Defend Long-length Jailbreak Attacks: Theoretical and Empirical Evidence
  [Link] [arXiv] [Video] [Code]
  Shaopeng Fu, Liang Ding, Jingfeng Zhang, and Di Wang
  NeurIPS 2025

• Theoretical Analysis of Robust Overfitting for Wide DNNs: An NTK Approach
  [OpenReview] [IEEE] [arXiv] [Video] [Code]
  Shaopeng Fu and Di Wang
  ICLR 2024
  IEEE Transactions on Information Theory 71(8), 2025

• Robust Unlearnable Examples: Protecting Data Against Adversarial Learning
  [Link] [arXiv] [Video] [Code]
  Shaopeng Fu, Fengxiang He, Yang Liu, Li Shen, and Dacheng Tao
  ICLR 2022

• Knowledge Removal in Sampling-based Bayesian Inference
  [Link] [arXiv] [Video] [Code]
  Shaopeng Fu*, Fengxiang He*, and Dacheng Tao
  ICLR 2022

• Artificial Neural Variability for Deep Learning: On Overfitting, Noise Memorization, and Catastrophic Forgetting
  [Link] [arXiv] [Code]
  Zeke Xie, Fengxiang He, Shaopeng Fu, Issei Sato, Dacheng Tao, and Masashi Sugiyama
  Neural Computation 33(8), 2021

Manuscripts

• RefineRL: Advancing Competitive Programming with Self-Refinement Reinforcement Learning
  [arXiv]
  Shaopeng Fu, Xingxing Zhang, Li Dong, and Furu Wei
  arXiv preprint 2026

• Dual-Adversarial Safety Alignment: Cultivating Intrinsic Threat Comprehension in LRMs
  [arXiv] [Code]
  Hongli Shen*, Shaopeng Fu*, Qinbo Zhang, Jian Li, and Di Wang
  arXiv preprint 2026

• Accelerating Suffix Jailbreak Attacks with Prefix-Shared KV-Cache
  [arXiv] [Code]
  Xinhai Wang*, Shaopeng Fu*, Shu Yang, Liangyu Wang, Tianhang Zheng, and Di Wang
  arXiv preprint 2026

• Understanding the Impact of Differentially Private Training on Memorization of Long-Tailed Data
  [arXiv]
  Jiaming Zhang, Huanyi Xie, Meng Ding, Shaopeng Fu, Jinyan Liu, and Di Wang
  arXiv preprint 2026

• Pre-trained Encoder Inference: Revealing Upstream Encoders in Downstream Machine Learning Services
  [arXiv] [Code]
  Shaopeng Fu, Xuexue Sun, Ke Qing, Tianhang Zheng, and Di Wang
  arXiv preprint 2024

• Robustness, Privacy, and Generalization of Adversarial Training
  [arXiv] [Code]
  Fengxiang He*, Shaopeng Fu*, Bohan Wang*, and Dacheng Tao
  arXiv preprint 2020