I’m a Ph.D. student at School of Cyber Science and Engineering, Wuhan University, where I am conducting research in AI Security. I am very fortunate to be advised by Prof. Qian Wang of NIS&P Lab. My works primarily focus on adversarial robustness of AI systems, alignment for large language models, etc.

Previously, I received the B.E. degree in communication engineering from Shandong University in 2019 and the M.S. degree in electronic information from Wuhan University, China, in 2022.

Contact me at shenyizhang@whu.edu.cn or syzhang.whu@gmail.com.

Publications

2025

• IntentBreaker: Intent-Adaptive Jailbreak Attack on Large Language Models
  Shengnan Guo, Yuchen Zhai, Shenyi Zhang, Lingchen Zhao, Zhangyi Wang
  European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD), 2025
• Selective Masking Adversarial Attack on Automatic Speech Recognition Systems
  Zheng Fang, Shenyi Zhang, Tao Wang, Bowen Li, Lingchen Zhao, Zhangyi Wang
  IEEE International Conference on Multimedia and Expo (ICME), 2025
  [preprint]
• JBShield: Defending Large Language Models from Jailbreak Attacks through Activated Concept Analysis and Manipulation
  Shenyi Zhang, Yuchen Zhai, Keyan Guo, Hongxin Hu, Shengnan Guo, Zheng Fang, Lingchen Zhao, Chao Shen, Cong Wang, Qian Wang
  USENIX Security Symposium, 2025
  [paper] [preprint] [code]

2024

• Zero-query Adversarial Attack on Black-box Automatic Speech Recognition Systems
  Zheng Fang, Tao Wang, Lingchen Zhao, Shenyi Zhang, Bowen Li, Yunjie Ge, Qi Li, Chao Shen, Qian Wang
  ACM SIGSAC Conference on Computer and Communications Security (CCS), 2024
  [paper] [preprint]
• Hijacking Attacks against Neural Networks by Analyzing Training Data
  Yunjie Ge, Qian Wang, Huayang Huang, Qi Li, Cong Wang, Chao Shen, Lingchen Zhao, Peipei Jiang, Zheng Fang, Shenyi Zhang
  USENIX Security Symposium, 2024
  [paper] [preprint] [code]
• Enhancing the Transferability of Adversarial Examples with Noise Injection Augmentation
  Yiheng Duan, Yunjie Ge, Zixuan Wang, Jiayi Yu, Shenyi Zhang, Libing Wu
  IEEE International Conference on Multimedia and Expo (ICME), 2024
  [paper]
• Perception-driven Imperceptible Adversarial Attack against Decision-based Black-box Models
  Shenyi Zhang, Baolin Zheng, Peipei Jiang, Lingchen Zhao, Chao Shen, Qian Wang
  IEEE Transactions on Information Forensics and Security (TIFS), 2024
  [paper] [code]

2021

• Black-box Adversarial Attacks on Commercial Speech Platforms with Minimal Information
  Baolin Zheng, Peipei Jiang, Qian Wang, Qi Li, Chao Shen, Cong Wang, Yunjie Ge, Qingyang Teng, Shenyi Zhang
  ACM SIGSAC Conference on Computer and Communications Security (CCS), 2021
  [paper] [preprint]

Services

• Reviewer
  • IEEE Transactions on Information Forensics and Security (TIFS)
  • IEEE Transactions on Dependable and Secure Computing (TDSC)
  • IEEE Transactions on Emerging Topics in Computing (TETC)
  • IEEE/ACM Transactions on Networking (TON)
  • ACM Transactions on Cyber-Physical Systems (TCPS)
  • ACM Transactions on Internet Technology (TOIT)
  • Computer Vision and Image Understanding (CVIU)
  • Knowledge-Based Systems (KBS)
  • Neurocomputing
  • ACM MM 2025
  • IEEE ICME 2024, 2025
  • IJCNN 2025

Projects

• NewAdversarialAttackPaper: A list of recent adversarial attack and defense papers (including those on large language models).
• Imagenet-1K-Formatter: Reorganizing the ImageNet-1k dataset into the standard directory structure.