Welcome to my homepage

I am a Ph.D. student in the Department of Computer Science and Engineering, The Hong Kong University of Science and Technology, advised by Prof. Shuai Wang.
Before that, I received my M.Eng. from Harbin Institute of Technology (Shenzhen) in January 2022, advised by Prof. Zheng Zhang. And I got my B.Eng. from China University of Geosciences, Wuhan, in 2019.
Research interests: AI Safety & Security, LLM Security, Adversarial Machine Learning
Google Scholar
Email: xunguangwang AT gmail.com; xunguang DOT wang AT cse.ust.hk

Publications

5. Semantic-Aware Adversarial Training for Reliable Deep Hashing Retrieval

Xu Yuan, Zheng Zhang, Xunguang Wang, Lin Wu

IEEE Transactions on Information Forensics and Security (TIFS), 2023

4. CgAT: Center-Guided Adversarial Training for Deep Hashing-Based Retrieval

Xunguang Wang, Yiqun Lin, Xiaomeng Li

The Web Conference (WWW), 2023

3. Targeted Attack of Deep Hashing via Prototype-Supervised Adversarial Networks

Zheng Zhang, Xunguang Wang, Guangming Lu, Fumin Shen, Lei Zhu

IEEE Transactions on Multimedia (TMM), 2022

2. Targeted Attack and Defense for Deep Hashing

Xunguang Wang, Zheng Zhang, Guangming Lu, Yong Xu

ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR), 2021

1. Prototype-Supervised Adversarial Network for Targeted Attack of Deep Hashing

Xunguang Wang, Zheng Zhang, Baoyuan Wu, Fumin Shen, Guangming Lu

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021

2. SelfDefend: LLMs Can Defend Themselves against Jailbreaking in a Practical Manner

Xunguang Wang, Daoyuan Wu, Zhenlan Ji, Zongjie Li, Pingchuan Ma, Shuai Wang, Yingjiu Li, Yang Liu, Ning Liu, Juergen Rahmel

arXiv, 2024

1. InstructTA: Instruction-Tuned Targeted Attack for Large Vision-Language Models

Xunguang Wang, Zhenlan Ji, Pingchuan Ma, Zongjie Li, Shuai Wang

arXiv, 2023