👋 Welcome to Hao Wang’s Homepage
Hi, this is Hao Wang (王浩). I’m a Ph.D. student at the College of Computer Science, Chongqing University, China, under the supervision of Prof. Tao Xiang (向涛) and Prof. Shangwei Guo (郭尚伟) and a visiting Ph.D. student at the College of Computing and Data Science, Nanyang Technological University, Singapore, under the supervision of Prof. Tianwei Zhang (张天威). My research interests focus on trustworthy machine learning, with a particular emphasis on the security of LLM-based agents.
📝 Publications
-
On the Adversarial Robustness of Large Vision-Language Models under Visual Token Compression
Xinwei Zhang, Hangcheng Liu, Li Bai, Hao Wang, Qingqing Ye, Tianwei Zhang, Haibo Hu
International Conference on Machine Learning (ICML), 2026 -
Vector-Guided Embezzler: A Reconstruction Attack Against Retrieval-Augmented Generation in Agentic AI Communication
Lishuang Hu, Hao Wang, Tao Xiang, Zhuo Chen, Jialing He, Shangwei Guo
IEEE Transactions on Cognitive Communications and Networking, 2026 -
LLMBD:Backdoor Defense via Large Language Model Paraphrasing and Data Voting in NLP
Fei Ouyang, Di Zhang, Chunlong Xie, Hao Wang, Tao Xiang
Knowledge-Based Systems, 2025 -
Model Supply Chain Poisoning: Backdooring Pre-trained Models via Embedding Indistinguishability (Oral)
Hao Wang, Shangwei Guo, Jialing He, Hangcheng Liu, Tianwei Zhang, Tao Xiang
Proceedings of the ACM Web Conference 2025 (WWW), 2025 -
Beware of Road Markings: A New Adversarial Patch Attack to Monocular Depth Estimation
Hangcheng Liu, Zhenhu Wu, Hao Wang, Xingshuo Han, Shangwei Guo, Tao Xiang, Tianwei Zhang
The Thirty-eighth Annual Conference on Neural Information Processing Systems (NeurIPS), 2024 -
EvilEdit: Backdooring Text-to-Image Diffusion Models in One Second
Hao Wang, Shangwei Guo, Jialing He, Kangjie Chen, Shudong Zhang, Tianwei Zhang, Tao Xiang
Proceedings of the 32nd ACM International Conference on Multimedia (MM), 2024 -
NLPSweep: A comprehensive defense scheme for mitigating NLP backdoor attacks
Tao Xiang, Fei Ouyang, Di Zhang, Chunlong Xie, Hao Wang
Information Sciences, 2024