Publications (24)
Salami Attack: Stealthy Collusive Memory Poisoning against OpenClaw
Zheng Lin, Yuzhe Huang, Zhenxing Niu +2
Towards Aligned Data Removal via Twin Machine Unlearning
Haoxuan Ji, Zheng Lin, Yuyao Sun +4
SoK: Acoustic Side Channels
Ping Wang, Shishir Nagaraja, Aurélien Bourquard +2
Attention-Guided Reward for Reinforcement Learning-based Jailbreak against Large Reasoning Models
Zheng Lin, Zhenxing Niu, Haoxuan Ji +2
A Systematic Security Evaluation of OpenClaw and Its Variants
Yuhang Wang, Haichang Gao, Zhenxing Niu +4
Alleviating Robust Overfitting of Adversarial Training With Consistency Regularization
Shudong Zhang, Haichang Gao, Tianwei Zhang +2
Draw a line on your PDA to authenticate
Xiyang Liu, Zhongjie Ren, Xiuling Chang +2
Whispers of Data: Unveiling Label Distributions in Federated Learning Through Virtual Client Simulation
Zhixuan Ma, Haichang Gao, Junxiang Huang +1
Lower Difficulty and Better Robustness: A Bregman Divergence Perspective for Adversarial Training
Zihui Wu, Haichang Gao, Bingqian Zhou +2
Robust MLLM Unlearning via Visual Knowledge Distillation
Yuhang Wang, Zhenxing Niu, Haoxuan Ji +3
Guaranteed Jailbreaking Defense via Disrupt-and-Rectify Smoothing
Zheng Lin, Zhenxing Niu, Haoxuan Ji +1
Null Space Constrained Contrastive Visual Forgetting for MLLM Unlearning
Yuhang Wang, Zhenxing Niu, Haoxuan Ji +3
The Dark Side of Function Calling: Pathways to Jailbreaking Large Language Models
Zihui Wu, Haichang Gao, Jianping He +1
An audio CAPTCHA to distinguish humans from computers
Haichang Gao, Honggang Liu, Dan Yao +2
ICU-Bench:Benchmarking Continual Unlearning in Multimodal Large Language Models
Yuhang Wang, Wenjie Mei, Junkai Zhang +3
A New Graphical Password Scheme Resistant to Shoulder-Surfing
Haichang Gao, Zhongjie Ren, Xiuling Chang +2
AdvFunMatch: When Consistent Teaching Meets Adversarial Robustness
Zihui Wu, Haichang Gao, Bingqian Zhou +1
The effect of baroque music on the PassPoints graphical password
Haichang Gao, Zhongjie Ren, Xiuling Chang +2
HumorReject: Decoupling LLM Safety from Refusal Prefix via A Little Humor
Zihui Wu, Haichang Gao, Jiacheng Luo +1
Can background baroque music help to improve the memorability of graphical passwords?
Haichang Gao, Xiuling Chang, Zhongjie Ren +2
From Assistant to Double Agent: Formalizing and Benchmarking Attacks on OpenClaw for Personalized Local AI Agent
Yuhang Wang, Feiming Xu, Zheng Lin +6
Against Spyware Using CAPTCHA in Graphical Password Scheme
Liming Wang, Xiuling Chang, Zhongjie Ren +3
GlitchMiner: Mining Glitch Tokens in Large Language Models via Gradient-based Discrete Optimization
Zihui Wu, Haichang Gao, Ping Wang +3
Re-Triggering Safeguards within LLMs for Jailbreak Detection
Zheng Lin, Zhenxing Niu, Haoxuan Ji +2