12 papers
Black-Box Skill Stealing Attack from Proprietary LLM Agents: An Empirical Study
Zihan Wang, Rui Zhang, Yu Liu +4
Large language model (LLM) agents increasingly rely on skills to package reusable capabilities through instructions, tools, and resources. High-quality skills embed expert knowledg…
The Art of (Mis)alignment: How Fine-Tuning Methods Effectively Misalign and Realign LLMs in Post-Training
Rui Zhang, Hongwei Li, Yun Shen +6
The deployment of large language models (LLMs) raises significant ethical and safety concerns. While LLM alignment techniques are adopted to improve model safety and trustworthines…
BadTemplate: A Training-Free Backdoor Attack via Chat Template Against Large Language Models
Zihan Wang, Hongwei Li, Rui Zhang +2
Chat template is a common technique used in the training and inference stages of Large Language Models (LLMs). It can transform input and output data into role-based and templated…
Hidden Tail: Adversarial Image Causing Stealthy Resource Consumption in Vision-Language Models
Rui Zhang, Zihan Wang, Tianli Yang +5
Vision-Language Models (VLMs) are increasingly deployed in real-world applications, but their high inference cost makes them vulnerable to resource consumption attacks. Prior attac…
ConfGuard: A Simple and Effective Backdoor Detection for Large Language Models
Zihan Wang, Rui Zhang, Hongwei Li +4
Backdoor attacks pose a significant threat to Large Language Models (LLMs), where adversaries can embed hidden triggers to manipulate LLM's outputs. Most existing defense methods,…
FIGhost: Fluorescent Ink-based Stealthy and Flexible Backdoor Attacks on Physical Traffic Sign Recognition
Shuai Yuan, Guowen Xu, Hongwei Li +5
Traffic sign recognition (TSR) systems are crucial for autonomous driving but are vulnerable to backdoor attacks. Existing physical backdoor attacks either lack stealth, provide in…