3 papers
cs.CR2026
A Systematic Security Evaluation of OpenClaw and Its Variants
Yuhang Wang, Haichang Gao, Zhenxing Niu +4
Tool-augmented AI agents substantially extend the practical capabilities of large language models, but they also introduce security risks that cannot be identified through model-on…
cs.AI2026
From Assistant to Double Agent: Formalizing and Benchmarking Attacks on OpenClaw for Personalized Local AI Agent
Yuhang Wang, Feiming Xu, Zheng Lin +6
Although large language model (LLM)-based agents, exemplified by OpenClaw, are increasingly evolving from task-oriented systems into personalized AI assistants for solving complex…
cs.LG2025
HumorReject: Decoupling LLM Safety from Refusal Prefix via A Little Humor
Zihui Wu, Haichang Gao, Jiacheng Luo +1
Large Language Models (LLMs) commonly rely on explicit refusal prefixes for safety, making them vulnerable to prefix injection attacks. We introduce HumorReject, a novel data-drive…