3 citations · 3 across the 3 of their papers we have counts for
Showing 2026Show all
2 papers · 1 filter
cs.CR2026
SIR: Self-improving Red-teaming for Compute Use Agents
Chen Xiong, Zhiyuan He, Pin-Yu Chen +2
Computer-use agents (CUAs) are agents powered by vision-language models (VLMs) that perceive a screen and operate an operating system through mouse, keyboard, and terminal interact…
cs.CR2026
Steering Externalities: Benign Activation Steering Unintentionally Increases Jailbreak Risk for Large Language Models
Chen Xiong, Zhiyuan He, Pin-Yu Chen +2
Activation steering is a practical post-training model alignment technique to enhance the utility of Large Language Models (LLMs). Prior to deploying a model as a service, develope…