SecurityWeek

Decades-Old Bash Tricks Expose AI Coding Agents to Supply Chain Attacks

Decades-old Bash shell tricks can bypass safeguards in most open source AI coding agents, creating a new software supply ...
IEEE

Control Barrier Function for Aligning Large Language Models

Abstract: This article proposes a control-based framework for aligning large language models (LLMs) by leveraging a control barrier function (CBF) to ensure user-desirable text generation. The ...
Microsoft

AutoJack: How a single page can RCE the host running your AI agent

Ongoing research into AI agent framework security identified an exploit chain in AutoGen Studio (AutoGen’s open-source prototyping user interface) that allows untrusted web content rendered by a ...
IEEE

Cooperative Control Framework for Dual-Arm Robot Enhanced by Vision Language Model and Reinforcement Learning

Abstract: This paper presents a cooperative control framework for dual-arm robots that integrates vision-language models (VLMs) with online reinforcement learning (RL) to enhance autonomy and ...