AI RESEARCH
A Framework for Formalizing LLM Agent Security
arXiv CS.AI
•
ArXi:2603.19469v1 Announce Type: cross Security in LLM agents is inherently contextual. For example, the same action taken by an agent may represent legitimate behavior or a security violation depending on whose instruction led to the action, what objective is being pursued, and whether the action serves that objective. However, existing definitions of security attacks against LLM agents often fail to capture this contextual nature.