NVIDIA + Johns Hopkins Paper: Three Principles for System-Level Defense Against Indirect Prompt Injection in AI Agents

arXiv·medium signalXBlueskyLinkedInCopy link

A March 31 position paper from NVIDIA and Johns Hopkins researchers proposes three system-level principles for securing AI agents: (1) dynamic replanning and security policy updates are necessary for realistic environments, (2) context-dependent security decisions requiring LLMs must be strictly constrained in what the model can observe and decide, (3) personalization and human-in-the-loop should be core design considerations for ambiguous cases. Addresses the fundamental gap between single-prompt defenses and real-world multi-step agent deployments.