AI RESEARCH
ESLD (External Surrogate Latent Defense): A Latent-Space Architecture for Faster, Stronger Prompt-Injection Defense
arXiv CS.AI
•
ArXi:2605.18918v1 Announce Type: cross Modern AI assistants are agentic. To answer a single user request, the underlying language model pulls in information from many sources, such as web searches, retrieved documents, tool outputs, and user follow-ups, and reasons over them across several steps. Any of these inputs can carry malicious content. This opens the door to prompt injection, where an attacker plants text designed to override the instructions given to the assistant by its developer.