ESLD (External Surrogate Latent Defense): A Latent-Space Architecture for Faster, Stronger Prompt-Injection Defense

Abstract

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. For example, an attacker applying for a jo

Categories

Framework mappings

Suggested from the entry's categories.

@misc{narendra2026esld,
  title = {{ESLD (External Surrogate Latent Defense): A Latent-Space Architecture for Faster, Stronger Prompt-Injection Defense}},
  author = {Yash Narendra},
  year = {2026},
  month = may,
  eprint = {2605.18918},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2605.18918}
}