Security--Fidelity Tradeoffs: The Hidden Cost of Prompt Injection Defense

Abstract

We identify a security-fidelity tradeoff in defending LLMs against indirect prompt injection: defenses resist injected instructions largely by suppressing untrusted text, which corrupts tasks that must preserve it, such as translation and document editing. Attack-success metrics cannot see this, because a model that ignores an injection and one that faithfully processes it as data score identically. We introduce SecFid, a benchmark built so that executing an injection, processing it as data, and

Categories

Framework mappings

Suggested from the entry's categories.

@misc{hermon2026securityfidelity,
  title = {{Security--Fidelity Tradeoffs: The Hidden Cost of Prompt Injection Defense}},
  author = {Mitchell Hermon and Rahul Gupta and Weitong Ruan and Ekraam Sabir and Haohan Wang},
  year = {2026},
  month = jun,
  eprint = {2606.30783},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2606.30783}
}