AgentDojo: A Dynamic Environment to Evaluate Attacks and Defenses for LLM Agents

Edoardo Debenedetti, Jie Zhang, Mislav Balunovic, Luca Beurer-Kellner, Marc Fischer, Florian Tramer

Abstract

Introduces AgentDojo, a framework for evaluating the security of LLM agents against prompt injection and other attacks in realistic tool-use scenarios.

Categories

Tags

Framework Mappings

Cite This Resource

@article{llmsec202400012,
  title = {AgentDojo: A Dynamic Environment to Evaluate Attacks and Defenses for LLM Agents},
  author = {Edoardo Debenedetti and Jie Zhang and Mislav Balunovic and Luca Beurer-Kellner and Marc Fischer and Florian Tramer},
  year = {2024},
  journal = {arXiv preprint},
  url = {https://arxiv.org/abs/2406.13352},
}