Papers › Adaptive Attacks Break Defenses Against Indirect Prompt Injection Attacks on LLM Agents

Adaptive Attacks Break Defenses Against Indirect Prompt Injection Attacks on LLM Agents

27 Feb 2025arXiv:2503.00061archive 2025-07-28

Qiusi Zhan, Richard Fang, Henil Shalin Panchal, Daniel Kang

Large Language Model (LLM) agents exhibit remarkable performance across diverse applications by using external tools to interact with environments. However, integrating external tools introduces security risks, such as indirect prompt injection (IPI) attacks. Despite defenses designed for IPI attacks, their robustness remains questionable due to insufficient testing against adaptive attacks. In this paper, we evaluate eight different defenses and bypass all of them using adaptive attacks, consistently achieving an attack success rate of over 50%. This reveals critical vulnerabilities in current defenses. Our research underscores the need for adaptive attack evaluation when designing defenses to ensure robustness and reliability. The code is available at https://github.com/uiuc-kang-lab/AdaptiveAttackAgent.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

uiuc-kang-lab/adaptiveattackagent officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Language ModelingLanguage ModellingLarge Language Model

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections