2605.28201v1 May 27, 2026 cs.AI

Plant, Persist, Trigger: Sleeper Attack on Large Language Model Agents

Fuli Feng
Fuli Feng
Citations: 1,400
h-index: 20
Dongrui Liu
Dongrui Liu
Citations: 49
h-index: 3
Wenjie Wang
Wenjie Wang
Citations: 31
h-index: 3
Fengbin Zhu
Fengbin Zhu
National University of Singapore
Citations: 1,375
h-index: 14
Yongxiang Li
Yongxiang Li
Citations: 156
h-index: 8
Moxin Li
Moxin Li
Citations: 770
h-index: 14
Z. Ma
Z. Ma
Citations: 19
h-index: 2

Large Language Model (LLM) agents remain vulnerable to safety threats from the external environment, where attackers inject adversarial content into external observations such as tool-returned data, webpages, or MCP context, causing harmful agentic behaviors such as unsafe actions or incorrect outputs. Existing studies typically focus on single-interaction attacks, where the agent observes adversarial content and immediately exhibits harmful behavior within one user request. However, we show that adversarial content can also persist across interactions served by the same agent, making such threats harder to detect and mitigate. Specifically, adversarial content may persist in the agent state, remain dormant across interactions, and later be activated by a benign user query. We formalize this type of safety threat as Sleeper Attack. To evaluate it, we construct a benchmark with 1,896 instances covering six real-world harmful outcomes, three attack strategies, and three agent state targets: session context, memory, and reusable skills. Experiments on seven strong open-source and closed-source LLMs show that state-of-the-art LLM agents remain vulnerable to Sleeper Attack, even when they achieve low attack success rates under a single-interaction baseline. Our code and data are available at https://anonymous.4open.science/r/skdvnfu23ihr9wdscnksf1asdffsaef.

0 Citations
0 Influential
10 Altmetric
50.0 Score
Original PDF

No Analysis Report Yet

This paper hasn't been analyzed by Gemini yet.

Log in to request an AI analysis.

댓글

댓글을 작성하려면 로그인하세요.

아직 댓글이 없습니다. 첫 번째 댓글을 남겨보세요!