プロンプトがロボットを操る:マルチエージェントロボットシステムにおけるプロンプトインジェクション攻撃
When Prompts Control Robots: Prompt Injection Attacks in Multi-Agent Robotic Systems
LLMベースのマルチエージェントロボットシステムに対するプロンプトインジェクション攻撃を体系的に評価し、攻撃がタスク遂行を妨げつつ敵対的行動を誘発し、エージェント間で伝播することを示した。
詳しい要約
1. どんなもの?
2. 先行研究と比べてどこがすごい?
3. 技術・手法の肝は?
4. どうやって有効だと検証した?
5. 議論はある?
6. 次に読むべき論文は?
※ AIが要旨から生成した要約です。正確性は原文をご確認ください。
著者: Neha Nagaraja, Amisha Bagari, Hayretdin Bahsi
分類: cs.RO, cs.AI, cs.CR, cs.MA
原文アブストラクト
Large language models are increasingly integrated into autonomous robotic systems for task planning and control, but this integration exposes them to prompt injection attacks that can lead to unsafe decisions and physical harm. Multi-agent settings increase the risks through cross-agent contamination and broader attack surfaces. In this paper, we evaluate prompt injection attacks against an LLM-based multi-agent robotic system, considering both direct injections into task instructions and indirect injections through perception modules. In our experiments across varying attack-goal complexities and injection strategies in both single-agent and multi-agent settings, we show that prompt injection can induce adversarial actions while reducing task completion. We find that attacks can propagate from one agent to others through shared prompt structures, with impacts varying depending on prompt composition and the targeted agent. We further analyze how architectural changes affect LLM queries and, consequently, the attack success. To the best of our knowledge, this is the first study that systematically investigates prompt injection attacks in a multi-agent LLM-based robotic system.
