LLM統合ロボットシステムの信頼性向上:セキュリティと安全性の統合アプローチ
Enhancing Reliability in LLM-Integrated Robotic Systems: A Unified Approach to Security and Safety
LLMを組み込んだロボットにおいて、プロンプトインジェクション攻撃への耐性と動作安全性を同時に高める統合フレームワークを提案し、シミュレーションと実機で有効性を検証した。
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: Wenxiao Zhang, Xiangrui Kong, Conan Dewitt, Thomas Bräunl, Jin B. Hong
分類: cs.RO, cs.AI
原文アブストラクト
Integrating large language models (LLMs) into robotic systems has revolutionised embodied artificial intelligence, enabling advanced decision-making and adaptability. However, ensuring reliability, encompassing both security against adversarial attacks and safety in complex environments, remains a critical challenge. To address this, we propose a unified framework that mitigates prompt injection attacks while enforcing operational safety through robust validation mechanisms. Our approach combines prompt assembling, state management, and safety validation, evaluated using both performance and security metrics. Experiments show a 30.8% improvement under injection attacks and up to a 325% improvement in complex environment settings under adversarial conditions compared to baseline scenarios. This work bridges the gap between safety and security in LLM-based robotic systems, offering actionable insights for deploying reliable LLM-integrated mobile robots in real-world settings. The framework is open-sourced with simulation and physical deployment demos at https://llmeyesim.vercel.app/
