基盤モデル搭載身体化エージェントのセキュリティ:攻撃面、攻撃、防御、評価
Security of Foundation-Model-Powered Embodied Agents: Attack Surfaces, Attacks, Defenses, and Evaluation
基盤モデルを使う身体化エージェントのセキュリティを、信頼境界を中心に整理したサーベイ論文。システムを5層・12の攻撃面に分け、58件の攻撃と61件の防御を分析し、研究の偏りを明らかにした。
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: Jiawei Liu, Jiacheng Guo, Tian Zhang, Yiwei Xu, Juan Wang, Jinlin Fan, Bowen Xiao
分類: cs.RO
原文アブストラクト
Foundation models are increasingly used for perception, reasoning, planning, and action generation in embodied agents, creating security risks that can propagate from digital inputs to physical behavior. Existing surveys often organize threats by mechanisms such as jailbreaks, prompt injection, backdoors, poisoning, or adversarial examples, but these categories do not consistently identify where an adversary first enters the embodied control loop. We present a trust-boundary-centric survey of foundation-model-powered embodied-agent security. Using a first-compromised-trust-boundary principle, we separate attack surface from attack mechanism and organize the system into five layers and twelve attack surfaces spanning the model supply chain, user instructions, context and memory, physical semantic environments, multimodal perception, world state, internal reasoning, task planning, action interfaces, middleware, multi-agent communication, and execution control. Based on 58 attack records and 61 defense records collected through August 15, 2026, we analyze representative attacks, cross-layer propagation, defense placement, and evaluation practices. Our quantitative analysis shows that attack research is concentrated on multimodal perception and action interfaces, while defenses are especially concentrated on action-level and runtime protection. Context and long-term memory, middleware and networking, world-state integrity, and multi-agent trust remain comparatively underexplored. We conclude with open challenges in state provenance, compositional defenses, long-horizon attack propagation, physical realizability, Byzantine multi-robot behavior, and unified closed-loop evaluation.