視覚言語行動モデルへの普遍的敵対攻撃:ロボット操作における脆弱性の悪用
Exploiting Vulnerabilities: Universal Adversarial Attacks on Vision-Language-Action Models in Robotics
ロボットの視界に置くだけでタスク成功率を大幅に下げる最適化された表面テクスチャを持つ球体を提案し、VLAモデルの軌道計画・実行・制御を同時に妨害する攻撃を実機とシミュレーションで検証した。
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: Songhua Yang, Ziyu Liu, Yuanwei Liu, Xuetao Li, Xuanye Fei, He Huang, Zheng Wang, Miao Li
分類: cs.RO, cs.CR, cs.CV
原文アブストラクト
Recently, Vision-Language-Action (VLA) models have revolutionized robotic manipulation by seamlessly integrating visual perception, language understanding, and action generation in an end-to-end learning framework. However, since these models are designed to interact directly with the physical world and humans, their security is critical, and even small vulnerabilities can lead to catastrophic failures. In this work, we propose the Universal Adversarial Object, a sphere with optimized surface texture that significantly degrades task success rates when placed within the robot's field of view. Specifically, our approach introduces a multi-level attack framework that jointly disrupts trajectory planning, task execution, and action control. We validate our method in both simulated and real-world robotic settings. Experimental results demonstrate that the adversarial object reduces the average task success rates by 31.2%-39.9% for two representative VLA models (Pi0 and RDT), with success rates dropping to near zero in complex scenarios. Index Terms--Vision-Language-Action models, adversarial attack, robotic security, universal adversarial object
