ロボティクスにおける視覚言語行動モデルに対する部分観測敵対的パッチ攻撃
Partially Observable Adversarial Patch Attacks on Vision-Language-Action Models in Robotics
視覚言語行動(VLA)モデルに対する敵対的パッチ攻撃を、全軌跡ではなく短いプレフィックスのみを利用する部分観測設定で行う手法を提案。注意マップで重要領域を特定し、パッチを最適化して知覚と制御の両方を妨害する。
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: Xiaofei Wang, Mingliang Han, Tianyu Hao, Yi Yang, Yun-Bo Zhao, Keke Tang
分類: cs.RO
原文アブストラクト
Vision-language-action (VLA) models are gaining attention in robotics, yet their robustness to adversarial attacks remains largely unexplored. Existing work shows that adversarial patches can mislead VLA-based robots but assumes full access to the entire execution trajectory, an unrealistic requirement in practice. We address this limitation by formulating a partially observable threat model, where the adversary can exploit only a short prefix of the trajectory to generate a fixed patch applied to all subsequent frames. Under this setting, we propose a two-phase framework. First, we localize the patch using the model's attention maps to identify visually critical regions that correspond to the full instruction. Then, we optimize the patch to disrupt the semantic grounding of target objects and increase the curvature of action trajectories, thereby compounding failures in both perception and control. Extensive experiments in simulation and real-world robotic environments show that our method sustains adversarial effects under partial observability, inducing long-horizon disruptions and significantly reducing task success rates.
関連論文
- 見えざる脅威:拡散モデルによる視覚言語行動モデルへの無制限ロボット攻撃VLA/敵対的攻撃
