VLAGuard: ワイヤレスセンサネットワークにおける視覚言語行動ロボットの物理的注意ハイジャック評価・緩和フレームワーク
VLAGuard: A Framework for Evaluating and Mitigating Physical Attention Hijacking in Vision-Language-Action Robots within Wireless Sensor Networks
VLAロボットの注意機構を妨害する物理的攻撃を評価し、注意保護ファインチューニングにより攻撃耐性を大幅に向上させるフレームワークを提案した。
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: Dongfu Yin, Jinquan Zhang
分類: cs.RO, cs.AI
原文アブストラクト
Deploying Vision-Language-Action (VLA) robots as mobile edge nodes within wireless sensor networks (WSNs) requires robust protection against physical adversarial threats. We present VLAGuard, a framework to assess and mitigate a critical vulnerability: policy-critical action-to-vision attention hijacking. We first introduce a stress-test module, Visuomotor Attention-guided Semantic Attack (VASA), using printable patches to severely distract the robot's action-conditioned cross-attention. To counter this, we propose Attention-Protective Fine-Tuning (APFT), a defense that stabilizes spatiotemporal attention and enforces geometric consistency with zero inference overhead. Evaluations across simulated and physical WSN-assisted smart environments demonstrate significant robustness gains. APFT reduces the OpenVLA failure rate from 100.0% to 25.9% in LIBERO simulations. Furthermore, across 2,000 real-world trials, APFT improves the average success rate from 23.0% to 67.4% under severe patch attacks. This highlights that protecting attention pathways is important for improving the robustness of VLA-driven edge nodes in sensor networks.
