ReasonBreak: 自動運転向け推論対応VLAモデルの脆弱性探査
ReasonBreak: Probing Vulnerabilities in Reasoning-Enabled Vision-Language-Action Models for Autonomous Driving
自動運転用の推論機能付き視覚言語行動(VLA)モデルが、現実的な入力摂動に対して脆弱であることを示し、最大89%の推論攻撃成功率と72%の軌道操作成功率を報告した。
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: Mohammadreza Teymoorianfard, Jean-Philippe Monteuuis, Jonathan Petit, Amir Houmansadr
分類: cs.CR, cs.LG, cs.RO
原文アブストラクト
Vision-Language-Action (VLA) models with integrated reasoning have been proposed for end-to-end autonomous driving, assuming a tight coupling between reasoning and trajectory generation. However, the robustness of such systems under realistic input perturbations remains largely unexplored. We show that these models are highly vulnerable to realistic input perturbations, achieving up to 89% attack success rate (ASR) on reasoning and up to 72% on trajectory manipulation in closed-loop simulation, leading to increased collision rates and degraded safety metrics. Using NVIDIA's recent Alpamayo models as representative industry-developed VLAs, we conduct the first systematic black-box study of reasoning-enabled VLA models under realistic textual input corruptions, evaluating their impact on reasoning and driving behavior. We introduce a reasoning-aware evaluation framework capturing both semantic and structural aspects of reasoning, along with safety-centric measures. We also introduce a benchmark for evaluating attacks and defenses on reasoning-trajectory interactions in autonomous driving. Our results highlight the need for rigorous evaluation and improved defenses to ensure the safety of reasoning-enabled VLA systems in autonomous driving.
関連論文
- 霧の中で迷う:センサー摂動が運転VLAの推論の脆弱性を露呈する自動運転/VLA/ロバスト性
