事故ではない：ヒューマノイドロボットにおける安全フィルタの不備の悪用
Not an Accident: Exploiting Safety Filter Inadequacy in Humanoid Robots
ヒューマノイドの安全フィルタはパラメータ設定が不適切だと保証が崩れることを示し、通常のユーザ操作だけで衝突を誘発する目標挿入攻撃と自動探索ツールSIRENを提案した論文。
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: Tiffany Bao, Shangtao Li, Yifan Sun, Mengwen He, Bowei Li, Alden Wang, Changliu Liu, Ruoyu Wang, David Brumley
分類: cs.CR, cs.RO
原文アブストラクト
As humanoid robots move from research laboratories toward deployment in human-centered environments such as homes, hospitals, and warehouses, safe operation around nearby people and objects becomes a fundamental requirement. Safety filters have emerged as a promising technique to address this challenge by providing mathematical guarantees that generated control actions do not result in collisions. This paper shows that these guarantees hold only when the safety parameters are configured correctly. However, correct parameter configurations are task- and environment-specific, and no general method exists to determine them across diverse deployments. As a result, safety filters shipped with humanoid robots can fail after deployment in specific scenarios. We show that attackers can exploit these failures through only normal user interactions without any additional privileges or capabilities. To demonstrate this risk, we present goal insertion attacks and develop SIREN, an automated tool that identifies vulnerable inserting goals for a given task and environment. Experimental results show that SIREN identifies attacks in all vulnerable scenarios in the SPARK dataset. Compared with a baseline approach, SIREN discovers three times as many attacks. We also show that SIREN is able to generate attacks against a real humanoid and cause it to collide while executing tasks. These results demonstrate that current safety filters introduce exploitable vulnerabilities that can cause safety violations, which reveals that existing safety mechanisms can themselves become a source of safety risk for humanoid robots.