学習ベース制御器の敵対的攻撃に対するロバスト性
Robustness to Adversarial Attacks in Learning-Enabled Controllers
サイバーフィジカルシステムの学習ベース制御器に対する状態摂動型の敵対的攻撃を定式化し、制御器と環境をブラックボックスとして扱えるシールドベースの二段階防御手法を提案、F16航空機の航法制御やヒューマノイドロボットの運動制御で有効性を示した論文。
著者: Zikang Xiong, Joe Eappen, He Zhu, Suresh Jagannathan
分類: cs.LG, cs.AI, cs.RO, stat.ML
原文アブストラクト
Learning-enabled controllers used in cyber-physical systems (CPS) are known to be susceptible to adversarial attacks. Such attacks manifest as perturbations to the states generated by the controller's environment in response to its actions. We consider state perturbations that encompass a wide variety of adversarial attacks and describe an attack scheme for discovering adversarial states. To be useful, these attacks need to be natural, yielding states in which the controller can be reasonably expected to generate a meaningful response. We consider shield-based defenses as a means to improve controller robustness in the face of such perturbations. Our defense strategy allows us to treat the controller and environment as black-boxes with unknown dynamics. We provide a two-stage approach to construct this defense and show its effectiveness through a range of experiments on realistic continuous control domains such as the navigation control-loop of an F16 aircraft and the motion control system of humanoid robots.
