動的ウォーターマーキングと行動条件付き潜在ダイナミクスによる安全な視覚ベース制御
Dynamic Watermarking and Action-Conditioned Latent Dynamics for Secure Vision-Based Controllers
視覚ベース制御へのリプレイ攻撃を検出するため、制御入力に秘密のガウスウォーターマークを付加し、画像から学習した潜在空間で応答を予測して不一致を検出する適応的フレームワークを提案。強化学習でウォーターマーク強度を調整し、検出性と制御歪みのバランスを取る。
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: Aditya Parameshwaran, Navid Aftabi, Abhishek Hanchate, Satish T. S. Bukkapatnam, Dan Li, Yue Wang
分類: cs.RO, cs.CR, eess.SY
原文アブストラクト
Replay attacks are difficult to detect in vision-based control systems because previously recorded observations can remain plausible while the physical system follows a different trajectory. This paper develops an adaptive dynamic-watermarking framework for detecting replay attacks against vision-based controllers. A private Gaussian watermark is added to the nominal control input, and a control input-conditioned latent dynamics network (LDN) predicts the corresponding evolution in a compact latent space learned from image observations. Attack evidence is obtained from the discrepancy between the predicted latent response and the latent representation of the received image observation. A reinforcement learning policy adjusts the watermark covariance using the latent state and detector confidence, thereby balancing attack detectability, watermark energy, and control distortion. A Lagrangian penalty on task-specific safety costs is included during training to limit the adverse effect of the excitation. The framework is evaluated on a vision-guided UR5 manipulation task in which the robot reaches a target while avoiding a moving human arm under nominal and replay-attacked observations.