日本フィジカルAI新聞

世界のフィジカルAIを、日本語で。

強化学習arXiv:2206.07188

検出とノイズ除去による深層強化学習の観測攻撃への防御

Defending Observation Attacks in Deep Reinforcement Learning via Detection and Denoising

シェア:XThreadsFacebookLINEはてブBluesky

連続制御タスクにおける観測空間への敵対的攻撃に対し、攻撃を検出してノイズ除去する防御手法を提案し、攻撃下でのデータ収集を不要にした。

著者: Zikang Xiong, Joe Eappen, He Zhu, Suresh Jagannathan

分類: cs.LG, cs.RO, cs.SY, eess.SY

原文アブストラクト

Neural network policies trained using Deep Reinforcement Learning (DRL) are well-known to be susceptible to adversarial attacks. In this paper, we consider attacks manifesting as perturbations in the observation space managed by the external environment. These attacks have been shown to downgrade policy performance significantly. We focus our attention on well-trained deterministic and stochastic neural network policies in the context of continuous control benchmarks subject to four well-studied observation space adversarial attacks. To defend against these attacks, we propose a novel defense strategy using a detect-and-denoise schema. Unlike previous adversarial training approaches that sample data in adversarial scenarios, our solution does not require sampling data in an environment under attack, thereby greatly reducing risk during training. Detailed experimental results show that our technique is comparable with state-of-the-art adversarial training approaches.

関連論文

  1. 1Boston Dynamics、車輪付きAtlasの研究試作機を紹介研究・技術
  2. 2newmoとKDDIが資本業務提携 2028年に堺市で自動運転タクシー商用化目指す提携・買収
  3. 3GXOとApptronik、Apolloの物流現場試験を拡大 最大1,000台の展開を構想量産・展開
  4. 4NVIDIA、CoRLでGR00T 2とIsaac Lab 3.0を発表新製品・発表
  5. 5UC BerkeleyとNVIDIAの研究者、AIエージェントでロボット制御コードを仮想環境で改善研究・技術

PR・アフィリエイト広告

OZ GAMING(GPU搭載BTOゲーミングPC)

OZ GAMING(GPU搭載BTOゲーミングPC)の公式広告バナーOZ GAMINGで完成品PCを見る ↗
PR本紙発行元 EmplifAI