日本フィジカルAI新聞

世界のフィジカルAIを、日本語で。

敵対攻撃arXiv:1903.05157

道路上の黒線で自動運転AIを誤作動させる物理的敵対攻撃

Simple Physical Adversarial Examples against End-to-End Autonomous Driving Models

シェア:XThreadsFacebookLINEはてブBluesky

道路に黒い線を描くだけで、深層学習ベースの自動運転モデルを誤動作させる物理的に実現可能な攻撃をシミュレーション上で初めて実証した。

著者: Adith Boloor, Xin He, Christopher Gill, Yevgeniy Vorobeychik, Xuan Zhang

分類: cs.RO, cs.LG, stat.ML

原文アブストラクト

Recent advances in machine learning, especially techniques such as deep neural networks, are promoting a range of high-stakes applications, including autonomous driving, which often relies on deep learning for perception. While deep learning for perception has been shown to be vulnerable to a host of subtle adversarial manipulations of images, end-to-end demonstrations of successful attacks, which manipulate the physical environment and result in physical consequences, are scarce. Moreover, attacks typically involve carefully constructed adversarial examples at the level of pixels. We demonstrate the first end-to-end attacks on autonomous driving in simulation, using simple physically realizable attacks: the painting of black lines on the road. These attacks target deep neural network models for end-to-end autonomous driving control. A systematic investigation shows that such attacks are surprisingly easy to engineer, and we describe scenarios (e.g., right turns) in which they are highly effective, and others that are less vulnerable (e.g., driving straight). Further, we use network deconvolution to demonstrate that the attacks succeed by inducing activation patterns similar to entirely different scenarios used in training.

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

MINISFORUM(ミニPC)

MINISFORUM(ミニPC)の公式広告バナーMINISFORUM公式ストアを見る ↗
PR本紙発行元 EmplifAI