One Pixel Attack for Fooling Deep Neural Networks

研究成果: ジャーナルへの寄稿学術誌査読

1288 被引用数 (Scopus)

抄録

Recent research has revealed that the output of deep neural networks (DNNs) can be easily altered by adding relatively small perturbations to the input vector. In this paper, we analyze an attack in an extremely limited scenario where only one pixel can be modified. For that we propose a novel method for generating one-pixel adversarial perturbations based on differential evolution (DE). It requires less adversarial information (a black-box attack) and can fool more types of networks due to the inherent features of DE. The results show that 67.97% of the natural images in Kaggle CIFAR-10 test dataset and 16.04% of the ImageNet (ILSVRC 2012) test images can be perturbed to at least one target class by modifying just one pixel with 74.03% and 22.91% confidence on average. We also show the same vulnerability on the original CIFAR-10 dataset. Thus, the proposed attack explores a different take on adversarial machine learning in an extreme limited scenario, showing that current DNNs are also vulnerable to such low dimension attacks. Besides, we also illustrate an important application of DE (or broadly speaking, evolutionary computation) in the domain of adversarial machine learning: creating tools that can effectively generate low-cost adversarial attacks against neural networks for evaluating robustness.

本文言語英語
論文番号8601309
ページ(範囲)828-841
ページ数14
ジャーナルIEEE Transactions on Evolutionary Computation
23
5
DOI
出版ステータス出版済み - 10月 2019

!!!All Science Journal Classification (ASJC) codes

  • ソフトウェア
  • 理論的コンピュータサイエンス
  • 計算理論と計算数学

フィンガープリント

「One Pixel Attack for Fooling Deep Neural Networks」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル