On the Matrix-Free Generation of Adversarial Perturbations for Black-Box Attacks

Authors: Hisaichi Shibata, Shouhei Hanaoka, Yukihiro Nomura, Naoto Hayashi, Osamu Abe
Published: 2020-02-18

Source: https://arxiv.org/abs/2002.07317

PDF: https://arxiv.org/pdf/2002.07317

AIにより推定されたラベル

計算効率 敵対的サンプル 敵対的攻撃検出

※ こちらのラベルはAIによって自動的に追加されました。そのため、正確でないことがあります。
詳細は文献データベースについてをご覧ください。

Abstract

In general, adversarial perturbations superimposed on inputs are realistic threats for a deep neural network (DNN). In this paper, we propose a practical generation method of such adversarial perturbation to be applied to black-box attacks that demand access to an input-output relationship only. Thus, the attackers generate such perturbation without invoking inner functions and/or accessing the inner states of a DNN. Unlike the earlier studies, the algorithm to generate the perturbation presented in this study requires much fewer query trials. Moreover, to show the effectiveness of the adversarial perturbation extracted, we experiment with a DNN for semantic segmentation. The result shows that the network is easily deceived with the perturbation generated than using uniformly distributed random noise with the same magnitude.