Empirical evaluation on robustness of deep convolutional neural networks activation functions against adversarial perturbation

研究成果: Chapter in Book/Report/Conference proceedingConference contribution

1 被引用数 (Scopus)

抄録

Recent research has shown that deep convolutional neural networks (DCNN) are vulnerable to several different types of attacks while the reasons of such vulnerability are still under investigation. For instance, the adversarial perturbations can conduct a slight change on a natural image to make the target DCNN make the wrong recognition, while the reasons that DCNN is sensitive to such small modification are divergent from one research to another. In this paper, we evaluate the robustness of two commonly used activation functions of DCNN, namely the sigmoid and ReLu, against the recently proposed low-dimensional one-pixel attack. We show that the choosing of activation functions can be an important factor that influences the robustness of DCNN. The results show that comparing with sigmoid, the ReLu non-linearity is more vulnerable which allows the low dimensional one-pixel attack exploit much higher success rate and confidence of launching the attack. The results give insights on designing new activation functions to enhance the security of DCNN.

本文言語英語
ホスト出版物のタイトルProceedings - 2018 6th International Symposium on Computing and Networking Workshops, CANDARW 2018
出版社Institute of Electrical and Electronics Engineers Inc.
ページ223-227
ページ数5
ISBN(電子版)9781538691847
DOI
出版ステータス出版済み - 12 26 2018
イベント6th International Symposium on Computing and Networking Workshops, CANDARW 2018 - Takayama, 日本
継続期間: 11 27 201811 30 2018

出版物シリーズ

名前Proceedings - 2018 6th International Symposium on Computing and Networking Workshops, CANDARW 2018

会議

会議6th International Symposium on Computing and Networking Workshops, CANDARW 2018
国/地域日本
CityTakayama
Period11/27/1811/30/18

All Science Journal Classification (ASJC) codes

  • コンピュータ ネットワークおよび通信
  • ハードウェアとアーキテクチャ
  • 統計学、確率および不確実性
  • コンピュータ サイエンスの応用

フィンガープリント

「Empirical evaluation on robustness of deep convolutional neural networks activation functions against adversarial perturbation」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