Amora: Black-box Adversarial Morphing Attack

Run Wang, Felix Juefei-Xu, Qing Guo, Yihao Huang, Xiaofei Xie, Lei Ma, Yang Liu

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

2 被引用数 (Scopus)

抄録

Nowadays, digital facial content manipulation has become ubiquitous and realistic with the success of generative adversarial networks (GANs), making face recognition (FR) systems suffer from unprecedented security concerns. In this paper, we investigate and introduce a new type of adversarial attack to evade FR systems by manipulating facial content, called adversarial morphing attack (a.k.a. Amora). In contrast to adversarial noise attack that perturbs pixel intensity values by adding human-imperceptible noise, our proposed adversarial morphing attack works at the semantic level that perturbs pixels spatially in a coherent manner. To tackle the black-box attack problem, we devise a simple yet effective joint dictionary learning pipeline to obtain a proprietary optical flow field for each attack. Our extensive evaluation on two popular FR systems demonstrates the effectiveness of our adversarial morphing attack at various levels of morphing intensity with smiling facial expression manipulations. Both open-set and closed-set experimental results indicate that a novel black-box adversarial attack based on local deformation is possible, and is vastly different from additive noise attacks. The findings of this work potentially pave a new research direction towards a more thorough understanding and investigation of image-based adversarial attacks and defenses.

本文言語英語
ホスト出版物のタイトルMM 2020 - Proceedings of the 28th ACM International Conference on Multimedia
出版社Association for Computing Machinery, Inc
ページ1376-1385
ページ数10
ISBN(電子版)9781450379885
DOI
出版ステータス出版済み - 10 12 2020
イベント28th ACM International Conference on Multimedia, MM 2020 - Virtual, Online, 米国
継続期間: 10 12 202010 16 2020

出版物シリーズ

名前MM 2020 - Proceedings of the 28th ACM International Conference on Multimedia

会議

会議28th ACM International Conference on Multimedia, MM 2020
国/地域米国
CityVirtual, Online
Period10/12/2010/16/20

All Science Journal Classification (ASJC) codes

  • ソフトウェア
  • コンピュータ グラフィックスおよびコンピュータ支援設計
  • 人間とコンピュータの相互作用

フィンガープリント

「Amora: Black-box Adversarial Morphing Attack」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