跳到主要导航 跳到搜索 跳到主要内容

Amora: Black-box Adversarial Morphing Attack

  • Run Wang
  • , Felix Juefei-Xu
  • , Qing Guo*
  • , Yihao Huang
  • , Xiaofei Xie
  • , Lei Ma
  • , Yang Liu
  • *此作品的通讯作者
  • Nanyang Technol Univ
  • Alibaba Grp
  • East China Normal Univ
  • Kyushu Univ
  • Zhejiang Univ

科研成果: 会议稿件 › 会议文章 › 同行评审

26 引用 (Scopus)

摘要

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.
源语言英语
页1376-1385
页数10
DOI
出版状态已出版 - 12 10月 2020
活动28th ACM International Conference on Multimedia (MM) - ELECTR NETWORK, ELECTR NETWORK
期限: 12 10月 2020 → 16 10月 2020

会议

会议28th ACM International Conference on Multimedia (MM)
市ELECTR NETWORK
时期12/10/20 → 16/10/20

基金资助

This research was supported in part by Singapore National Cybersecurity R&D Program No. NRF2018NCR-NCR005-0001, National Satellite of Excellence in Trustworthy Software System No. NRF2018NCR-NSOE003-0001, NRF Investigatorship No. NRFI06-2020-0022. It was also supported by JSPS KAKENHI Grant No. 20H04168, 19K24348, 19H04086, and JST-Mirai Program Grant No. JPMJMI18BB, Japan. We gratefully acknowledge the support of NVIDIA AI Tech Center (NVAITC) to our research.

关键词

  • Black-box adversarial attack
  • morphing
  • face recognition

收录

  • CPCI-S

学术指纹

探究 'Amora: Black-box Adversarial Morphing Attack' 的科研主题。它们共同构成独一无二的学术指纹。

引用此