The intriguing phenomenon of adversarial examples has attracted significant attention in machine learning and what might be more surprising to the community is the existence of universal adversarial perturbations (UAPs), i.e. a single perturbation to fool the target DNN for most images. With the focus on UAP against deep classifiers, this survey summarizes the recent progress on universal adversarial attacks, discussing the challenges from both the attack and defense sides, as well as the reason for the existence of UAP. We aim to extend this work as a dynamic survey that will regularly update its content to follow new works regarding UAP or universal attack in a wide range of domains, such as image, audio, video, text, etc. Relevant updates will be discussed at: https://bit.ly/2SbQlLG. We welcome authors of future works in this field to contact us for including your new finding.
翻译:令人感兴趣的对抗性实例现象在机器学习中引起极大关注,对于社会来说,更令人惊讶的是存在普遍的对抗性干扰(UAPs),即为欺骗目标DNN而为大多数图像进行一次干扰。关于UAP对深层次分类者的关注,本调查总结了全球对抗性攻击的最新进展,讨论了攻击和防御双方的挑战以及UAP存在的原因。我们打算扩大这项工作,作为动态调查,定期更新其内容,以跟踪有关UAP或普遍攻击的新作品,如图像、音频、视频、文本等。 相关的最新情况将在以下网站讨论:https://bit.ly/2SbQlLG。 我们欢迎今后在这一领域工作的作者与我们联系,以了解你的新发现。