arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2103.01498cs.LGcs.CV
收藏

通用对抗攻击综述

A Survey On Universal Adversarial Attack

Korea Advanced Institute of Science and Technology(韩国科学技术院);University of Electronic Science and Technology of China(电子科技大学);Sichuan University(四川大学)

Chaoning Zhang, Philipp Benz, Chenguo Lin, Adil Karjauv, Jing Wu, In So Kweon

摘要:

对抗性示例的有趣现象在机器学习中引起了极大的关注,而更令人惊讶的是普遍对抗性扰动(universal adversarial perturbations,UAP)的存在,即对于大多数图像,一个扰动就可以欺骗目标DNN。本文以针对深度分类器的UAP为研究重点,综述了通用对抗攻击的最新进展,讨论了攻击和防御双方面临的挑战,以及UAP存在的原因。我们的目标是将这项工作扩展为动态调查,定期更新其内容,以跟踪有关UAP或广泛领域(如图像,音频,视频,文本等)的通用攻击的新作品。https://bit.ly/2SbQlLG我们欢迎该领域未来作品的作者与我们联系,以纳入您的新发现。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑