后门学习:调查 (Backdoor Learning: A Survey)

from arxiv, 12 pages. A curated list of backdoor learning resources in this paper is presented in the Github Repo (https://github.com/THUYimingLi/backdoor-learning-resources). We will try our best to continuously maintain the repo

Backdoor attack intends to embed hidden backdoor into deep neural networks (DNNs), such that the attacked model performs well on benign samples, whereas its prediction will be maliciously changed if the hidden backdoor is activated by the attacker-defined trigger. This threat could happen when the training process is not fully controlled, such as training on third-party datasets or adopting third-party models, which poses a new and realistic threat. Although backdoor learning is an emerging and rapidly growing research area, its systematic review, however, remains blank. In this paper, we present the first comprehensive survey of this realm. We summarize and categorize existing backdoor attacks and defenses based on their characteristics, and provide a unified framework for analyzing poisoning-based backdoor attacks. Besides, we also analyze the relation between backdoor attacks and relevant fields ($i.e.,$ adversarial attacks and data poisoning), and summarize widely adopted benchmark datasets. Finally, we briefly outline certain future research directions relying upon reviewed works. A curated list of backdoor-related resources is also available at \url{https://github.com/THUYimingLi/backdoor-learning-resources}.

翻译：后门攻击意图将隐藏的后门攻击嵌入深层神经网络(DNNs),这样,被攻击的模式在良性样本上表现良好,而如果攻击者定义的触发器触发隐藏的后门攻击,其预测将恶意改变。这种威胁可能发生在培训过程没有完全控制的情况下,例如第三方数据集培训或采用第三方模型,这构成了新的现实威胁。虽然后门学习是一个新兴的和迅速增长的研究领域,但其系统审查仍然空白。在本文中,我们介绍该领域的第一次全面调查。我们根据现有后门攻击和防御的特点对现有的后门攻击和防御进行总结和分类,并为分析基于中毒的后门攻击提供一个统一的框架。此外,我们还分析后门攻击和相关领域之间的关系(即,美元对抗性攻击和数据中毒),并总结广泛采用的基准数据集。最后,我们简要概述了依赖审查的工程的某些未来研究方向。在\url{https://github.com/THUYIMINL/bormainresslegress)。