对离群点检测方法植入后门：一种新型攻击方法
Backdooring Outlier Detection Methods: A Novel Attack Approach
AI总结：
针对现有后门攻击只影响闭集分类、难以破坏开集离群点检测的问题，本文提出 BATOD，通过两类触发器混淆闭集与开集边界，并在多个真实数据集及防御条件下验证其攻击效果。
摘要：
后门攻击已有若干研究，但这些工作主要聚焦于分类器的闭集性能（即分类）。这使得分类器的开集性能所面临的威胁仍未得到解决；在文献中，这种开集性能被称为离群点检测。可靠的离群点检测对于在自动驾驶和医学图像分析等关键现实应用中部署分类器至关重要。首先，我们表明现有后门攻击难以影响分类器的开集性能，因为它们是专门为混淆闭集内部的决策边界而设计的。相比之下，一种有效的针对离群点检测的后门攻击需要混淆闭集与开集之间的决策边界。受此启发，本研究提出了 BATOD，这是一种面向离群点检测任务的新型后门攻击（Backdoor Attack targeting the Outlier Detection task）。具体而言，我们设计了两类触发器，用于将内点样本转变为离群点，以及将离群点转变为内点。我们使用多个真实世界数据集评估 BATOD，并证明无论在应用防御之前还是之后，与以往攻击相比，BATOD 在降低分类器开集性能方面都具有更强的能力。
英文摘要：
There have been several efforts in backdoor attacks, but these have primarily focused on the closed-set performance of classifiers (i.e., classification). This has left a gap in addressing the threat to classifiers' open-set performance, referred to as outlier detection in the literature. Reliable outlier detection is crucial for deploying classifiers in critical real-world applications such as autonomous driving and medical image analysis. First, we show that existing backdoor attacks fall short in affecting the open-set performance of classifiers, as they have been specifically designed to confuse intra-closed-set decision boundaries. In contrast, an effective backdoor attack for outlier detection needs to confuse the decision boundary between the closed and open sets. Motivated by this, in this study, we propose BATOD, a novel Backdoor Attack targeting the Outlier Detection task. Specifically, we design two categories of triggers to shift inlier samples to outliers and vice versa. We evaluate BATOD using various real-world datasets and demonstrate its superior ability to degrade the open-set performance of classifiers compared to previous attacks, both before and after applying defenses.
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。
