A2SC: Adversarial Attacks on Subspace Clustering

Yikun Xu

doi:10.1145/3587097

A2SC: Adversarial Attacks on Subspace Clustering

2023-07-12

2

OA

AI

DOI：10.1145/3587097

Original request for help

Save

Abstract

En 中文

Many studies demonstrate that supervised learning techniques are vulnerable to adversarial examples. However, adversarial threats in unsupervised learning have not drawn sufficient scholarly attention. In this article, we formally address the unexplored adversarial attacks in the equally important unsupervised clustering field and propose the concept of the adversarial set and adversarial set attack for clustering. To illustrate the basic idea, we design a novel adversarial space-mapping attack algorithm to confuse subspace clustering, one of the mainstream branches of unsupervised clustering. It maps a sample into one wrong class by moving it towards the closest point on the linear subspace of the target class, that is, along the normal of the closest point. This simple single-step algorithm has the power to craft the adversarial set where the image samples can be wrongly clustered, even into the targeted labels. Empirical results on different image datasets verify the effectiveness and superiority of our algorithm. We further show that deep supervised learning algorithms (such as VGG and ResNet) are also vulnerable to our crafted adversarial set, which illustrates the good cross-task transferability of the adversarial set.

Keywords:

Subspace clustering

unsupervised learning

adversarial attack

black-box attack

adversarial set

A2SC: Adversarial Attacks on Subspace Clustering

Abstract

Journal

Organization