Practical Attacks Against Graph-based Clustering

TL;DR

This paper introduces and evaluates two novel adversarial attacks on graph-based clustering detection systems, highlighting vulnerabilities and potential defenses in the context of security and machine learning.

Contribution

The paper presents new attack methods against graph clustering and discusses practical defense strategies, addressing a gap in adversarial machine learning research.

Findings

Less informed attackers can evade detection at low cost

Some practical defenses can mitigate attack effectiveness

Graph clustering vulnerabilities are significant in security applications

Abstract

Graph modeling allows numerous security problems to be tackled in a general way, however, little work has been done to understand their ability to withstand adversarial attacks. We design and evaluate two novel graph attacks against a state-of-the-art network-level, graph-based detection system. Our work highlights areas in adversarial machine learning that have not yet been addressed, specifically: graph-based clustering techniques, and a global feature space where realistic attackers without perfect knowledge must be accounted for (by the defenders) in order to be practical. Even though less informed attackers can evade graph clustering with low cost, we show that some practical defenses are possible.