Practical Attacks Against Graph-based Clustering
This addresses security vulnerabilities in graph-based clustering for network-level detection, which is an incremental contribution to adversarial machine learning.
The paper tackles the problem of adversarial attacks on graph-based clustering systems, specifically targeting a state-of-the-art network-level detection system, and shows that practical defenses are possible even against less informed attackers.
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.