Automating Botnet Detection with Graph Neural Networks

TL;DR

This paper introduces a novel approach using graph neural networks to automatically detect botnets by capturing their hierarchical and decentralized communication structures, outperforming traditional methods.

Contribution

The paper develops tailored GNN architectures for botnet detection, demonstrating their effectiveness over existing non-learning techniques on synthesized and real network data.

Findings

GNNs outperform traditional detection methods.

Deeper GNNs improve detection of complex botnet structures.

Synthesized datasets enable effective training of GNN models.

Abstract

Botnets are now a major source for many network attacks, such as DDoS attacks and spam. However, most traditional detection methods heavily rely on heuristically designed multi-stage detection criteria. In this paper, we consider the neural network design challenges of using modern deep learning techniques to learn policies for botnet detection automatically. To generate training data, we synthesize botnet connections with different underlying communication patterns overlaid on large-scale real networks as datasets. To capture the important hierarchical structure of centralized botnets and the fast-mixing structure for decentralized botnets, we tailor graph neural networks (GNN) to detect the properties of these structures. Experimental results show that GNNs are better able to capture botnet structure than previous non-learning methods when trained with appropriate data, and that deeper GNNs are crucial for learning difficult botnet topologies. We believe our data and studies can be useful for both the network security and graph learning communities.