One-Class Intrusion Detection with Dynamic Graphs
By: Aleksei Liuliakov , Alexander Schulz , Luca Hermes and more
Potential Business Impact:
Finds hidden computer network dangers.
With the growing digitalization all over the globe, the relevance of network security becomes increasingly important. Machine learning-based intrusion detection constitutes a promising approach for improving security, but it bears several challenges. These include the requirement to detect novel and unseen network events, as well as specific data properties, such as events over time together with the inherent graph structure of network communication. In this work, we propose a novel intrusion detection method, TGN-SVDD, which builds upon modern dynamic graph modelling and deep anomaly detection. We demonstrate its superiority over several baselines for realistic intrusion detection data and suggest a more challenging variant of the latter.
Similar Papers
Noise Robust One-Class Intrusion Detection on Dynamic Graphs
Machine Learning (CS)
Finds computer attacks even with messy data.
An intrusion detection system in internet of things using grasshopper optimization algorithm and machine learning algorithms
Optimization and Control
Protects smart devices from hackers.
Intrusion Detection System Using Deep Learning for Network Security
Cryptography and Security
Finds bad computer stuff to keep networks safe.