One-Class Intrusion Detection with Dynamic Graphs

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Liuliakov, Aleksei, Schulz, Alexander, Hermes, Luca, Hammer, Barbara
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866916905337487360
author Liuliakov, Aleksei
Schulz, Alexander
Hermes, Luca
Hammer, Barbara
author_facet Liuliakov, Aleksei
Schulz, Alexander
Hermes, Luca
Hammer, Barbara
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2508_12885
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle One-Class Intrusion Detection with Dynamic Graphs
Liuliakov, Aleksei
Schulz, Alexander
Hermes, Luca
Hammer, Barbara
Machine Learning
Artificial Intelligence
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.
title One-Class Intrusion Detection with Dynamic Graphs
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2508.12885