An Intrusion Detection System using Graph Neural Networks

Master Thesis (2025)
Author(s)

T. Hristov (TU Delft - Electrical Engineering, Mathematics and Computer Science)

Contributor(s)

G. Smaragdakis – Mentor (TU Delft - Cyber Security)

Harm Griffioen – Graduation committee member (TU Delft - Cyber Security)

M. Khosla – Graduation committee member (TU Delft - Multimedia Computing)

Emmanouil Leontaris – Graduation committee member (Fox-IT)

Faculty
Electrical Engineering, Mathematics and Computer Science
More Info
expand_more
Publication Year
2025
Language
English
Graduation Date
28-08-2025
Awarding Institution
Delft University of Technology
Programme
['Computer Science | Cyber Security']
Faculty
Electrical Engineering, Mathematics and Computer Science
Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Abstract

Cybersecurity attacks are increasingly sophisticated, while traditional, rule-based intrusion detectionsystems (IDS) remain prone to high false alert rates. This research explores temporal graph learning fornetwork intrusion detection, introducing a framework that combines temporal graph construction withGraph Attention Networks and recurrent modeling (GATv2 + LSTM). We evaluate on the LANL authentication logs and Zeek logs from the University of West Florida (UWF).

On LANL, our models (Try1/Try2) outperform state-of-the-art baselines for temporal link prediction,achieving high precision and robustness: Accuracy ≈ 0.994, F1 ≈ 0.993, AUC ≈ 0.993–0.998, AP ≈ 0.999.On Zeek data, edge prediction is sensitive to how malicious activity is distributed over time: a simple“Day" shuffling that preserves the temporal structure while also spreading the clusters of attack activity,yields large gains (e.g., Accuracy ≈ 0.969, AUC ≈ 0.996, F1 ≈ 0.959, AP ≈ 0.995), whereas random shufflingharms temporal dependencies and performance.

Extending to edge classification (benign vs. malicious) reveals a key limitation: despite high accuracy,AUC and AP remain low due to a tendency to label nearly all edges as benign under class imbalance andtemporal clustering, producing many false negatives. We test mitigation strategies (dropout, alternativeloss formulations with confidence weighting), which provide a small increase in stability but do notfully resolve the issue.

With our results, we find that the proposed temporal graph method is a strong fit for anomaly detectionvia edge prediction: robust across datasets, resilient to imbalance, and practically applicable. In contrast,edge classification currently lacks reliability for production without improved data balancing, graphconstruction, and training.

Files

MSc_Thesis.pdf
(pdf | 4.11 Mb)
License info not available