Noise Robust One-Class Intrusion Detection on Dynamic Graphs
This work addresses robustness in intrusion detection for network security, but it appears incremental as it builds on an existing method with specific modifications.
The study tackled the problem of network intrusion detection on dynamic graphs by introducing a probabilistic TGN-SVDD model to enhance robustness against noisy data, resulting in significant improvements in detection performance compared to the baseline, especially at higher noise levels.
In the domain of network intrusion detection, robustness against contaminated and noisy data inputs remains a critical challenge. This study introduces a probabilistic version of the Temporal Graph Network Support Vector Data Description (TGN-SVDD) model, designed to enhance detection accuracy in the presence of input noise. By predicting parameters of a Gaussian distribution for each network event, our model is able to naturally address noisy adversarials and improve robustness compared to a baseline model. Our experiments on a modified CIC-IDS2017 data set with synthetic noise demonstrate significant improvements in detection performance compared to the baseline TGN-SVDD model, especially as noise levels increase.