Convolutional Neural Networks and Mixture of Experts for Intrusion Detection in 5G Networks and beyond

Loukas Ilias^*George DoukasVangelis LamprouChristos NtanosDimitris Askounis

• National Technical University of Athens, Athens, Greece

The advent of 6G/NextG networks comes along with a series of benefits, including extreme capacity, reliability, and efficiency. 6G/NextG networks must be equipped with advanced Artificial Intelligence algorithms, in order to evade new security threats. Existing studies on the intrusion detection task are based on deep neural networks consisting of static components, which are not conditional on the input. This limits their representation power and efficiency. To resolve these issues, we present the first study integrating Mixture of Experts (MoE) for identifying malicious traffic. Specifically, we use network traffic data and convert the 1D array of features into a 2D matrix. Next, we pass this matrix through convolutional neural network (CNN) layers followed by batch normalization and max pooling layers. After this, a sparsely gated MoE layer is used. This layer consists of a set of experts (dense layers) and a router, where the router assigns weights to the output of each expert. Sparsity is achieved by choosing the most relevant experts of the total ones. Finally, we perform a series of ablation experiments to prove the effectiveness of our proposed model. Experiments are conducted on the 5G-NIDD dataset, a network intrusion detection dataset generated from a real 5G test network, and the NANCY dataset, which includes cyberattacks on O-RAN 5G Testbed Dataset. Results show that our introduced approach reaches Accuracy up to 99.96% and 79.59% in terms of the 5G-NIDD and NANCY datasets respectively. Findings also show that our proposed model achieves multiple advantages over state-of-the-art approaches.