IDS-GAN: Stepping up Intrusion Detection Method using GAN Algorithm

Abstract

Many computer network threats cause the security aspect to become the most critical problem.  The intrusion detection system is a widely used practical security tool to prevent malicious traffic from penetrating networks and systems. To solve the issue, we construct a novel algorithm using Generative Adversarial Networks (GAN) to address the IDS security problem. In this paper, we propose an intrusion detection model using GAN by analyzing the extracted features of the network. To build our detection model, we collect the dataset, conduct pre-processing, train our model with several hyper-parameters to get the best accuracy, then test the model using the new data. Based on experimental results, the proposed model can produce a 0.00539 error rate and indicate a more accurate model to detect anomalies in the network traffic.