Enhancing Network Analysis Through Computational Intelligence in GANs

Literature Review

Artificial intelligence fields such as computer vision, natural language processing, and now network analysis have found great use for Generative Adversarial Networks (GANs). The utilization of GANs in the integration of computational intelligence presents innovative methods for comprehending, simulating, and enhancing the intricacies present in interconnected systems. Researchers examine the current research contributions, approaches, and applications that demonstrate how GANs can improve network analysis in the present overview of the literature.

When used to identify anomalies in network data, GANs have demonstrated encouraging outcomes. (Akcora et al. 2019) developed a GAN-based technique that creates normal traffic profiles and identifies deviations from them in order to identify anomalies in network traffic. Comparably, a GAN-based system to facilitate identifying anomalies in network intrusions was introduced by Wu et al. 2020, and it performed competitively when compared to conventional techniques. To ensure effective network management and optimize resource allocation, network traffic patterns must be forecasted. A GAN-based model for network traffic prediction was presented by (Wang et al. 2018). It made use of GANs' generative capabilities to identify temporal relationships and variations in traffic data. Their strategy proved to be more accurate than traditional predicting techniques.