Detecting malicious data using deep learning

Abstract

Traffic classification is a fundamental task in network anomaly detection and intrusion prevention systems. By accurately identifying the types of traffic traversing a network, security professionals can detect and mitigate various threats, such as malicious attacks, unauthorized access, and network congestion. Traditional methods of traffic classification often rely on handcrafted features, which can be time-consuming and prone to errors.

In this research, we present a novel approach that leverages artificial intelligence to streamline and improve the process of traffic classification. Specifically, we propose a convolutional neural network (CNN) model that directly processes raw traffic data as images. This eliminates the need for manual feature extraction, which can be a laborious and error-prone task.

Our CNN model is designed to capture the underlying patterns and characteristics of network traffic. By processing raw traffic data as images, the model can learn to identify distinctive features that differentiate various traffic types.