Enhanced Deep Learning Approaches for Robust Darknet Traffic Classification

The classification of darknet traffic remains a pivotal task in modern cybersecurity efforts, necessitating advanced analytical techniques to address malicious activities pre-emptively. This study introduces and compares the efficacy of several deep learning models for classifying darknet traffic, including a Feedforward Neural Network (FFNN), Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM) network, and a novel deep learning model designed to enhance classification performance. Utilizing the CIC-Darknet2020 dataset, we implement a comprehensive evaluation using accuracy, precision, recall, and F1 score metrics. The results reveal that the proposed model surpasses traditional architectures, significantly improving classification accuracy and reliability, thereby contributing valuable insights to cybersecurity.