Survey and Analysis of DDOS Attack Detection by Hybrid Deep Learning Methodologies

This study provides an extensive overview and analysis of hybrid deep learning approaches for Distributed Denial of Service (DDoS) attack detection. The efficiency of classic DDoS detection technologies is declining in the face of growing cyber threats. In order to improve detection efficiency and accuracy, this work investigates the integration of deep learning with conventional machine learning techniques. In-depth literature reviews, model comparisons, and statistical analyses of performance indicators for distinct DDoS attack types are all part of the study. The research evaluates the performance of hybrid models, such as HTM-LSTM, LSTM, RNN, and others, using real-world datasets and measures the results in terms of accuracy, ROC, recall, precision, and F-score. The findings show that hybrid deep learning models greatly enhance DDoS attack detection, providing reliable and flexible responses to address the constantly changing cyberthreat environment.