Improving the Efficiency of DDoS Attack Detection Using Artificial Intelligence

This review article discusses how artificial intelligence enhances the detection of Distributed Denial-of-Service (DDoS) attacks in modern high-speed networks. Traditional security mechanisms are increasingly ineffective against sophisticated, encrypted, and low-rate attack techniques. The paper explains why classical detection approaches are no longer sufficient and examines how machine learning and deep learning techniques improve detection accuracy, reduce false positives, and adapt to evolving attack patterns. Popular methods such as Random Forest, Long Short-Term Memory (LSTM), and Graph Neural Networks (GNN) are reviewed, along with current challenges and future research directions in this field.