DeepDefend: A comprehensive framework for DDoS attack detection and prevention in cloud computing

Abstract

DeepDefend is an advanced framework for real-time detection and prevention of DDoS attacks in cloud environments. It employs deep learning techniques, notably CNN-LSTM-Transformer networks, to predict network traffic entropy and detect potential attacks. The framework uses a genetic algorithm for optimal feature selection, enhancing the efficacy of the AutoCNN-DT model in distinguishing between normal and attack traffic. Tested on the CIDDS-001 traffic dataset, DeepDefend demonstrates high accuracy in entropy forecasting and rapid, precise detection of DDoS attacks. This integrated approach combines time series analysis, genetic algorithms, and deep learning, offering a robust solution to protect cloud computing infrastructure against DDoS threats.

Keywords

• DDoS attacks
• Cloud computing systems
• Entropy forecasting
• Deep learning models
• CNN
• Genetic algorithm