Survey on Detection of Application Layer DDoSAttack Using Machine Learning Tool Kits

Abstract

The relentless threat posed by Distributed Denial-of-Service (DDoS) attacks, particularly those aimed at the application layer, underscores the urgent necessity for advanced detection techniques. This paper introduces an innovative methodology that harnesses the power of deep learning to accurately identify such attacks. Our hybrid model, combining Convolutional Neural Networks (CNN) and Recurrent Neural Networks (RNN), is meticulously crafted to analyze network traffic data with precision. CNNs excel in extracting spatial features, unveiling underlying attack patterns inherent in the data. Conversely, RNNs adeptly handle sequential information, capturing temporal dependencies and recognizing anomalous traffic behaviour over time. By synergizing these complementary strengths, our deep learning model strives to achieve superior accuracy in distinguishing between normal traffic and malicious DDoS attempts. This research significantly contributes to bolstering application-layer security, providing robust defences against the constantly evolving landscape of DDoS threats. The adoption of our methodology promises to enhance the resilience of network infrastructures and safeguard critical services against disruptive cyber-attacks, ultimately ensuring the uninterrupted availability and reliability of online platforms and applications.