Intelligent Detection of Distributed Denial-of-Service Attacks in Cloud Platforms Using the Osprey Optimized Dense-SEQNET Architecture

Cloud Computing platforms are one among the most commonly used internet-based applications. Adapting to cloud computing leads to reduced expenses for maintaining and managing internet applications. However, with its growing popularity, these platforms are prone to several attack types, including Denial Of Service (DOS), Distributed DoS and spoofing. Among these, DDoS is a widely recongnized intrusion attack on cloud platforms causing a downfall of services or denial of services. Hence, this paper focuses on developing an intelligent identification of DDoS attacks using a Deep Learning (DL) based classification model. To improve the raw data quality, data pre-processing techniques such as data normalization, visualization, and feature encoding are deployed, further enhancing the data classification process. To achieve this, a Dense Sequential Network (Dense-SeqNeT) is utilized which analyzes the data to detect anomalies and malicious DDoS attacks with real-time detection. Additionally, for attaining augmented classification, the Osprey Optimization Algorithm (OOA) technique is integrated with Dense-SeqNeT, which enables solving complex problems with rapid convergence speed. The proposed work is validated using PYTHON software, and the attained experimental results demonstrate that the developed model performs well with higher accuracy in DDoS detection and reduced execution time. Therefore, the developed system ensures accurate detection and evaluates its performance.