Abstract Distributed cloud computing and its reliance on internet connectivity have more challenges. They offer a great deal of flexibility, and these assets are accessible through the Internet using popular requirements, forms, and protocols for networking according to the cloud service-providing organizations. Attacks like distributed denial of service are a few of the most frequent attacks that severely harm the cloud and lower its performance. Internal attacks cannot be identified using established methods of detection such as firewalls. The attackers frequently modify their skill strategies, because of the increasing amount of data created and stored, conventional detection techniques are inefficient in identifying novel DDoS attacks. Radial Basis Function (RBF) networks are a type of artificial neural network commonly used for function approximation, pattern recognition, and classification tasks. While they have been used in various domains, they are not typically used directly within convolutional neural networks (CNNs) for DDoS (Distributed Denial of Service) detection. This paper presents a hybrid model of Radial Basis Function (RBF) and LSTM networks-based approach for DDoS attack detection and mitigation, aiming to enhance the overall security of cloud computing infrastructures. Our proposed method is evaluated on benchmark dataset CICDDoS2019, demonstrating its effectiveness in identifying DDoS attacks and mitigating their impact on cloud systems.
Alan : Mühendislik
Dergi Türü : Uluslararası
Benzer Makaleler | Yazar | # |
---|
Makale | Yazar | # |
---|