5th International Conference on Inventive Research in Computing Applications, ICIRCA 2023, Coimbatore, India, 3 - 05 August 2023, pp.668-673
Attacks known as Distributed Denial-of-Service (DDoS) are rising as a result of recent, dramatic increase in demand for Internet access. When the amount and characteristics of network traffic, which may include harmful DDoS contents, expand dramatically, traditional basic algorithms using machine learning for classifying DDoS attacks frequently fail because it cannot automatically extract high-value characteristics. In order to effectively identify and classify DDoS attacks, a hybrid technique called DFNN-SAE-DCGAN that combines three deep learning-based models is suggested. The Deep Feed-Forward Neural Network (DFNN) and Stacked Auto encoder offers an efficient method for extracting features that identifies the most pertinent feature sets without the assistance of a person. To avoid the operational overhead and presumption associated with processing massive set of features with distortion and redundant characteristic values, the Deep Convolutional Generative Adversarial Networks (DCGAN) component of the proposed model classifies the attacks into various DDoS attack types using the restricted and minimized characteristic sets generated by the DFNN-SAE as inputs. The experimental results show a very high and resilient accuracy rate and an F1-score of 98.5%, which is higher than the performance of many similar approaches. These results were acquired by thorough and extensive trials on various performance aspects on the CICDDoS2019 dataset. This demonstrates that the suggested methodology may be utilized to defend against the increasing amount of DDoS attacks.