Detection of DDOS Attack using Deep Learning Model in Cloud Storage Application

In recent years, distributed denial of service (DDoS) attacks pose a serious threat to network security. How to detect and defend against DDoS attacks is currently a hot topic in both industry and academia. There have been a lot of methodologies and tools devised to detect DDoS attacks and reduce the damage they cause. Still, most of the methods cannot simultaneously achieve efficient detection with a small number of false alarms. In this case, deep learning techniques are appropriate and effective algorithm to categorize both normal and attacked information. Hence, a novel a feature selection-whale optimization algorithm-deep neural network (FS-WOA-DNN) method is proposed in this research article to mitigate DDoS attack in effective manner. Initially, pre-processing step is carried out for the input dataset where min-max normalization technique is applied to replace all the input in a specified range. Later on, that normalized information is fed into the proposed FS-WOA to select the optimal set of features for ease the classification process. Those selected features are subjected to deep neural network classifier to categorize normal and attacked data. Further to enhance the security of proposed model, the normal data are secure with the help of homomorphic encryption and are securely stored in the cloud. The proposed algorithm will be simulated using the MATLAB tool and tested experimentally that shows 95.35% accuracy in detecting DDoS attack.

Automated summary

DDoS attacks have become a serious threat to network security in recent years, leading to a focus on detecting and defending against them. Deep learning techniques have been identified as an effective algorithm for classifying normal and attacked information. A novel FS-WOA-DNN method has been proposed with a 95.35% accuracy in detecting DDoS attacks.