Cloud computing leads an organization for data storage, sharing, processing, and other services. It was subjected to several challenges insecurity due to the presence of regular attacks. These security challenges are worsened due to the presence of various attack environment. The conventional techniques adopted in cloud security are Intrusion Detection System (IDS). However, the IDS system requires an efficient security model for improving security in the cloud. In this paper, proposed a Game Theory Cloud Security Deep Neural Network (GT-CSDNN). The proposed model incorporates the game theory model with the incorporation of defense and attacker strategies. Also, the developed game theory model is implemented in the DNN network for classification of attack and normal data. The performance of the proposed GT-CSDNN is evaluated with CICIDS - 2017 dataset. The collected data is normalized and optimal points about normal and attack data are evaluated based on the Improved whale algorithm (IWA). The proposed GT-CSDNN is implemented in the networking layer of the model. The simulation results stated that the proposed GT-CSDNN exhibits improved performance compared with existing technique in terms of accuracy, precision, F-Score, AUC, FPR, and Detection rate.
Digital Object Identifier (DOI)
Varun, P. and Ashokkumar, K.
"Intrusion Detection System in Cloud Security using Deep Convolutional Network,"
Applied Mathematics & Information Sciences: Vol. 16:
4, Article 11.
Available at: https://digitalcommons.aaru.edu.jo/amis/vol16/iss4/11