An Enhanced Intrusion Detection And Secure Mobile Cloud Computing System Using Automated Ensemble Machine Learning Classification

Abstract

Mobile Cloud Computing (MCC) is fastest growing technology era and has been presented as one of the most efficient techniques for hosting and delivering such mobile services over the internet. In this fast-growing world security and data privacy in such environment are the most challenging problem. In this scenario Machine Leaning (ML) brings an important role to detect all the attacks and providing a data privacy and confidentiality levels. In this paper, an enhanced intrusion detection and secure mobile cloud computing system using machine automated ensemble machine learning techniques is proposed. The proposed system uses an ensemble learning method for the attack detection by taking best solution from Naïve bayes, adaptive boost and part classifiers and the Training dataset Filtration Key Nearest Neighbour (TsF-KNN) classifier is used as automated data classification

to classifies the data file as confidential and non-confidential based on attributes. Then the symmetric encryption methods are used to assuring privacy and confidentiality levels for the data storage.  The results show that proposed system offer enhanced detection rate and improved data storage security and privacy compared to existing methods.