A Combined Decision for Secure Cloud Computing Based on Machine Learning and Past Information

Abstract

Cloud computing has been presented as one of the most efficient techniques for hosting and delivering services over the internet. However, even with its wide areas of application, cloud security is still a major concern of cloud computing. In order to protect the communication in such environment, many secure systems have been proposed and most of them are based on attack signatures. These systems are often not very efficient for detecting all the types of attacks. Recently, machine learning technique has been proposed. This means that if the training set does not include enough examples in a particular class, the decision may not be accurate. In this paper, we propose a new firewall scheme named Enhanced Intrusion Detection and Classification (EIDC) system for secure cloud computing environment. EIDC detects and classifies the received traffic packets using a new combination technique called most frequent decision where the nodes' 11In this document we will use the words 'node' and 'user' interchangeably.past decisions are combined with the current decision of the machine learning algorithm to estimate the final attack category classification. This strategy increases the learning performance and the system accuracy. To generate our results, a public available dataset UNSW-NB-15 is used. Our results show that EICD improves the anomalies detection by 24% compared to complex tree.