Exploratory data analysis toward cloud intrusion detection
Date
2019-05-31
Authors
Mashkanova, Aigerim
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
Cloud computing is one of the fastest growing areas of information technologies. The growth rate and the prosperity of this industry have led to important security concerns. For the Masters Project, the ISOT Cloud Intrusion Dataset (ISOT-CID) was utilized to explore cloud anomaly detection using different machine learning tech- niques. The dataset involves terabytes of data that contain various attacks and normal activities gathered in a real cloud environment. Three different supervised machine learning techniques were applied to analyze anomalous behavior in network traffic. The implemented experiments demonstrated that the Logistic Regression classifier achieves the lowest false negative rate while the Naive Bayes has achieves the highest accuracy rate.
Description
Keywords
cloud computing, intrusion detection, data analysis