An Automated Framework to Uncover Malicious Traffic for University Campus Network

Abstract

The paper presents an automated framework that stimulates the campus network traffic to detect and prevent the malicious network activities and visualization of the logs using customized reporting dashboards on a real-time basis over the university campus network. The framework combines open source tools to give a realistic analysis of the network traffic using the detection and prevention engine. The detected malicious events by the engine are then processed by the elastic cluster for visualization of the threats. The framework measures the detection of the events and generates alerts, which shows that the engine performs better with elastic cluster which works on NoSQL for real-time incidence reporting. Once the system gets trained, the framework automatically blocks the attack as per the severity threat for further propagation in the future, over the network. This helps to secure and increase the performance of the campus networks using open source libraries and reduces the financial burdens due to commercial threat detection and prevention systems.