• home
• current students
• graduate
• events

Presenter: Onyekachi Nwamuo
Supervisor:

Date: Tue, January 7, 2020
Time: 12:00:00 - 13:00:00
Place: EOW 430

ABSTRACT

Although cloud network flows are similar to conventional network flows in many ways, there are some major differences in their statistical characteristics. However, due to the lack of adequate public datasets, the proponents of many existing cloud intrusion detection systems (IDS) have relied on the DARPA dataset which was obtained by simulating a conventional network environment.  In the current thesis, we show empirically that the DARPA dataset by failing to meet important statistical characteristics of real world cloud traffic data center is inadequate for evaluating cloud IDS. We analyze, as alternative, a new public dataset collected through a cooperation between our lab and a non-profit cloud service provider, which contains benign data and a wide variety of attack data.

More so, we present a new Hypervisor-based cloud IDS using instance-oriented feature model and supervised machine learning techniques. We achieve this using three different classifiers: Logistic Regression (LR), Random Forest (RF), and Support Vector Machine (SVM) algorithms.