A student from the Department of Computer Science holds a Master's Degree in Enhancing Intrusion detection in a cloud computing environment

Back

A student from the Department of Computer Science holds a Master's Degree in Enhancing Intrusion detection in a cloud computing environment

The student Shawq Malek Mohaibes received a master's degree from the Department of Computer Science at the University of Technology for her thesis titled "Suggesting the Blurry Logical Staphylococcus aurous to Enhance the Detection System in the Cloud Computing Environment" at the discussion hall in the annex building.
The discussion committee consisted of Dr. Abdel Karim Abdul-Hassan, chairman of the University of Technology / Computer Science Department, Dr. Haidar Kadhem Hamoud from Al Mustansiriya University, Faculty of Education, Computer Science Department, Dr. Alaa Kadhem Farhan. Members & Dr. Sakina Hassan Hashim from the Department of Computer Science / University of Technology supervisor.
The researcher showed that Cloudy computing is one of the most common technologies used in most enterprises because of its unique features such as availability, flexibility and integration. The Cloudy computing provides storage, resources and other services to customers. Adding that the open architecture and distributed cloud computing and services rendered it a desirable target for potential cyber attacks. The Intrusion Detection System (NIDS) is an important security mechanism that provides a defensive layer that monitors network traffic to detect suspicious activities or violate policies.

In this thesis, a system was proposed as a network sniffer for the traditional / cloud network; the proposal is based on both the Fuzzy C-Mean algorithm and the Back Propagation algorithm.
In the first stage, the clustered cluster algorithm is used to determine the abnormal traffic of the natural movement, where this algorithm is able to identify new attack types. In the second phase, non-nature traffic is classified as a specific type of attack or referred to as unknown in the case of natural traffic which is incorrectly classified as abnormal in the first stage. The reverse propagation algorithm is used as a classifier to determine the type of attack or signal as unknown.
The proposed system was evaluated using the KDD99 standard data set to increase the speed of the proposed system algorithm for character selection, which is the algorithm for obtaining information and used to determine the relevant characteristics of others. The obtaining results showed the efficiency and feasibility of the proposed system in detection of parasitism and type of parasitism. The proposed system met the criteria for assessing the performance of the intrusion detection system: detection accuracy, detection rate, false positive alarm rate for the first stage, and attack detection rate for the second stage. The detection rate of the proposed system is 99%, the detection rate is 100% and the false alarm rate is 1%. The attack detection rate (Dos) is 99%, the Probe detection rate is 98%, the attack detection rate (U2R) is 96% and the attack detection rate (R2L) is 98%. The system has been implemented in the case of BASIC.NET 2010.

Source : Uot Media Date :20/3/2017