Network Security Research Group
Network security is a very important factor in today's information-driven world. According to Internet World Stats and miniwatts marketing group as of June 2014, there were more than 3 billion online users throughout the world and this number keeps growing. With the number growing, the potential risks for corporate and individual users are also growing. We now use the internet for more than just information gathering. According to eMarketer global online retail sales have topped $1trillion and will continue to grow $1,321.4 billion by 2017 ("Trends & Data - Internet Retailer," n.d.). A market this size will require extra precautions from Network Attacks and Intrusions.
Network Security Research group focuses on using machine learning techniques on Network Intrusion-detection systems as well as Mobile Phone security and biometric security. Specialized Machine techniques are Artificial Neural Networks (ANN), Support Vector Machines (SVM), and Decision Tree methods.
Background and Motivation
The "Network Security" Research group is a part of the Faculty of Information Technologies and Engineering at the International Burch University. The group member structure changed over the time. The current members of the group are three professors, three Ph.D. candidates, and two Master students. The group focuses on Network Security, Intrusion-detection, Biometric Security, Mobile Security using Machine Learning and Data Mining techniques.
Network Security research at the International Burch University was initiated in 2009 when prof. Abdulhamit Subasi (former head of the group) came to the University and started to work as Dean of Faculty. During this period, members of the group did a number of scientific researches. With a wide range of researches being a member of the group and close cooperation with IT Center (University IT office in charge of University network and computers), Network security group has the unique advantage of gathering production data from university networks for research and test purposes.
Assis. Prof. Dr. Nejdet Dogru (contact person)
Assis. Prof. Dr. Jasmin Kevrić
Zerina Mašetić, PhD Candidate
Samed Jukic, PhD Candidate
Adnan Hodžić, PhD Candidate
Accepted/Published Articles in SCI indexed Journals (Peer-review)Jasmin Kevric, Samed Jukic, and Abdulhamit SUbasi; An effective combining classifier approach using tree algorithms for network intrusion detection, Neural Computing and Applications, Jun. 2016
E. Kremic, A. Subasi, Performance of Random Forest and SVM in Face Recognition (Accepted International Arab Journal of Information Technology)
Accepted/Published Articles in non-SCI indexed Journals (Peer-review)Z. Masetic, A. Subasi, J. Azemovic; Malicious Web Sites Detection using C4.5 Decision Tree, Southeast Europe Journal of Soft Computing, Vol. 5, No. 1, Mar. 2016
Samed Jukic, Jasmin Azemovic, Dino Keco, Jasmin Kevric; COMPARISON OF MACHINE LEARNING TECHNIQUES IN SPAM E-MAIL CLASSIFICATION, Southeast Europe Journal of Soft Computing, Vol. 4, No. 1, Mar. 2015
International conferences:Adnan Hodzic, Jasmin Kevric, Ahmed Karadag; COMPARISON OF MACHINE LEARNING TECHNIQUES IN PHISHING WEBSITE CLASSIFICATION, International Conference on Economic and Social Studies (ICESoS), Sarajevo, BiH, Apr. 2016, Vol. 3, Page 249 - 256
Kemal Hajdarevic, Vahidin Dzaltur; Internal penetration testing of Bring Your Own Device (BYOD) for preventing vulnerabilities exploitation, XXV International Conference on Information, Communication and Automation Technologies (ICAT), 2015
Kemal Hajdarevic, Vahidin Dzaltur; An approach to digital evidence collection for successful forensic application: An investigation of blackmail case, 38th International Convention on Information and Communication Technology, Electronics and Microelectronics (MIPRO), 2015
E. Kremic, A. Subasi, and K. Hajdarevic, Face Recognition Implementation for Client Server Mobile Application using PCA, Proceedings of the ITI 2012, 34th Int. Conf.on Information Technology Interfaces, June 25-28, 2012, Cavtat, Croatia.
COMPLETED PROJECTS1. Project
Comparison of Machine Learning Methods for Robust Intrusion Detection
Supported by: International Burch University