Dr. M. Radwan Shushane
Unable to retrieve contact information.
Ph.D. University of Louisiana at Lafayette
Dr. Mohamed Radwan Shushane has earned a B.S. degree in Mathematics from the Faculty of Tunis, Tunisia in 1998, and an M.S. degree in applied computer science from CSU in 2003. Inspired by his professors and mentors at CSU, he decided to continue his studies in computer science and keep growing as a student of the sciences, which led to his publishing several research papers in computer security, writing a dissertation on software security, and earning a Ph.D. degree in computer science from the University of Louisiana at Lafayette in 2008. Appreciative of the great learning experiences that he has had as an M.S. student at CSU, he became an Assistant Professor of Computer Science at CSU's TSYS School of Computer Science in the Fall of 2008.
Dr. Shushane is interested in all aspects of software engineering, pattern recognition, and the theory of computation, with particular emphasis on their applications to computer security. His current research explores ways in which these bodies of knowledge could be leveraged to construct, evaluate, and deploy automated tools for attributing malware (i.e., malicious software) instances to known malware-generating machines, such as polymorphic engines and virus generation toolkits. The ultimate goal of the research is to provide the computer security community with a fast decision support procedure that would quickly (and with no need for slow, error-prone human intervention) determine whether a never-before-seen piece of code could possibly have been generated by a program that is known to have produced malware in the past. This decision support procedure hopes to reduce the dependence that current malware detectors have on the resource-intensive process of maintaining, regularly updating, and searching databases of millions of malware signatures (typically one signature per malware instance). This decision support procedure uses just one small signature, or a set of properties about a malware-generating machine, to efficiently detect the potentially vast numbers of malware instances that the malware-generating machine can generate..