Emad Alsuwat (Ph.D., University of South Carolina, 2019) is an assistant professor of Computer Science in the College of Computers and Information Technology at Taif University. He received a bachelor’s degree with first class honors in computer science from Taif University in 2008 and a Master of Science degree with first class honors in computer science and engineering from the department of computer science and engineering at the University of South Carolina in 2014. Emad Alsuwat is a certified cybersecurity trainer since May 2014 as he joined the National Training Standard for Information Systems Security (INFOSEC) Professionals, CNSS 4011 during his graduate work at the University of South Carolina. He Also received a graduate certificate in cybersecurity studies from the department of computer science and engineering at the University of South Carolina in 2018. In January 2020 he joined the faculty at the college of computers and information technology at Taif University. Emad’s research interests are in the fields of cybersecurity, machine learning and adversarial machine learning. His research interests are in cybersecurity and machine learning, namely probabilistic graphical models. His first research result, which is known as “Alsuwat’s link strength measure,” is a novel mathematical technique that is useful to not only quantify the strength of links of causal models but also analyze the security of such causal models. Indeed, the proposed link strength measure plays a crucial role in identifying vulnerable network structures and the ease of corrupting the Bayesian models, and thus it is useful for increasing the robustness of probabilistic graphical models. Most of his later research has been in the area of secure machine learning, a.k.a adversarial machine learning. His theoretical and methodological contributions include results on measuring the uncertainty of links of causal models, an algorithm for learning the structure of Bayesian networks from data, theoretical frameworks to classify cyber-attacks, namely data poisoning attacks, against Bayesian networks, a theoretical framework to classify long duration cyber-attacks on causal models, algorithms for measuring the resilience of Bayesian network structure learning algorithms against traditional and long duration cyber-attacks, algorithms for detecting adversarial attacks in the context of Bayesian networks, novel algorithms for data dependencies preserving shuffle, and a probabilistic graphical model framework to explicitly detect the presence of concept drift using latent variables.
For complete information, check out my CV.