Constantinos Kolias - Considerations for EM-based Anomaly Detection Systems in Real-Life Environments
March 18 @ 10:30 am - 11:30 am MDT
Constantinos Kolias, Assistant Professor
University of Idaho
“Considerations for EM-based Anomaly Detection Systems in Real-Life Environments”
The penetration of digital devices to critical infrastructures has exposed these networks to a wide range of attacks. Stuxnet is the first malware designed specifically to infect devices residing in critical environments. However, due to the resource-constrained nature of such devices, the well-known protection mechanisms designed for high-end computer platforms cannot be supported. Naturally, a large body of research seeks unconventional ways of protection. The analysis of Electromagnetic (EM) patterns emitted by the microcontrollers of such devices is one such solution for detecting malicious code injections. These approaches are based on the strong correlation of EM emanations with the instructions that are executed in the CPU. In this way, intrusion/anomaly detection in a totally external way becomes possible even for these minimalist devices. Nevertheless, the majority of the research efforts are conducted in controlled laboratory environments, neglecting the practical challenges that arise in real-life deployments. In this lecture, we will explore the main challenges and possible solutions for deploying EM-based anomaly detection systems in real-life networks.
Constantinos Kolias joined the Computer Science Department at the University of Idaho in 2018. Before that he served as a Research Assistant Professor under the supervision of Angelos Stavrou, in the CS Department at George Mason University. He received his doctorate in 2014 from the University of the Aegean under the supervision of Georgios Kambourakis. His main research interest revolves around security and privacy for the Internet of Things and critical infrastructures. He is also active in the design of intelligent Intrusion Detection Systems (IDS) with a special interest in privacy preserving distributed IDS. Other areas of interest include mobile and wireless communications security, and privacy enchasing techniques for the Internet. In 2015 he created and released the first wireless dataset specifically intended for research in wireless security, namely the AWID dataset. Today AWID has been downloaded and used as a benchmark by hundreds of organizations and universities.