IOT@CyLab Webinar

  • Remote Access - Zoom Webinar
  • Virtual Presentations - ET

Swarun Kumar, Associate Professor, Department of Electrical and Computer Engineering, Carnegie Mellon University
      — Wireless Anomaly Detection in Industrial IoT

This talk presents a wireless systems approach to improve anomaly detection in the industrial IoT context. Rather than view the broadcast nature and limited capabilities of wireless IoT devices as a negative, our objective is to leverage their wireless physical layer to improve security. Specifically, we devise a solution that uses software radio sniffers in an industrial IoT context to sense and locate adversarial radios based on their perceived wireless channel state information. We further show how active evasive strategies used by these adversaries counter-intuitively improves our system's ability to locate them. We present preliminary results and a report of ongoing work at the Mill-19 industrial IoT testbed.

Swarun Kumar is an Associate Professor at CMU where heads the laboratory for emerging wireless technologies (WiTech lab). He designs and builds novel systems to enable faster wireless networks and new services. Swarun is a recipient of the NSF CAREER Award, the ACM SIGBED Early Career Researcher award, the Google Faculty Research award and several best paper awards. Swarun received the George Sprowls Award for the best Ph.D thesis in Computer Science at MIT and the President of India Gold Medal at IIT Madras

EUNSUK KANG , Assistant Professor, Institute for Software Research, Carnegie Mellon University
     Systematic Attack Recovery in Industrial Control Systems

Industrial control systems (ICS) provide many critical functions that our society depends on, including water treatment, power generation and distribution, and public transportation. Responding to a security incident in ICS involves recognizing when an attack has taken place, identifying parts of the system that might have been compromised, and reversing the effect of attacker actions over those compromised parts. These tasks are typically performed by human operators who are in charge of the ICS operation; carrying these out manually, however, can be challenging due to the deliberate and stealthy nature of attacks. In this talk, I will introduce some of our ongoing work in developing a semi-automated framework for detecting, diagnosing, and responding to attacks within ICS. In particular, I will focus on a model-based approach for monitoring system behaviors to detect potential attacks, and discuss our approach in the context of a water treatment plant.

Eunsuk Kang is an Assistant Professor in the Institute for Software Research, School of Computer Science at Carnegie Mellon University. His research interests include software engineering and formal methods, with applications to system safety and security. He is interested in leveraging formal modeling techniques, design methodologies, and automated verification to construct secure and reliable cyber-physical systems (CPS), and he has applied his work to a diverse range of systems, including intelligent vehicles, unmanned aerial vehicles (UAVs), medical devices, water treatment plants, and mobile applications. 

Zoom Participation. See announcement.

For More Information, Please Contact: