Early Epidemic Detection Inference from Weak Signals

Motivated by zero-day exploits, we discuss the problem of detecting malware spread in communities. We consider a setting where the "signal" (detector at an individual node) is extremely noisy. By viewing the malware detection problem as hypothesis testing on a graph "” is there malware or not within the community "” we develop new inference algorithms (with asymptotic performance guarantees) to detect unknown malware. We also discuss practical implementations of these ideas.

Sanjay Shakkottai received his Ph.D. from the ECE Department at the University of Illinois at Urbana-Champaign in 2002. He is with the ECE Department at the University of Texas at Austin, where he is currently the Ashley H. Priddy Centennial Professor in Engineering, and the Director of the Wireless Networking and Communications Group (WNCG). He received the NSF CAREER award in 2004, and was elected as an IEEE Fellow in 2014. His current research interests include network architectures, algorithms and performance analysis for wireless networks, and learning and inference over social networks.