Abstract: The proliferation and sophistication of malware (malicious software) activities -- as well as their growing capacity to do serious harm -- requires constant vigilance and upgrading. We aim to develop anomaly detection solutions that can identify suspicious network and system activities. Specifically, we focus on identifying characteristic human-user behaviors (namely application-level user inputs via keyboard and mouse), developing protocols for analyzing inputs and system calls, and preventing forgeries and attacks by malware. The talk will also describe our recent work on privacy-preserving data leak detection.
Speaker: Danfeng (Daphne) Yao is an assistant professor of computer science at Virginia Tech. She received her Ph.D. degree from Brown University in 2007 and her research is on network and system security, malware detection, and applied cryptography. She was awarded NSF CAREER award for her human-behavior inspired malware detection work, and has three Best Paper Awards on her malware detection work. She was named Outstanding New Assistant Professor by Virginia Tech College of Engineering in 2012. She has 45+ peer-reviewed publications.