University of Virginia
January 15, 2021
11:00am - 12:00pm
Donald Bren Hall 6011
When Machine Learning Meets Security: Challenges and Opportunities
The modern computing platforms are pervasive, interconnected, scalable, and data-intensive. From smartphones to IoT devices, and to cloud servers, these computing platforms bringing more functionality and convenience for people; however, these new platforms also expose users to security and privacy risks. The massive amount of data in these computing platforms provides great opportunities for data-driven security solutions, however, there are still many challenges to make such solutions robust, scalable, and privacy-friendly. For example, how to build a reliable anomaly detection model when only a handful of labeled data is available? How to protect user privacy while running machine learning models? In this talk, I’ll present my example projects in the thrusts of (1) AI for information security and privacy, as well as (2) design and implement secure and privacy-preserving machine learning systems. In the first thrust, I will introduce our work on transfer-learning-based vulnerability detection across different platforms with a limited amount of labeled data, and explain our scalable anomaly detection frameworks that are deployed in Facebook and Microsoft Azure. In the second thrust, I will introduce our efforts in designing secure and privacy-preserving machine learning algorithms by system and security co-design. I’ll use voice-controlled devices as an example to show how we identify new security and privacy threats on the devices powered by machine learning.
Yuan Tian is an Assistant Professor of Computer Science at University of Virginia. Before joining UVA, she obtained her Ph.D from Carnegie Mellon University in 2017, and interned at Microsoft Research, Facebook, and Samsung Research. Her research interests involve security and privacy and its interactions with computer systems, machine learning, and human-computer interaction. Her current research focuses on developing new technologies for protecting user privacy, particularly in the areas of mobile systems and the Internet of Things. Her work has generated real-world impact as countermeasures and design changes have been integrated into platforms (such as Android, Chrome, SmartThings, Azure, and iOS), and also impacted the security recommendations of standard organizations such as Internet Engineering Task Force (IETF) and World Wide Web Consortium (W3C). She is a recipient of NSF CAREER award 2020, NSF CRII award 2019, Amazon AI Faculty Fellowship 2019, CSAW Best Security Paper Award 2019, Rising Stars in EECS 2016 and Black Hat Future Female Leaders in Cyber Security 2015. Her research has appeared in top-tier venues in Security, Machine Learning, and System. Her projects have been covered by media outlets such as IEEE Spectrum, Forbes, Fortune, Wired, and Telegraph.