Skip to main content

Distinguished Seminar:  Using Unsupervised Big-Data Analytics to Detect Sleeper Cells Among Billions of Users

Date:March 28, 2016 
Talk Title:Using Unsupervised Big-Data Analytics to Detect Sleeper Cells Among Billions of Users
Speaker:Yinglian Xie, CEO and Founder, DataVisor
Time & Location:12:00pm - 1:00pm
DEC, CIC Building, Pittsburgh

Abstract

Today’s consumer-facing online services are measured by the size and growth of their user account base, as users are both contributors of content as well as a channel for monetization.  Despite being their backbone, these user accounts are also their “Achilles heel” — well-organized crime rings leverage compromised or fraudulent accounts to hide amongst billions of benign users, waging a variety of large-scale attacks.

 In this talk, I will present the anatomy of modern attacks and the sophisticated attack techniques that we have observed across a number of services, including social networking, gaming, financial, ecommerce and other vertical markets.  I will then discuss the new challenges we face to defend against these attacks in the billion user era.  Finally I’ll outline the directions pursued by DataVisor through unsupervised big data analytics to detect and mitigate large attack campaigns early, without prior knowledge of attack patterns. 

Speaker Bio

Yinglian Xie is the CEO and co-founder of DataVisor, a leading big-data fraud detection provider in identifying large attack campaigns before they conduct any damage.  She received her Ph.D. in Computer Science from CMU, and has been working in the area of Internet security and privacy for over 10 years.  Prior to founding DataVisor, Yinglian was a researcher at Microsoft Research Silicon Valley, where she successfully developed a series of new technologies in Microsoft products.  These include social graphing techniques for user authentication in Microsoft Hotmail and algorithms to detect fraudulent transactions for Xbox that saved the company millions of dollars per year.  She holds over 20 patents for her work and has been widely published in top conferences and served on the committees of many of them.  Yinglian’s work has helped improve the security of billions of online users.