For too long, computer science has approached security in an attack-driven, ad hoc and reactionary manner with huge efforts devoted by human analysts In order to make meaningful progress, we need to shift our defensive approaches to be automated, intelligent and adversarial resilient Over the course of my Ph D , I have built security systems incorporating intelligent security techniques, and I have developed corresponding defenses and testing methodologies to guard against emerging attacks specifically adversarial to these newly-proposed techniques In this talk, I will first highlight two of these systems for mobile security, AppContext and WHYPER Second, I will show how we can generate adversarial inputs to test and further strengthen these systems I will conclude by discussing how, in the future, I want to develop AI-based attack-detection systems to enable a defense-driven security ecosystem

Wei Yang is a PhD student in University of Illinois at Urbana-Champaign. He is advised by Prof. Carl A. Gunter and Prof. Tao Xie. He is a member of Illinois Security Lab and Illinois Software Engineering Research Group. He received an M.S. in Computer Science from North Carolina State University in 2013, advised by Prof. Tao Xie, and a B.E. in Software Engineering from Shanghai Jiao Tong University in 2011, advised by Prof. Jianjun Zhao. He was a visiting student researcher in University of California, Berkeley in 2017, invited by Prof. Dawn Song.