Yevgeniy Vorobeychik, assistant professor of computer science and computer engineering, has received a National Science Foundation Faculty Early Career Development grant.
The five-year, $518,000 grant – Adversarial Artificial Intelligence for Social Good – begins March 1, 2017.
Vorobeychik combines approaches from artificial intelligence and game theory to solve important social problems, for instance, police and fire departments using limited resources to protect an entire city. His work in developing secure machine learning algorithms results in more effective detection of fraud and cyber attacks.
“While AI has a long history in playing adversarial games, such as chess and poker, the approaches have not been appropriate for many real-world situations. The goal of the proposed research is to develop a general framework for adversarial AI that is far broader in scope and applicability, building on insights from game theory, AI planning, and cybersecurity,” Vorobeychik said.
A key modeling insight of the proposed research is that attacks across a broad array of settings can be modeled as planning problems so that robust algorithms can be viewed as intercepting and restricting attack plans.
“A challenge is the adversarial nature of many domains in which social, economic, and political interests may try to manipulate intelligent systems into making costly mistakes,” Vorobeychik said.
Vorobeychik will develop new foundational techniques for scalable plan interdiction under uncertainty, building off the framework of Stackelberg games (leader-follower games). Scalable algorithms will be developed for multi-stage interdiction problems. The research will make novel modeling and algorithmic contributions in multi-defender and multi-attacker interdiction games.
“In the more applied arena, the research will make significant intellectual contributions in applying advances in adversarial AI to model problems such as privacy-preserving data sharing, access control and audit policies, and vaccine design,” Vorobeychik said.
Vorobeychik’s research has been supported by Sandia National Laboratories, the Office of Naval Research, the U.S. Army, and the National Science Foundation.
He received a Ph.D. in computer science and engineering in 2008 from the University of Michigan. He joined the School of Engineering faculty in 2013.