Wednesday Feb 27, 12pm-1pm, Pettit 102A
AI-infused Security: Robust Defense by Bridging Theory and Practice
Advisor: Prof. Polo Chau
While Artificial Intelligence (AI) has tremendous potential as a defense against real-world cybersecurity threats, understanding the capabilities and robustness of AI remains a fundamental challenge, especially in adversarial environments. In this talk, I address two interrelated problems that are essential to deployment of AI in security settings. (1) Designing robust and efficient machine learning algorithms with strong theoretical guarantees for large-scale, distributed, and noisy data. Specifically, I will present a boosting-based learning approach that solves an open problem in distributed learning. Based on this boosting algorithm and its insightful connection to game theory, I then propose a novel online framework that balances between risk and reward in adversarial scenarios. (2) Discovering real-world vulnerabilities of deep neural networks in and countermeasures to mitigate threats. I will present ShapeShifter, the first targeted physical adversarial attack that fools state-of-the-art object detectors, and SHIELD, a real-time defense that removes adversarial noise by stochastic data compression. Finally, I share my vision on making AI more robust under different threat models, and research directions on deploying AI in security-critical and high-stakes societal problems, such as cyber threat detection and fraud detection.
Shang-Tse Chen is a Ph.D. Candidate in Computer Science at Georgia Tech. He works in the intersection of applied and theoretical machine learning. His research focuses on designing robust machine learning algorithms for security-critical applications. He has worked closely with industry and government partners. His research has led to patent-pending cyber threat detection technology with Symantec, open-sourced adversarial attack and defense tools with Intel, deployed fire risk prediction system with the Atlanta Fire Rescue Department. He received his Bachelor's degree in CS from National Taiwan University. He is a recipient of the KDD Best Student Paper Runner-up Award (2016) and the IBM Fellowship (2018). Homepage: : https://www.cc.gatech.edu/~schen351