Artificial Intelligence and Machine Learning in Autonomic and Automated Security
|
ABSTRACT Most existing approaches for autonomic and automated security are primarily based on formal models and reasoning. While formal approaches have advantages in explainability and theoretical guarantees, their application in security faces significant challenges, such as requiring accurate models that must be updated regularly as the threat landscape evolves. Artificial intelligence and machine learning provide alternative, data-driven approaches for creating sophisticated computational agents that can perform a variety of tasks. Building on recent advances in deep reinforcement learning, this project explores the applicability of learning based approaches for autonomic and automated |
management and mitigation of cybersecurity incidents. We consider two exemplary problems in this project: (1) resilient control of cyber-physical systems under adversarial tampering with sensor and actuator devices and (2) strategic remote attestation of Internet of Things devices with limited computational capabilities.
Slides found here.
BIO
Aron Laszka is an Assistant Professor in the Department of Computer Science at the University of Houston. His research interests revolve around the applications of artificial intelligence, machine learning, and game theory to security, the economics of cybersecurity, and the resilience of cyber-physical systems, including smart cities and critical infrastructure. His recent work has been funded by the National Science Foundation, the Department of Energy, NTT Research Inc., the Department of Homeland Security, the Department of Transportation, and Siemens. Previously, he was a Research Assistant Professor at Vanderbilt University from 2016 to 2017, a Postdoctoral Scholar at the University of California, Berkeley from 2015 to 2016, a Postdoctoral Research Scholar at Vanderbilt University from 2014 to 2015, and a Visiting Research Scholar at Pennsylvania State University in 2013. He graduated summa cum laude with a Ph.D. in Computer Science from the Budapest University of Technology and Economics in 2014.