Within our group, we model, analyze and solve a wide range of problems in which secure decisions must be made in noisy and adversarial environments. We utilize rigorous tools and techniques from decision, control, optimization and game theory to model the system and we apply techniques from Machine Learning to obtain potent strategies. Over the past few years, our work focused on cyber security topics in Cyber-Physical Systems (CPS), wireless communication and cloud computing. Our efforts span the following activities:
We focus on protecting future Cyber-Physical systems within various applications such as intelligent transportation systems, manufacturing and multi-agent systems. Our approach relies on game-theoretic models that we solve using reinforcement learning methods.
In this project we study the susceptibility of dynamic channel allocation methods -- commonly used in Software Defined Networks (SDN) -- to stealthy jamming attacks. Through Markov Decision Process and game-theoretic frameworks we were able to expose potent attacks and develop defense mechanisms that mitigate their impact.
Security and privacy in cloud computing are critical components for various organizations that depend on the cloud in their daily operations. Customers' data and the organizations' proprietary information have been subject to various attacks in the past. In this project, we develop a set of Moving Target Defense (MTD) strategies that randomize the location of the Virtual Machines (VMs) to harden the cloud against attacks.