Towards Designing Robust Smart Infrastructure System

Rising Star Symposium on Cyber-Physical Systems Security, Resilience, and Privacy https://sites.google.com/nyu.edu/ieee-css-tcsp-symp By Shivam Bajaj from Purdue University https://shivambajaj08.github.io/ While the integration of information technology and physical infrastructure systems has already made smart infrastructure systems a reality, the advent of AI has the promise of making such systems even more responsive and efficient. However, making this promise a reality requires solving multiple challenges. In this two-part talk, I will present my work on two of these challenges. In the first part, leveraging concepts from bi-similarity frameworks, I will present a principled framework towards designing, in a compositional and robust manner, approximate but computationally more efficient models of the physical system that can be used in control design and contingency planning. In the second part, I will present a framework to design robust learning algorithms for multiple non-cooperative AI agents. Both frameworks that I will present are general in the sense that they can also be used with preexisting methods.