My research interests broadly lie at the intersection of Formal Methods (FM), Artificial Intelligence (AI), and Machine Learning (ML). Specifically, I am focused on ensuring the safety and reliability of systems commonly used in AI applications. To this end, I have been exploring rigorous techniques to explain and verify the behavior of AI systems.

I have worked on designing algorithms for detecting temporal patterns in system behavior using human-interpretable temporal logics. Additionally, I have worked on the verification of neural networks by abstracting their high-level behavior using surrogate models such as finite automata.