Harsh Chaudhari

I recently completed my PhD at Northeastern University, where I was advised by Alina Oprea. My research interests broadly lie at the intersection of machine learning, security, and privacy. Current research focuses on stress testing Large Language Models to understand and mitigate threats to participating users. Previously, I completed my Masters (via Research) from Indian Institute of Science (IISc) where I mainly worked in the area of privacy-preserving machine learning via Multi-Party Computation (MPC).