Rishi Jha is a PhD student in Computer Science at Cornell Tech, where he is advised by Professor Vitaly Shmatikov. His research interests lie in understanding how generative AI’s internal knowledge representations—such as embeddings and inter-agent communications—create privacy and security vulnerabilities. He holds an M.S. in Computer Science and a B.S.B.A. in Computer Science and Mathematics (Philosophy) from the University of Washington, Seattle. As a DLI Fellow, he hopes to explore ethical and legal perspectives on meaningful AI safety.