Minghao Shao is a NYU Abu Dhabi Global Ph.D. fellow and Google Ph.D. fellow in Privacy, Safety, and Security. A Ph.D. candidate in Computer Science at the NYU Tandon School of Engineering and NYU Abu Dhabi, he is co-advised by Professors Muhammad Shafique and Ramesh Karri. Minghao received his B.Sc. (Hons) degree in Computer Science with Artificial Intelligence from the University of Nottingham, UK, in 2020, and an M.Sc. degree in Computer Science from New York University, in 2023. His research focuses on advanced agentic systems and machine learning, with a particular emphasis on large language models (LLMs), cybersecurity, and AI Application for Science and Industry. Encompassing the development of novel approaches to enhance LLM capabilities, his work includes creating innovative datasets and benchmarks, designing algorithms to improve model performance and robustness, and optimizing computational efficiency and security. Specifically, Minghao investigates LLM security challenges, such as jailbreak attacks and alignment, cybersecurity agentic systems, and LLM-aided electronic design automation (EDA) in code generation, optimization and data security. His research efforts aim to foster trustworthy and efficient AI systems, while accelerating scientific discovery and driving industrial innovation across diverse domains.