Yang Yuxiang

Yang Yuxiang is an Assistant Professor at the University of Hong Kong's School of Computing and Data Science. His research focuses on software security, adversarial machine learning, and AI safety, with a particular emphasis on formal methods and large language models. He holds a PhD from Hong Kong.

Research interests include:

• Automated program repair using LLMs
• Cybersecurity in open-source ecosystems
• Adversarial attacks on vision-language models
• Formal verification of theorem provers
• Ethical implications of AI systems

Recent publications explore cutting-edge topics such as causality-aware safety testing for autonomous systems, smart contract vulnerability detection, and large model safety at scale. His work bridges theoretical foundations with practical applications in secure software development and AI ethics.