About
Tony Bui is a Research Fellow at the Department of Data Science & AI, Monash University. His research focuses on the intersection of Generative AI and Trustworthy Machine Learning, particularly addressing ethical and security challenges in AI models such as ChatGPT and Stable Diffusion. He is actively involved in developing methodologies to prevent harmful outputs from generative models.
Research Interests:
- Trustworthy Machine Learning
- Generative Models
- Adversarial Machine Learning
- Model Security
- Ethical AI
Current Project: TMLGenAI: Trustworthy Generative AI (2024–2026), a collaborative initiative exploring safe and aligned foundation models. As a Chief Investigator, he contributes to advancing the theoretical and practical aspects of ethical AI.
Advising/Grants: Tony Bui has been accepting PhD students since 2020 and is a key researcher in projects funded by Monash University. His work bridges foundational theory with real-world applications, emphasizing robustness and ethical considerations in AI systems.
