Selected publication: 'MUNBa: Machine Unlearning via Nash Bargaining' by Jing Wu and Mehrtash Harandi, arXiv preprint arXiv:2411.15537v2, 2024.
Research Experience
Currently a Postdoctoral Research Fellow at the Department of Data Science & AI, Faculty of Information Technology, Monash University.
Education
Ph.D. in Engineering from Monash University, Australia, supervised by A/Prof. Mehrtash Harandi and Dr. Munawar Hayat; Master's student at UESTC, working with Prof. Yipeng Liu and Prof. Ce Zhu; Interned at Megvii under the mentorship of Prof. Shuaicheng Liu.
Background
Research interests include Trustworthy ML and Responsible AI, focusing on the analysis of vulnerabilities in deep learning models and developing algorithms to enhance safety and reliability. The long-term goal is to make AI systems safe, reliable, and unbiased.