I am currently a Postodoctoral Research Fellow at Department of Data Science & AI, Faculty of Information Technology, Monash University. I completed my Ph.D. in Engineering at Faculty of Engineering, Monash University, Australia, where I have the privilege of being mentored by A/Prof. Mehrtash Harandi and Dr. Munawar Hayat. Before joining Monash University, I was a master’s student at UESTC, where I worked with Prof. Yipeng Liu and Prof. Ce Zhu. I also interned at Megvii under the mentorship of Prof. Shuaicheng Liu.

My work mostly contributes to the fields of Trustworthy ML and Responsible AI. My research mainly focuses on the analysis of the vulnerabilities of deep learning models, and developing algorithms for enhancing safety and reliability by defending against attacks and mitigating inappropriate influence in AI systems. My long-term research objective is to make AI systems safe, reliable, and unbias, as AI increasingly becomes a part of our daily lives, its safety and reliability must be paramount considerations prior to deployment.

My current and past research services include being the reviewer for IEEE Transactions on Pattern Analysis and Machine Intelligence, Transactions on Machine Learning Research, IEEE Transactions on Emerging Topics in Computational Intelligence, and CVPR, ICCV, ECCV, NeurIPS, ICML, ICLR, AAAI, ECAI, ACM MM, AISTATS.

• Trustworthy ML
• Machine unlearning & Image Edit & Model Edit
• Model inversion attacks & defenses, adversarial attacks & defenses