Dr. Qiongkai Xu is a Lecturer in Computing at Macquarie University, having earned his Ph.D. from the Australian National University and previously served as a research fellow at the University of Melbourne. His research primarily focuses on Natural Language Processing, Privacy & Security, Machine Learning and Data Mining. Recently, his attention has been directed towards auditing machine learning models, specifically in two areas: 1) identifying and addressing privacy and security issues in ML/NLP models and their applications and 2) developing comprehensive evaluation theory and methods for ML/NLP models from various perspectives.

For more information , please see:

• my personal webpage;
• my Google Scholar profile.

My research spans a range of disciplines, with a focus on areas such as Natural Language Processing (NLP), Machine Learning (ML), Security & Privacy, Artificial Intelligence (AI), and Data Mining (DM). I have an active publication record in these fields, such as ACL, EMNLP, NeurIPS, ICLR, AAAI, WWW, WSDM, CIKM. Recently, my focus has shifted to more specific topics, including:

• Text Watermarking and Fingerprinting (NLP/ML+Security); 
• Backdoor and Adversarial Attack (NLP/ML+Security+DM); 
• Data Leakage in Language Model (NLP/ML+Security); 
• Performance Evaluation (NLP/ML).