Towards Trustworthy AI

Dr. Qiongkai Xu is a research fellow on Security in NLP at the University of Melbourne (UoM) in Australia. Qiongkai’s research primarily lies in among Privacy & Security, Natural Language Processing, Machine Learning and Data Mining. Recently, he is interested in auditing machine learning models, such as 1) unvealing privacy and security issues in ML/NLP models and 2) evaluating ML/NLP models from various angles.

If you’re as passionate about these research topics, I would love to hear your thoughts and ideas. Email: qiongkai.xu[at]unimelb.edu.au

Latest News

• [May, 2023] ‘Rethinking Round-Trip Translation for Machine Translation Evaluation’ is accepted to Findings of ACL 2023. Our work discusses and clarifies the confusing signals in Round-Trip Translation (RTT) evaluation on SMT, and we demonstrate some successful usage of RTT evaluation on NMT. Congrats to Terry and all co-authors!
• [Apr, 2023] I will serve as Publication Chair at ALTA 2023.
• [Feb, 2023] I will be teaching ‘Text Analytics for Business’ (BUSA90543) this winter semester.
• [Feb, 2023] ‘Security Challenges in Natural Language Processing Models’ is accepted to EMNLP 2023 (Tutorial). See you in Singapore!
• [Jan, 2023] One paper ‘Humanly Certifying Superhuman Classifiers’ is accepted to ICLR’23 (spotlight, notable-top-25%). If you would like to certify a ‘superhuman’ classifier, check our latest paper.
• [Jan, 2023] Congrats to Yujin and Terry! One paper ‘Training-Free Lexical Backdoor attacks on Language Models’ is accepted to WWW’23 (oral, acceptance rate 19.2%).
• [Oct, 2022] Two papers are accepted to EMNLP main conference. Congrats to Zhuang and Xuanli!
• [Sep, 2022] One paper is accepted to NeurIPS. Check our work on conditional watermarks for NLP APIs.
• [Sep, 2022] I am honored to be invited to give a talk at TrustML YSS on ‘Humanly Certifying Superhuman Classifiers’.
• [Aug, 2022] One paper ‘Student Surpasses Teacher: Imitation Attack for Black-Box NLP APIs’ is accepted to COLING (oral).

Selected Publications

• Rethinking Round-Trip Translation for Machine Translation Evaluation, Terry Yue Zhuo, Qiongkai Xu, Xuanli He, Trevor Cohn
  (Accepted to Findings of ACL 2023).

• Humanly Certifying Superhuman Classifiers, Qiongkai Xu, Christian Walder, Chenchen Xu Proceedings of the Eleventh International Conference on Learning Representations (ICLR), May 2023.

• CATER: Intellectual Property Protection on Text Generation APIs via Conditional Watermarks, Xuanli He, Qiongkai Xu, Yi Zeng, Lingjuan Lyu, Fangzhao Wu, Jiwei Li, Ruoxi Jia Proceedings of the 36th Conference on Neural Information Processing Systems (NeurIPS), Nov 2022.

• Student Surpasses Teacher: Imitation Attack for Black-Box NLP APIs, Qiongkai Xu, Xuanli He, Lingjuan Lyu, Lizhen Qu, Gholamreza Haffari Proceedings of the 29th International Conference on Computational Linguistics (COLING), Oct 2022.

• Adhering, Steering, and Queering: Treatment of Gender in Natural Language Generation, Yolande Strengers, Lizhen Qu, Qiongkai Xu, Jarrod Knibbe Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems (CHI), Apr 2020.

• GraRep: Learning Graph Representations with Global Structural Information, Shaosheng Cao, Wei Lu, Qiongkai Xu Proceedings of the 24th ACM international on conference on information and knowledge management (CIKM), Oct 2015.