About me

I’m a Research Fellow at University College London (NLP group). I received my Ph.D. from Monash University (Australia), supervised by Prof. Reza Haffari and Dr. Mohammad Norouzi. My recent research lies in an intersection between deep learning and natural language processing, with an emphasis on robustness and security in NLP models.

Now, I’m highlighting:

• Security in NLP models, including privacy leakage and protection, backdoor attack and defense, imitation attack and defense
• Robustness in NLP models

Recent News

• I joined UCL as a Research Fellow under the supervision of Dr. Pontus Stenetorp and Dr. Pasquale Minervini
• I did my internship at Amazon Search (Seattle, WA) (Jul-Oct, 2021)
• I did my internship at Adobe Research (San Jose, CA) (Jul-Sep, 2019)

Recent Research Highlights

• Extracted BERT Model Leaks More Information than You Think!
  Xuanli He, Chen Chen, Lingjuan Lyu, Qiongkai Xu. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing. 2022.
• Student Surpasses Teacher: Imitation Attack for Black-Box NLP APIs
  Qiongkai Xu, Xuanli He, Lingjuan Lyu, Lizhen Qu, Gholamreza Haffari. In Proceedings of the 29th International Conference on Computational Linguistics. 2022.
• Protecting Intellectual Property of Language Generation APIs with Lexical Watermark
  Xuanli He, Qiongkai Xu, Lingjuan Lyu, Fangzhao Wu, Chenguang Wang. In Proceedings of the AAAI Conference on Artificial Intelligence. 2022.
• 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. In Advances in Neural Information Processing Systems. 2022.
• Generate, Annotate, and Learn: NLP with Synthetic Text
  Xuanli He, Islam Nassar, Jamie Kiros, Gholamreza Haffari, Mohammad Norouzi. In Transactions of the Association for Computational Linguistics. 2022.
• Generalised Unsupervised Domain Adaptation of Neural Machine Translation with Cross-Lingual Data Selection
  Thuy-Trang Vu, Xuanli He, Dinh Phung, and Gholamreza Haffari. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing. 2021.
• Model Extraction and Adversarial Transferability, Your BERT is Vulnerable!
  Xuanli He, Lingjuan Lyu, Lichao Sun, and Qiongkai Xu. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 2021.
• Scene Graph Modification Based on Natural Language Commands
  Xuanli He, Quan Hung Tran, Gholamreza Haffari, Walter Chang, Zhe Lin, Trung Bui, Franck Dernoncourt, Nhan Dam. In The Findings of the Empirical Methods in Natural Language Processing (Findings-EMNLP). 2020.
• Differentially Private Representation for NLP: Formal Guarantee and An Empirical Study on Privacy and Fairness
  Lingjuan Lyu, Xuanli He, Yitong Li. In The Findings of the Empirical Methods in Natural Language Processing (Findings-EMNLP). 2020.
• Towards Differentially Private Text Representations
  Lingjuan Lyu, Yitong Li, Xuanli He, Tong Xiao. In Proceedings of 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval. 2020.
• Dynamic Programming Encoding for Subword Segmentation in Neural Machine Translation
  Xuanli He, Gholamreza Haffari, Mohammad Norouzi. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. 2020.