CV

Appointments

  • Research Associate. 2022 – present. University College London.
  • Research Assistant. 2017 – 2018. Monash University.

Education

  • Ph.D. 2022. Monash University.
  • M.S. 2015. University of Melbourne.
  • B.S. 2013. Southwest University of Science and Technology.

Papers

Refereed journal articles

  • Xuanli He, Qiongkai Xu, Jun Wang, Benjamin Rubinstein, Trevor Cohn. 2024. SEEP: Training Dynamics Grounds Latent Representation Search for Mitigating Backdoor Poisoning Attacks. In Transactions of the Association for Computational Linguistics.
  • Xuanli He, Islam Nassar, Jamie Kiros, Gholamreza Haffari, Mohammad Norouzi. 2022. Generate, Annotate, and Learn: NLP with Synthetic Text. In Transactions of the Association for Computational Linguistics.
  • Lingjuan Lyu, James C Bezdek, Xuanli He, Jiong Jin. 2019. Fog-embedded Deep Learning for the Internet of Things. In IEEE Transactions on Industrial Informatics.
  • Lingjuan Lyu, James C Bezdek, Yee Wei Law, Xuanli He, Marimuthu Palaniswami. 2018. Privacy-preserving collaborative fuzzy clustering. In Data & Knowledge Engineering.
  • Lingjuan Lyu, Jiong Jin, Sutharshan Rajasegarar, Xuanli He, Marimuthu Palaniswami. 2017. Fog-empowered anomaly detection in IoT using hyperellipsoidal clustering. In Proceedings of Educational Data Mining.

Refereed conference papers

  • Ansh Arora, Xuanli He, Maximilian Mozes, Srinibas Swain, Mark Dras, Qiongkai Xu. 2024. Here’s a Free Lunch: Sanitizing Backdoored Models with Model Merge. In Findings of the Association for Computational Linguistics ACL 2024.
  • Jun Wang, Qiongkai Xu, Xuanli He, Benjamin Rubinstein, Trevor Cohn. 2024. Backdoor Attacks on Multilingual Machine Translation. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers).
  • Jiayi Wang, David Adelani, Sweta Agrawal, Marek Masiak, Ricardo Rei, Eleftheria Briakou, Marine Carpuat, Xuanli He, Sofia Bourhim, Andiswa Bukula, Muhidin Mohamed, Temitayo Olatoye, Tosin Adewumi, Hamam Mokayed, Christine Mwase, Wangui Kimotho, Foutse Yuehgoh, Anuoluwapo Aremu, Jessica Ojo, Shamsuddeen Muhammad, Salomey Osei, Abdul-Hakeem Omotayo, Chiamaka Chukwuneke, Perez Ogayo, Oumaima Hourrane, Salma El Anigri, Lolwethu Ndolela, Thabiso Mangwana, Shafie Mohamed, Hassan Ayinde, Oluwabusayo Awoyomi, Lama Alkhaled, Sana Al-azzawi, Naome Etori, Millicent Ochieng, Clemencia Siro, Njoroge Kiragu, Eric Muchiri, Wangari Kimotho, Toadoum Sari Sakayo, Lyse Naomi Wamba, Daud Abolade, Simbiat Ajao, Iyanuoluwa Shode, Ricky Macharm, Ruqayya Iro, Saheed Abdullahi, Stephen Moore, Bernard Opoku, Zainab Akinjobi, Abeeb Afolabi, Nnaemeka Obiefuna, Onyekachi Ogbu, Sam Ochieng’, Verrah Otiende, Chinedu Mbonu, Yao Lu, Pontus Stenetorp. 2024. AfriMTE and AfriCOMET: Enhancing COMET to Embrace Under-resourced African Languages. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers).
  • Xuanli He, Yuxiang Wu, Oana-Maria Camburu, Pasquale Minervini, Pontus Stenetorp. 2024. Using Natural Language Explanations to Improve Robustness of In-context Learning. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers).
  • Xuanli He, Qiongkai Xu, Jun Wang, Benjamin Rubinstein, Trevor Cohn. 2023. Mitigating Backdoor Poisoning Attacks through the Lens of Spurious Correlation. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing.
  • Terry Yue Zhuo, Qiongkai Xu, Xuanli He, Trevor Cohn. 2023. Rethinking Round-Trip Translation for Machine Translation Evaluation. In Findings of the Association for Computational Linguistics: ACL 2023.
  • Jun Wang, Xuanli He, Benjamin Rubinstein, Trevor Cohn. 2022. Foiling Training-Time Attacks on Neural Machine Translation Systems. In Findings of the Association for Computational Linguistics: EMNLP 2022.
  • Xuanli He, Chen Chen, Lingjuan Lyu, Qiongkai Xu. 2022. Extracted BERT Model Leaks More Information than You Think!. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing.
  • Qiongkai Xu, Xuanli He, Lingjuan Lyu, Lizhen Qu, Gholamreza Haffari. 2022. Student Surpasses Teacher: Imitation Attack for Black-Box NLP APIs. In Proceedings of the 29th International Conference on Computational Linguistics.
  • Xuanli He, Qiongkai Xu, Lingjuan Lyu, Fangzhao Wu, Chenguang Wang. 2022. Protecting Intellectual Property of Language Generation APIs with Lexical Watermark. In Proceedings of the AAAI Conference on Artificial Intelligence.
  • Xuanli He, Qiongkai Xu, Yi Zeng, Lingjuan Lyu, Fangzhao Wu, Jiwei Li, Ruoxi Jia. 2022. CATER: Intellectual Property Protection on Text Generation APIs via Conditional Watermarks. In Proceedings of Advances in Neural Information Processing Systems.
  • Thuy-Trang Vu, Xuanli He, Dinh Phung, and Gholamreza Haffari. 2021. Generalised Unsupervised Domain Adaptation of Neural Machine Translation with Cross-Lingual Data Selection. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing.
  • Xuanli He, Lingjuan Lyu, Lichao Sun, and Qiongkai Xu. 2021. Model Extraction and Adversarial Transferability, Your BERT is Vulnerable!. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies.
  • Xuanli He, Quan Hung Tran, Gholamreza Haffari, Walter Chang, Zhe Lin, Trung Bui, Franck Dernoncourt, Nhan Dam. 2020. Scene Graph Modification Based on Natural Language Commands. In The Findings of the Empirical Methods in Natural Language Processing (Findings-EMNLP).
  • Lingjuan Lyu, Xuanli He, Yitong Li. 2020. Differentially Private Representation for NLP: Formal Guarantee and An Empirical Study on Privacy and Fairness. In The Findings of the Empirical Methods in Natural Language Processing (Findings-EMNLP).
  • Lingjuan Lyu, Yitong Li, Xuanli He, Tong Xiao. 2020. Towards Differentially Private Text Representations. In Proceedings of 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval.
  • Xuanli He, Gholamreza Haffari, Mohammad Norouzi. 2020. Dynamic Programming Encoding for Subword Segmentation in Neural Machine Translation. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics.
  • Xuanli He, Quan Hung Tran, Gholamreza Haffari. 2019. A Pointer Network Architecture for Context-Dependent Semantic Parsing. In Proceedings of ALTA.
  • Xuanli He, Gholamreza Haffari, Mohammad Norouzi. 2018. Sequence to sequence mixture model for diverse machine translation. In Proceedings of CoNLL.
  • Xuanli He, Quan Hung Tran, William Havard, Laurent Besacier, Ingrid Zukerman, Gholamreza Haffari. 2018. Exploring Textual and Speech information in Dialogue Act Classification with Speaker Domain Adaptation. In Proceedings of ALTA.
  • Lingjuan Lyu, Xuanli He, Yee Wei Law, Marimuthu Palaniswami. 2017. Privacy-preserving collaborative deep learning with application to human activity recognition. In Proceedings of the 2017 ACM on Conference on Information and Knowledge Management.

Awards

  • Winning Team. 2018. Winning Team in Collaborative Research Challenge Final (FIT at Monash).
  • International Postgraduate Research Scholarship. 2018. Faculty of Information at Monash.
  • Co-funded Monash Graduate Scholarship. 2018. Monash.

Grants

  • OpenAI Research Credits. 2024. $2,500 (USD) credits from OpenAI for "Disclosing and Protecting Vulnerabilities in LLM-Orchestrated Autonomous Frameworks.".
  • GCP Research Credits. 2019. $1,000 (USD) credits from Google Cloud Platform for Machine Translation project.

Teaching

University courses

  • Statistical NLP. 2023, 2024. as Senior TA.
  • Fundamentals of Artificial Intelligence. 2020. as TA.

Service

Research community

  • Reviewer. ACL 2020–2023, EMNLP 2020–2023, AAAI 2022–2024, NeurIPS 2024, ICLR 2024.

Engineering Positions

  • Software Engineer. 2016–2017. IBM Research AU.