🎈 About Me

I am currently a second-year Ph.D. student at AI Thrust, Information Hub, The Hong Kong University of Science and Technology (Guangzhou) supervised by Prof. Li Liu and Prof. Hui Xiong. Previously, I received my master degree from City University of Hong Kong, advised by Prof. Xiangyu Zhao.

Research Interests

• AI Security
• Backdoor Learning
• Recommendation

🔥 News

• 2024.12:  🎉🎉 Our paper on audio backdoor defense is accepted by ICASSP 2025. Congrats to Nanjun!
• 2024.12: I will serve as a reviewer for ICML 2025. It’s my great honor to contribute to the machine learning community. Looking forward to learning from the latest research.
• 2024.12:  🎉🎉 Our paper using optimal transport for data-free backdoor defense is accepted by AAAI 2025! Looking forward to present our work in Philadelphia!
• 2024.09:  🎉🎉 Our paper on backdoor defense is accepted by NeurIPS 2024! Thanks for co-authors from CUHKSZ and SRIBD. Please refer to the project page for more details if you are interested in our work.
• 2024.05: I will serve as a reviewer for NeurIPS 2024. I am grateful for the reviewer nomination by NeurIPS 2024 Program Chairs.
• 2023.09: I start my Ph.D. study in HKUST(GZ)!

📝 Selected Papers

(* indicates equal contribution, # indicates corresponding author)

Publications

AAAI 2025

Fusing Pruned and Backdoored Models: Optimal Transport-based Data-free Backdoor Mitigation

Weilin Lin, Li Liu^#, Jianze Li, Hui Xiong

• One of the few data-free defense strategies against backdoor attacks.
• First adaptation of OT and model fusion on backdoor defense.

The Thirty-Ninth AAAI Conference on Artificial Intelligence (AAAI-25), Philadelphia, Pennsylvania, USA, 2025

NeurIPS 2024

Unveiling and Mitigating Backdoor Vulnerabilities based on Unlearning Weight Changes and Backdoor Activeness

Weilin Lin, Li Liu^#, Shaokui Wei, Jianze Li, Hui Xiong

• New insights on unlearning weight change and backdoor activeness.
• Propose an effective defense strategy using reinitialization and fine-tuning.

Annual Conference on Neural Information Processing Systems (NeurIPS), Vancouver, Canada, 2024

• WWW 2023 Autodenoise: Automatic data instance denoising for recommendations, Weilin Lin, Xiangyu Zhao^#, Yejing Wang, Yuanshao Zhu, Wanyu Wang.
• KDD 2022 AdaFS: Adaptive feature selection in deep recommender system, Weilin Lin, Xiangyu Zhao^#, Yejing Wang, Tong Xu, Xian Wu.

Preprints

• Arxiv 2023 A comprehensive survey on segment anything model for vision and beyond, Chunhui Zhang, Li Liu^#, Yawen Cui, Guanjie Huang, Weilin Lin, Yiqian Yang, Yuehong Hu

📖 Educations

• Ph.D., Artificial Intelligence, The Hong Kong University of Science and Technology (Guangzhou), September 2023 - Present
  • Advisors: Prof. Li Liu and Prof. Hui Xiong
• M.S.c, Multimedia Information Technology, City University of Hong Kong, August 2021 - October 2022
  • Advisor: Prof. Xiangyu Zhao
• B.S., Electronic Information Science and Technology, South China Normal University, September 2017 - July 2021

🧭 Experience

• 2023.03 - 2023.09, Research Assistant, The Hong Kong University of Science and Technology (Guangzhou). Advisor: Prof. Li Liu.
• 2022.07 - 2023.03, Research Assistant, USAIL Group, HKUST Fok Ying Tung Research Institute / The Hong Kong University of Science and Technology (Guangzhou). Advisor: Prof. Hao Liu.
• 2021.09 - 2022.10, Research Assistant, Applied Machine Learning Lab (AML Lab), City University of Hong Kong. Advisor: Prof. Xiangyu Zhao.

🎖 Honors and Awards

• Best Student Paper Award Finalist in ICSR 2024.
• Full Postgraduate Scholarship, HKUST(GZ).

🍀 Services

Reviewer/External Reviewer

• The International Conference on Machine Learning (ICML), 2025
• Annual Conference on Neural Information Processing Systems (NeurIPS), 2024
• Annual AAAI Conference on Artificial Intelligence (AAAI), 2024
• Conference on Research and Development in Information Retrieval (SIGIR), 2024