Fuyao Zhang
I am currently a PhD student at the College of Computing and Data Science, Nanyang Technological University (NTU), advised by Prof. Wei Yang Bryan Lim. Prior to joining NTU, I received my bachelor’s degree in 2025 from the School of Telecommunications Engineering at Xidian University, under the supervision of Prof. Dan Wang. From 2024 to 2025, I was an exchange student at Heriot-Watt University.
My research interests include Agents, Multimodal Large Language Models, and Trustworthy AI.
News
2025.11: 🔥 Oblivionis is accepted by AAAI 2026.
2025.08: 🔥 One paper on federated learning accepted by IEEE TMC.
Selected Works
DualTAP: A Dual-Task Adversarial Protector for Mobile MLLM Agents
Fuyao Zhang, Jiaming Zhang, Che Wang, Xiongtao Sun, Yurong Hao, Guowei Guan, Wenjie Li, Longtao Huang, Wei Yang Bryan Lim
[Website]
Oblivionis: A Lightweight Learning and Unlearning Framework for Federated Large Language Models
Fuyao Zhang , Xinyu Yan, Tiantong Wu, Wenjie Li, Tianxiang Chen, Yang Cao, Ran Yan, Longtao Huang, Wei Yang Bryan Lim, Qiang Yang
AAAI 2026, [PDF], [Website], [Code]
Verifiably Forgotten? Gradient Differences Still Enable Data Reconstruction in Federated Unlearning
Fuyao Zhang, Wenjie Li, Yurong Hao, Xinyu Yan, Yang Cao, Wei Yang Bryan Lim
ArXiv 2025, [PDF], [Code]
Ground-Assisted LEO Satellite Federated Learning: Dynamic, Efficient, Distributed Learning
Fuyao Zhang, Dan Wang, Jiawen Kang, Dusit Niyato
IEEE Transactions on Mobile Computing 2025, [PDF]
DPFCIL: Differentially Private Federated Class-Incremental Learning on non-IID Data
Fuyao Zhang, Dan Wang, Chuyang Liang
TrustCom 2024, [PDF]
Honors and Awards:
- 2022 National Scholarship，China (Top 1%)
- 2023 National Scholarship，China (Top 1%)