Lizhao Wu ☕️
Lizhao Wu

PhD Student

University of Exeter

About Me

Lizhao Wu received his master’s degree from the School of Computer and Cyberspace Security at Fujian Normal University in 2025 and is currently pursuing a Ph.D. degree at University of Exeter. His research interests include distributed federated learning and trusted computing.

Download CV
Interests
  • Quantum Mechanics
  • Federated Learning
  • Secure Deep Learning
  • Casual Inference
  • Agriculture in Federated Learning
Education

  • University of Exeter

    Stocker Rd, Exeter EX4 4PY, UK

  • Fujian Normal University

    Fuzhou City, Fujian Province, China

  • North China University of Science and Technology

    Tangshan City, Hebei Province, China

📚 My Research

I have recently been awarded the China Scholarship Council (CSC) PhD scholarship at the University of Exeter.

Currently, my research efforts are primarily focused on quantum machine learning research and the development of distributed trustworthy federated learning frameworks.

I welcome communication or collaboration opportunities with anyone interested in these areas. 😃

Featured Publications
Bad-MFL: A Cross-Modality Bi-Trigger Backdoor Attack against Multi-Modal Federated Learning
Toward Personalized Federated Meta-learning with Constrained Hypernetwork on Non-IID Data
Federated Training Generative Adversarial Networks for Heterogeneous Vehicle Scheduling in IoV
Defending Against Backdoor Attacks through Causality-Augmented Diffusion Models for Dataset Purification
Recent Publications
Yuefeng Lai, Lizhao Wu*, Hui Lin (2025). Bad-MFL: A Cross-Modality Bi-Trigger Backdoor Attack against Multi-Modal Federated Learning. IEEE IoTJ.
Cite
Lizhao Wu, Xiaoding Wang, Hui Lin, Xu Yang, Jiwu Shu, Xun Yi, Ibrahim Khalil, Albert Y. Zomaya (2025). Toward Personalized Federated Meta-learning with Constrained Hypernetwork on Non-IID Data.
Code
Lizhao Wu, Hui Lin, Xiaoding Wang (2025). Federated Training Generative Adversarial Networks for Heterogeneous Vehicle Scheduling in IoV. IEEE IoTJ.
Cite DOI
Yuefeng Lai, Lizhao Wu*, Hui Lin, Xiaokang Zhou (2024). Defending Against Backdoor Attacks through Causality-Augmented Diffusion Models for Dataset Purification. IEEE TrustCom2024.
PDF Cite DOI
Recent & Upcoming Talks
A Graph Generation Network with Privacy Preserving Capabilities

A Graph Generation Network with Privacy Preserving Capabilities

Large datasets drive advancements in science, technology, and economic growth, with graph-structured data playing a pivotal role in mining and analysis. However, graph data often contains sensitive personal information, exposing it to privacy risks. To address this, the RDP-GGAN framework is proposed, integrating Rényi differential privacy (RDP) with generative adversarial networks (GANs). This framework enforces strict privacy constraints on deep graph generative models, focusing on preserving edge privacy to safeguard relational data connections. By injecting controlled noise into gradients of link-reconstruction models, RDP-GGAN enhances edge differential privacy, offering robust protection for sensitive graph-structured information.

Recent News