Wei Shen

I'm a master student at Wuhan University, under the supervision of Prof. Mang Ye. Before that, I obtained my B.S. degree from Wuhan University in 2023.

My research interests lie in Trustworthy AI, with a focus on Federated Learning and LLMs. I am committed to developing practical, generalizable algorithms that enhance the safety, robustness and explainability of AI systems, making them controllable.

I am currently seeking opportunities for PhD programs (starting Fall 2026) or research assistant positions focused on Trustworthy AI, especially Trustworthy LLMs. If you’d like to collaborate or discuss potential opportunities, feel free to reach out.

Email / Google Scholar / Github

News

[02/2025] One paper on VFL has been accepted by IEEE Transactions on Mobile Computing (TMC).
[12/2024] One paper on backdoor attacks in VFL has been accepted at AAAI 2025. See you in Philadelphia!
[07/2024] One paper on Graph Learning has been accepted at ACM MM 2024. See you in Melbourne!

Publications

	Label-Free Backdoor Attacks in Vertical Federated Learning [paper] [codes] Wei Shen⁺, Wenke Huang⁺, Guancheng Wan, Mang Ye The 39th Annual AAAI Conference on Artificial Intelligence (AAAI), 2025 We propose a backdoor attack paradigm for VFL that operates without explicit label information.
	Build Yourself Before Collaboration: Vertical Federated Learning with Limited Aligned Samples [paper] [codes] Wei Shen, Mang Ye, Wei Yu, Pong C. Yuen IEEE Transactions on Mobile Computing (TMC), 2025 We address the challenge of limited aligned samples in VFL by implementing local learning before each collaboration.
	Resisting Over-Smoothing in Graph Neural Networks via Dual-Dimensional Decoupling [paper] [codes] Wei Shen, Mang Ye, Wenke Huang ACM Multimedia (ACM MM), 2024 We address the oversmoothing issue in GNNs by leveraging both instance-level and dimension-level cues.
	Securereid: Privacy-preserving anonymization for person re-identification [paper] [codes] Mang Ye, Wei Shen, Junwu Zhang, Yao Yang, Bo Du IEEE Transactions on Information Forensics and Security (TIFS), 2024 We propose a reversible anonymization method for person re-identification (Re-ID) with customized encryption.
	Vertical Federated Learning for Effectiveness, Security, Applicability: A Survey [paper] [codes] Mang Ye, Wei Shen, Bo Du, Eduard Snezhko, Vassili Kovalev, Pong C. Yuen ACM Computing Surveys, 2025 We provide a literature review on VFL, focusing on effectiveness, security, and applicability.

Service

Conference Reviewer: CVPR 2024/2025, ICLR 2025, IJCNN 2025, ICME 2024/2025

Thanks for the template from Jon Barron.