Puwei Lian

According to our database, Puwei Lian authored at least 4 papers between 2025 and 2026.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2026

Noise as a Probe: Membership Inference Attacks on Diffusion Models Leveraging Initial Noise.

Puwei Lian, Yujun Cai, Songze Li, Bingkun Bao

CoRR, January, 2026

2025

Unveiling Impact of Frequency Components on Membership Inference Attacks for Diffusion Models.

Puwei Lian, Yujun Cai, Songze Li

CoRR, May, 2025

FedPD: Defending federated prototype learning against backdoor attacks.

Zhou Tan, Jianping Cai, De Li, Puwei Lian, Ximeng Liu, Yan Che

Neural Networks, 2025

Achieving Zero-Glance Unlearning with Data-Free Inversion and Selective Parameters Suppression.

Puwei Lian, Xiao Ke, Zhou Tan, Jianping Cai, Ximeng Liu

Proceedings of the IEEE International Conference on Multimedia and Expo, 2025