no code implementations • 7 Nov 2023 • Fei Zheng
However, in this paper, we demonstrate that in LLMs, VFL fails to protect the user input since it is simple and cheap to reconstruct the input from the intermediate embeddings.
no code implementations • 18 Aug 2023 • Haoze Qiu, Fei Zheng, Chaochao Chen, Xiaolin Zheng
As a privacy-preserving method for implementing Vertical Federated Learning, Split Learning has been extensively researched.
no code implementations • 26 Jun 2023 • Xiaolin Zheng, Senci Ying, Fei Zheng, Jianwei Yin, Longfei Zheng, Chaochao Chen, Fengqin Dong
In this work, we propose FedND: federated learning with noise distillation.
no code implementations • 29 May 2023 • Fei Zheng, Chaochao Chen, Lingjuan Lyu, Binhui Yao
However, communication efficiency is still a crucial issue for split learning.
no code implementations • 18 Oct 2022 • Fei Zheng, Chaochao Chen, Binhui Yao, Xiaolin Zheng
As a practical privacy-preserving learning method, split learning has drawn much attention in academia and industry.
1 code implementation • 17 Aug 2021 • Fei Zheng, Chaochao Chen, Xiaolin Zheng, Mingjie Zhu
Since our method reduces the cost for element-wise function computation, it is more efficient than existing cryptographic methods.
no code implementations • 18 Aug 2020 • Fei Zheng
With the increasing demands for privacy protection, many privacy-preserving machine learning systems were proposed in recent years.