arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2402.01154cs.CR
收藏

通过同态加密实现抗量子安全的联邦学习:基于梯度的学习

Towards Quantum-Safe Federated Learning via Homomorphic Encryption: Learning with Gradients

Guangfeng Yan, Shanxiang Lyu, Hanxu Hou, Zhiyong Zheng, Linqi Song

AI总结:

该研究提出基于私钥同态加密的隐私保护分布式学习框架,利用梯度量化随机性消除LWE加密的误差项,支持多参与者在诚实但好奇的服务器上安全协作深度学习。

摘要:

本文提出了一种基于私钥同态加密的隐私保护分布式学习框架。得益于梯度量化的随机性,我们基于带错学习(LWE)的加密方案能够消除误差项,从而避免了传统基于LWE的同态加密中存在的误差膨胀问题。该系统允许大量学习参与者在诚实但好奇的服务器上协作开展基于神经网络的深度学习,同时确保参与者上传梯度的密码学安全性。

英文摘要:

This paper introduces a privacy-preserving distributed learning framework via private-key homomorphic encryption. Thanks to the randomness of the quantization of gradients, our learning with error (LWE) based encryption can eliminate the error terms, thus avoiding the issue of error expansion in conventional LWE-based homomorphic encryption. The proposed system allows a large number of learning participants to engage in neural network-based deep learning collaboratively over an honest-but-curious server, while ensuring the cryptographic security of participants' uploaded gradients.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑