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 2104.03152cs.CRcs.LG
收藏

TenSEAL:一个使用同态加密的加密张量运算库

TenSEAL: A Library for Encrypted Tensor Operations Using Homomorphic Encryption

École Supérieure en Informatique, Sidi Bel Abbès(西迪贝勒阿巴斯高等信息学院);OpenMined

Ayoub Benaissa, Bilal Retiat, Bogdan Cebere, Alaa Eddine Belfedhal

摘要:

机器学习算法已经取得了令人瞩目的成果,并在各个领域得到了广泛的应用。这些算法通常依赖于敏感和私人数据,如医疗和财务记录。因此,必须进一步关注应用于机器学习模型的隐私威胁和相应的防御技术。在本文中,我们介绍了TenSEAL,一个使用同态加密的隐私保护机器学习的开源库,可以很容易地集成到流行的机器学习框架中。我们使用MNIST对我们的实现进行基准测试,并表明加密的卷积神经网络可以在不到一秒的时间内进行评估,使用不到半兆字节的通信。

英文摘要:

Machine learning algorithms have achieved remarkable results and are widely applied in a variety of domains. These algorithms often rely on sensitive and private data such as medical and financial records. Therefore, it is vital to draw further attention regarding privacy threats and corresponding defensive techniques applied to machine learning models. In this paper, we present TenSEAL, an open-source library for Privacy-Preserving Machine Learning using Homomorphic Encryption that can be easily integrated within popular machine learning frameworks. We benchmark our implementation using MNIST and show that an encrypted convolutional neural network can be evaluated in less than a second, using less than half a megabyte of communication.

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。

↑