arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2302.10906cs.LGcs.AIcs.CR
收藏

使用TFHE进行加密推理的深度神经网络

Deep Neural Networks for Encrypted Inference with TFHE

Zama(Zama(扎马)公司(注:根据上下文,Zama 是一家从事相关技术研究的公司))

Andrei Stoian, Jordan Frery, Roman Bredehoft, Luis Montero, Celia Kherfallah, Benoit Chevallier-Mames

摘要:

全同态加密(FHE)是一种允许对加密数据执行计算而无需解密的加密方法。FHE保护处理敏感数据(如健康数据、生物识别数据、信用评分和其他个人信息)的在线服务用户的隐私。对此类数据提供有价值服务的常见方式是通过机器学习,此时,神经网络是非结构化数据的主要机器学习模型。在这项工作中,我们将展示如何构建与TFHE(一种允许任意深度计算电路的FHE方案)的约束兼容的深度神经网络(DNN)。我们讨论的约束条件,并显示DNN的两个计算机视觉任务的架构。我们基准的架构使用混凝土栈,TFHE的开源实现。

英文摘要:

Fully homomorphic encryption (FHE) is an encryption method that allows to perform computation on encrypted data, without decryption. FHE preserves the privacy of the users of online services that handle sensitive data, such as health data, biometrics, credit scores and other personal information. A common way to provide a valuable service on such data is through machine learning and, at this time, Neural Networks are the dominant machine learning model for unstructured data. In this work we show how to construct Deep Neural Networks (DNN) that are compatible with the constraints of TFHE, an FHE scheme that allows arbitrary depth computation circuits. We discuss the constraints and show the architecture of DNNs for two computer vision tasks. We benchmark the architectures using the Concrete stack, an open-source implementation of TFHE.

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。

↑