计算机科学与探索

• 学术研究 •    下一篇

高精度可扩展的密态隐私保护语音分类

王雷蕾,宋考,张媛媛,毕仁万,熊金波   

  1. 1.福建师范大学 计算机与网络空间安全学院, 福州 350117
    2.福建省网络安全与密码技术重点实验室, 福建师范大学, 福州 350117

PPSC: High-Precision and Scalable Encrypted Privacy-Preserving Speech Classification

WANG Leilei, SONG Kao, ZHANG Yuanyuan, BI Renwan, XIONG Jinbo   

  1. 1.College of Computer and Cyber Security, Fujian Normal University, Fuzhou 350117, China
    2.Fujian Provincial Key Laboratory of Network Security and Cryptology, Fujian Normal University, Fuzhou 350117, China

摘要: 为解决现有全同态加密技术在语音分类任务中计算效率和分类准确率均较低的挑战,提出一种高精度可扩展的密态隐私保护语音分类PPSC方案。首先,设计基于CKKS全同态加密技术两方服务器协同的安全乘法协议,因避免使用昂贵的自举操作,可有效提升深层次密文乘法的计算效率,从而使得方案可扩展到更深层次的神经网络;基于上述架构设计安全指数、安全倒数以及安全比较等安全非多项式协议,相较于多项式近似拟合非多项式运算的方法,在提高计算精度的同时,降低了计算开销。其次,安全实现卷积层、ReLU层、平均池化层、全连接层、Softmax层等PPSC方案的基本模块,确保语音数据、语音模型和中间计算结果的隐私性。最后,从有效性和安全性等维度对PPSC方案进行了详尽的理论分析,证明安全乘法协议在更深层次的乘法运算中具有更高的运算效率。在Speech Command Database语音数据集上的实验结果表明,PPSC方案可以在保护数据和模型参数隐私的情况下实现有效的语音分类,其准确率相比于HEKWS方案提高3.57%。

关键词: 全同态加密, 隐私保护, 两方协同, 语音分类, 安全计算协议

Abstract: To address the challenges of low computational efficiency and classification accuracy in existing fully homomorphic encryption technology for speech classification tasks, a high-precision and scalable encrypted privacy-preserving speech classification (PPSC) scheme is proposed. First of all, A secure multiplication protocol based on CKKS fully homomorphic encryption technology is designed to avoid the use of expensive bootstrapping operations, which can effectively improve the computational efficiency of deep ciphertext multiplication, so that the scheme can be extended to deeper neural networks. Based on the above architecture, secure non-polynomial protocols such as secure exponent, secure reciprocal and secure comparison are designed. Compared with the method of polynomial approximate fitting of non-polynomial operations, our protocols improve computation accuracy and reduces computation overhead. Secondly, the PPSC scheme securely implements the fundamental modules such as the convolutional layer, ReLU layer, average pooling layer, fully connected layer, and Softmax layer. This ensures the privacy of speech data, speech classification models, and intermediate computing results. Finally, a detailed theoretical analysis of the PPSC scheme is conducted to evaluate its effectiveness and security. The analysis demonstrates that the secure multiplication protocol exhibits higher computational efficiency in deeper multiplication operations. Experimental results on the Speech Command Database validate the effectiveness of the PPSC scheme in achieving accurate speech classification while preserving the privacy of data and model parameters. Furthermore, the proposed scheme achieves an accuracy that is 3.57% higher than that of the HEKWS scheme.

Key words: Fully Homomorphic Encryption, Privacy-Preserving, Two-Party Collaboration, Speech Classification, Secure Computing Protocol