安全多方学习:从安全计算到安全学习  

Secure Multi-Party Learning:From Secure Computation to Secure Learning

作　　者：韩伟力[1] 宋鲁杉 阮雯强 林国鹏 汪哲轩 HAN Wei-Li;SONG Lu-Shan;RUAN Wen-Qiang;LIN Guo-Peng;WANG Zhe-Xuan(School of Computer Science,Fudan University,Shanghai 200438)

机构地区：[1]复旦大学计算机科学技术学院,上海200438

出　　处：《计算机学报》2023年第7期1494-1512,共19页Chinese Journal of Computers

基　　金：国家自然科学基金项目“可编程安全多方学习机制及优化方法研究”(62172100);上海市科委“科技创新行动计划”项目“基于大数据的电信网络诈骗受害人群评估与防范技术研究”(21DZ1201400)资助。

摘　　要：如何在保护原始数据隐私的前提下,利用分散在多方的数据,高效且安全地完成高质量的机器学习模型训练和预测成为当前安全多方计算和机器学习两个研究方向的一个共同研究热点.本文在调研这一研究热点最新进展的基础上,提出安全多方学习这一概念.作为一个安全攸关软件工程领域的研究主题,安全多方学习是指基于安全多方计算实现隐私保护机器学习的方法、框架与平台.本文分析了安全多方学习中的安全模型、系统部署方式和功能场景,从底层安全多方计算原语和隐私保护技术入手,对现有安全多方学习框架进行了系统全面综述.首先,本文根据所使用的底层技术将安全多方学习框架分成了四类,并从计算复杂度、通信轮次、通信量、线性操作效率、非线性操作效率、支持的功能场景6个方面总结了不同安全多方学习框架的特点.进一步地,本文调研了38个典型的安全多方学习框架,根据支持的参与方数量、安全模型、功能场景,支持的机器学习模型,支持的激活函数,所实现的池化方式以及准确率等要素对它们进行对比,以展示它们的优势和局限.最后,本文分析了安全多方学习与其他隐私保护机器学习技术之间的区别,给出了安全多方学习提高安全性、可证明安全、提高性能和效率以及安全多方学习框架间的互联互通等方面的未来发展方向.How to leverage the data distributed among/between multiple parties to efficiently and securely enforce high-performance machine learning training and inference with privacy preservation has become a hot spot of two research topics,i.e.,secure multi-party computation and machine learning.This paper proposes the concept of secure multi-party learning based on the investigation of the latest developments in the hot spot.Secure multi-party learning,a research topic in(secure)software engineering rather than cryptography,hereby refers to the methods,frameworks,and platforms that enforce privacy-preserving machine learning based on secure multi-party computation.It enables multiple parties to perform secure training and secure inference of machine learning models without directly leveraging their plaintext data and any private information beyond the final result.Therefore,secure multi-party learning can be applied to several practical fields involving private data,such as risk control in the financial field and medical diagnosis.Researchers have proposed a dozen of secure multi-party learning frameworks recently.Considering the rapid development of secure multi-party learning,a comprehensive and systematic survey,which covers the underlying technologies and classification of secure multi-party learning frameworks,is still absent so far.Therefore,this paper is motivated to conduct a literature review of the categories,characteristics,and frameworks of secure multi-party learning to help researchers choose suitable secure multi-party learning frameworks for various scenarios,further identify research gaps,and improve the weaknesses of secure multi-party learning frameworks.This paper analyzes the security models,system deployment methods,and functional scenarios in secure multi-party learning and starts with the underlying secure multi-party computation primitives and the privacy-preserving technologies to summarize secure multi-party learning frameworks systematically and comprehensively.The underlying technologies use

关 键 词：安全多方学习 机器学习 数据隐私 安全多方计算 隐私保护机器学习 访问控制 

分 类 号：TP309[自动化与计算机技术—计算机系统结构]