面向征信数据安全共享的SVM训练机制  

SVM Training Mechanism for Secure Sharing of Credit Data

作　　者：沈蒙[1] 张杰 祝烈煌[1] 徐恪[2,3] 张开翔 李辉忠 唐湘云 SHEN Mengl;ZHANG Jiel;ZHU Lie-Huang;XU Ke;ZHANG Kai-Xiang;LI Hui-Zhong;TANG Xiang-Yun(School of Compuler Science,Beijing Instilule of Technology,Beijing 100081;Deparlmenl of Compuler Science and Technology,Tsinghua Universily,Beijing 100084;Beijing Nalional Research Cenler for In formalion Science and Techrology,Beijing 100084;Shenzhen Qianhai Micro Public Bank Co.,Lld.,Shenzhen 518052)

机构地区：[1]北京理工大学计算机学院,北京100081 [2]清华大学计算机科学与技术系,北京100084 [3]北京信息科学与技术国家研究中心,北京100084 [4]深圳前海微众银行股份有限公司,深圳518052

出　　处：《计算机学报》2021年第4期696-708,共13页Chinese Journal of Computers

基　　金：国家重点研发计划(2018YFB0803405);国家自然科学基金(61902039,61872041,61932016);北京市自然科学基金(4192050);CCF腾讯犀牛鸟基金微众银行专项基金资助.

摘　　要：在征信行业中,征信数据的丰富性和多样性对信用评价极为重要.然而,征信机构尤其是小型征信机构拥有的征信数据存在内容不完整、种类不全、数量不充足等问题.同时由于征信数据价值高、隐私性强、易被非授权复制,征信机构之间难以直接共享数据.针对这一问题,本文提出了面向征信数据安全共享的SVM训练机制.首先共享数据经同态加密后存储在区块链上,保证数据不可篡改以及隐私安全.其次使用基于安全多方计算的支持向量机(SVM)在共享的加密数据上进行运算,保证在不泄露原始数据的条件下,训练信用评价模型.最后,通过真实数据集上的实验对本文所提出机制的可用性和性能进行验证.实验结果显示,相比于基于明文数据集训练出的模型,本文提出的机制在可接受时间内训练出的模型无准确率损失.同时,与其他同类隐私训练方案相比,本机制在实验数据集.上的计算耗时小于对比实验的5%,且无需可信第三方协助计算.In the credit reporting industry,the richness and diversity of credit reporting data is extremely important for the development of credit evaluation.However,credit data owned by credit reporting agencies,especially small credit reporting agencies,has issues like incomplete content,incomplete types,and insufficient instance numbers.Therefore,data sharing among credit reporting agencies is very important.In practical application scenarios,credit data has the characteristics of high value,strong privacy,and easy to be copied without authorization.These characteristics will cause great security challenges when sharing credit data.To solve this problem this paper proposes a SVM training mechanism for secure sharing of credit data.Meanwhile we design a system prototype based on this mechanism,as showed in Figure 3 in the manuscript.This mechanism is based on the consortium blockchain and the addition homomorphic encryption scheme Paillier.With the decentralization of blockchain technology,this mechanism does not need to rely on any trusted third party during model training.At the same time,through secure.collaborative computing between credit reporting agencies,the mechanism can meet the credit evaluation needs of the model trainer without revealing data privacy.Firstly,the shared data is stored on the blockchain and is encrypted to ensure that the data is secure and cannot be tampered.This process is completed through smart contracts,without the need for a third party as a data sharing platform.Secondly,based on the addition homomorphic encryption algorithm Paillier,this paper implements various secure operations in the SV M training process based on the stochastic gradient descent algorithm,and designs a secure SVM training algorithm according to the training process.The algorithm flow is shown in Algorithm 2.Based on this algorithm,the.credit reporting agencies participating to the calculation can perform operations on the shared encrypted data,ensuring that the model trainer can train the credit evaluation model wi

关 键 词：联盟链 征信数据 支持向量机 隐私保护 同态加密 

分 类 号：TP309[自动化与计算机技术—计算机系统结构]