Machine Learning on Cloud With Blockchain: A Secure, Verifiable and Fair Approach to Outsource the Linear Regression

Linear Regression (LR) is a classical machine learning algorithm which has many applications in the cyber physical social systems (CPSS) to shape and simplify way we live, work, communicate. This paper focuses on data analysis for CPSS when applied. The training process of LR time-consuming since it involves complex matrix operations, especially gets large scale dataset In CPSS. Thus, how enable devices efficiently perform significant importance. To address this issue, paper, present secure, verifiable fair approach outsource an untrustworthy cloud-server. proposed scheme, computation inputs/outputs are obscured so that privacy sensitive information protected against Meanwhile, result from cloud-server verifiable. Also, fairness guaranteed by blockchain, ensures cloud paid only if he correctly performed outsourced workload. Based presented approach, exploited fair, secure outsourcing system Ethereum blockchain. We analysed our scheme theoretical experimental, all indicate valid, efficient.