Design of Anti Machine Learning Malicious Node System Based on Blockchain

Abstract

AbstractIn order to solve the problem of security and privacy in machine learning, researchers have proposed many distributed solutions to protect data security and privacy, but the problem of anti malicious nodes in distributed machine learning system is still an open problem. Most of the existing distributed learning schemes solve the problem of malicious nodes by adding a disciplinary mechanism to the protocol. This method is based on two assumptions: 1. Participants give up the assumption of malicious behavior to maximize their own interests, and the calculation results can be verified only after the event occurs, which is not suitable for some scenarios requiring immediate verification; 2. Based on the assumption of a trusted third party, however, in practice, the credibility of the third party cannot be fully guaranteed. Using the trust mechanism of blockchain, this paper proposes an anti malicious node scheme based on smart contract, which realizes the whole process of model training in machine learning through smart contract to ensure that the machine learning model is not damaged by malicious nodes. This scheme takes the distributed model based on secure multi-party computing as the research model, stores the data involved in machine learning in the blockchain system, uses the smart contract of the blockchain to realize the data sharing, verification and training process, and writes the training results into the blockchain, so that the authorized users can aggregate the final model by obtaining the calculation results of each participant, Through experiments, compared with the traditional distributed machine learning model based on secure multi-party computing, and showed the advantages of this scheme.KeywordsBlockchainSmart contractDistributed learningMalicious nodesSecure multi-party computationRing signature