Research on machine learning technology with privacy protection strategy in recommendation field

Abstract

Technologies such as machine learning can achieve accurate personalized recommendations. However, due to the collection and utilization of a large amount of user information in this process, people are widely worried about data security and privacy issues. This paper first introduces two key issues of privacy protection in the field of machine learning, namely data privacy and model privacy. On this basis, this paper introduces and analyzes homomorphic encryption, differential privacy and federated learning, and compares their advantages and disadvantages. Among them, homomorphic encryption technology has a large computational cost, differential privacy technology has a negative impact on system accuracy, and federated learning technology has a high training and communication cost. Therefore, it will be the future research direction to study more efficient and accurate recommendation models.