Privacy-Preserving Matrix Factorization for Recommendation Systems using Gaussian Mechanism. (arXiv:2304.09096v1 [cs.IR])

Building a recommendation system involves analyzing user data, which can
potentially leak sensitive information about users. Anonymizing user data is
often not sufficient for preserving user privacy. Motivated by this, we propose
a privacy-preserving recommendation system based on the differential privacy
framework and matrix factorization, which is one of the most popular algorithms
for recommendation systems. As differential privacy is a powerful and robust
mathematical framework for designing privacy-preserving machine learning
algorithms, it is possible to prevent adversaries from extracting …

adversaries adversary algorithms data differential privacy framework information leak machine machine learning machine learning algorithms matrix popular privacy sensitive information system systems user data user privacy