Privacy Amplification for Matrix Mechanisms

arXiv:2310.15526v2 Announce Type: replace
Abstract: Privacy amplification exploits randomness in data selection to provide tighter differential privacy (DP) guarantees. This analysis is key to DP-SGD's success in machine learning, but, is not readily applicable to the newer state-of-the-art algorithms. This is because these algorithms, known as DP-FTRL, use the matrix mechanism to add correlated noise instead of independent noise as in DP-SGD.
In this paper, we propose "MMCC", the first algorithm to analyze privacy amplification via sampling for any generic …

abstract algorithms analysis art arxiv cs.cr cs.lg data differential differential privacy exploits key machine machine learning matrix noise privacy randomness state success the matrix type