Bridging the gap in differentially private model training
In today's world, machine learning (ML) models are becoming more ubiquitous. While they provide great utility, such models may sometimes accidentally remember sensitive information from their training data. Differential privacy (DP) offers a rigorous mathematical framework to protect user privacy by injecting "noise" during the model training procedure, making it harder for the model to remember information unique to individual data points. It is desirable to have techniques that provide the ...| research.google
