This Artificial Intelligence Paper Presents An Advanced Method For Differential Privacy In Image Recognition With Better Accuracy

This article discusses the use of differential privacy in image recognition and how the existing methods for differentially private deep learning need to be improved. To address this problem, a research team from Shanghai University in China suggests a simulated annealing-based differentially private stochastic gradient descent (SA-DPSGD) approach that accepts a candidate update with a probability that depends on the quality of the update and the number of iterations.