Performances of Symmetric Loss for Private Data from Exponential Mechanism
This work addresses privacy-preserving machine learning by enhancing robustness in differential privacy techniques, though it appears incremental as it builds on existing methods.
The study investigated the robustness of symmetric loss for private data using the exponential mechanism, providing theoretical analysis and numerical guidance for privacy budgets across data scales, with experiments on CIFAR-10 showing traits of symmetric loss.
This study explores the robustness of learning by symmetric loss on private data. Specifically, we leverage exponential mechanism (EM) on private labels. First, we theoretically re-discussed properties of EM when it is used for private learning with symmetric loss. Then, we propose numerical guidance of privacy budgets corresponding to different data scales and utility guarantees. Further, we conducted experiments on the CIFAR-10 dataset to present the traits of symmetric loss. Since EM is a more generic differential privacy (DP) technique, it being robust has the potential for it to be generalized, and to make other DP techniques more robust.