基于自适应裁剪的深度学习差分隐私保护方案OA

To address the issues of utility degradation in deep learning models under differential privacy protection and the gap between theoretical and actual privacy protection effectiveness,this paper proposes a deep learning differential privacy protection scheme based on adaptive clipping.The scheme optimizes the process through a four-step mechanism:firstly,gradient adaptive clipping controls the gradient magnitude during training by dynamically adjusting the gradient clipping threshold,thereby enabling the control of the magnitude of noise added subsequently;secondly,group label selection identifies the group with the smallest gradient as the privacy-preserving object,and more accurate privacy loss can be obtained by training this group;thirdly,optimized privacy loss calculation combines the gaussian mechanism based on subsampling to reduce the computational overhead of model privacy loss calculation;finally,optimized gradient adaptive descent realizes the adaptive descent of gradients by adjusting the conditional smoothing parameter,thus improving the usability of the model.Experiments were conducted on the VGG architecture using the MNIST,CIFAR-10,and Medical-MNIST datasets.The results show that the model accuracy rates after training with this scheme are 81.08％,72.30％,and 67.91％respectively,representing improvements of 15.60％,10.60％,and 9.71％compared to the traditional DPSGD,and 0.63％,2.50％,and 4.40％over the widely used Nadam algorithm in recent years.The model training efficiency has been improved by 35.5％and 39.4％,respectively.