Differential privacy (DP) provides a formal privacy guarantee that prevents adversaries with access to machine learning models from extracting information about individual training points. Differentially private stochastic gradient descent (DPSGD) is the most popular training method with differential privacy in image recognition. However, existing DPSGD schemes lead to significant performance degradation, which prevents the application of differential privacy. In this paper, we propose a simulated annealing-based differentially private stochastic gradient descent scheme (SA-DPSGD) which accepts a candidate update with a probability that depends both on the update quality and on the number of iterations. Through this random update screening, we make the differentially private gradient descent proceed in the right direction in each iteration, and result in a more accurate model finally. In our experiments, under the same hyperparameters, our scheme achieves test accuracies 98.35%, 87.41% and 60.92% on datasets MNIST, FashionMNIST and CIFAR10, respectively, compared to the state-of-the-art result of 98.12%, 86.33% and 59.34%. Under the freely adjusted hyperparameters, our scheme achieves even higher accuracies, 98.89%, 88.50% and 64.17%. We believe that our method has a great contribution for closing the accuracy gap between private and non-private image classification.
翻译:差异隐私(DP) 提供了正式的隐私保障, 防止使用机器学习模型的对手获取关于个人培训点的信息。 差异私人随机更新筛选(DPSGD)是最受欢迎的培训方法,在图像识别方面有不同的隐私。 但是,现有的DPSGD计划导致显著性能退化,从而防止了差异隐私的适用。 在本文中,我们提议了模拟基于模拟的基于互不相同的私人随机性基底的梯底计划(SA-DPSGD),接受候选人更新的可能性取决于更新质量和迭代数。 通过随机更新筛选,我们使差异私人梯级下降(DPSGD)朝着每个迭代的正确方向发展,并最终形成一个更准确的模式。 在我们的实验中,在相同的超参数下,我们的计划在MNIST、FASAshionMNIST和CIFAR10等数据集(SA-DPSGD)上取得了98.92%的模拟匹配率, 与98.12%、86.33%和59. 34.4%的私人梯级数据分类结果相比,我们完全相信了98.