Differential privacy (DP) is considered a de-facto standard for protecting users' privacy in data analysis, machine, and deep learning. Existing DP-based privacy-preserving training approaches consist of adding noise to the clients' gradients before sharing them with the server. However, implementing DP on the gradient is not efficient as the privacy leakage increases by increasing the synchronization training epochs due to the composition theorem. Recently researchers were able to recover images used in the training dataset using Generative Regression Neural Network (GRNN) even when the gradient was protected by DP. In this paper, we propose two layers of privacy protection approach to overcome the limitations of the existing DP-based approaches. The first layer reduces the dimension of the training dataset based on Hensel's Lemma. We are the first to use Hensel's Lemma for reducing the dimension (i.e., compress) of a dataset. The new dimensionality reduction method allows reducing the dimension of a dataset without losing information since Hensel's Lemma guarantees uniqueness. The second layer applies DP to the compressed dataset generated by the first layer. The proposed approach overcomes the problem of privacy leakage due to composition by applying DP only once before the training; clients train their local model on the privacy-preserving dataset generated by the second layer. Experimental results show that the proposed approach ensures strong privacy protection while achieving good accuracy. The new dimensionality reduction method achieves an accuracy of 97%, with only 25 % of the original data size.
翻译:不同的隐私(DP) 被视为在数据分析、机器和深层学习中保护用户隐私的不准确标准。 现有的基于 DP 的隐私保护培训方法包括: 在与服务器共享客户梯度之前,在客户梯度上添加噪音; 但是, 在梯度上实施 DP 效率不高, 因为由于组成方言增加了同步培训分级, 隐私渗漏增加。 最近研究人员能够利用 引力回力神经网络( GRNNN) 来恢复培训数据集中使用的图像。 即使在梯度受到 DP 保护时, 也能够使用 引力回力回力神经网络( GRNNN) 。 在本文中, 我们提议了两层隐私保护方法, 以克服现有基于 DP 方法的局限性。 第一层将压缩数据数据集的尺寸缩小。 我们首先使用 Hensel 的 Lemmma 来降低数据集的维度( 缩放) 。 新的维度减少方法只能减少数据集的维度, 自Hensel's Lemma 保证其独特性。 第二层将 应用 压缩模型应用到 压缩模型, 以先使用 DP 生成的驱动 来显示生成数据 。 。 将生成生成数据生成的保存法 。