用误差反馈优化生成高隐私保障的高质量图像，打破隐私与实用的权衡困境。
Differential Privacy Image Generation with Reconstruction Loss and Noise Injection Using an Error Feedback SGD
- 引入误差反馈梯度下降结合重建损失与噪声注入，提升生成质量。
- 在相同隐私预算下，图像质量显著优于现有方法，三基准上均达顶尖水平。
- 适用于对隐私敏感的图像生成场景，如医疗或金融数据合成。
传统数据遮蔽技术（如匿名化）难以在保障数据效用的同时实现理想隐私保护。合成数据因能生成大量训练样本并防止真实数据泄露而日益重要，但现有方法仍面临隐私与实用性之间的反复权衡。本文提出一种新型差分隐私图像生成框架，采用误差反馈随机梯度下降（EFSGD）方法，并在训练中引入重建损失与噪声注入机制。实验表明，在相同隐私预算下，本方法生成的图像在质量和可用性上均显著优于现有工作。在灰度与彩色图像上均表现优异，于三个基准数据集（MNIST、Fashion-MNIST、CelebA）上几乎所有指标均达到当前最优性能。
原文摘要 · Abstract (English)
Traditional data masking techniques such as anonymization cannot achieve the expected privacy protection while ensuring data utility for privacy-preserving machine learning. Synthetic data plays an increasingly important role as it generates a large number of training samples and prevents information leakage in real data. The existing methods suffer from the repeating trade-off processes between privacy and utility. We propose a novel framework for differential privacy generation, which employs an Error Feedback Stochastic Gradient Descent(EFSGD) method and introduces a reconstruction loss and noise injection mechanism into the training process. We generate images with higher quality and usability under the same privacy budget as the related work. Extensive experiments demonstrate the effectiveness and generalization of our proposed framework for both grayscale and RGB images. We achieve state-of-the-art results over almost all metrics on three benchmarks: MNIST, Fashion-MNIST, and CelebA.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。