CVAIJan 21

Differential Privacy Image Generation with Reconstruction Loss and Noise Injection Using an Error Feedback SGD

arXiv:2601.15061v1
Originality Incremental advance
AI Analysis

This addresses privacy-preserving image generation for machine learning applications, representing an incremental improvement over existing methods.

The paper tackles the privacy-utility trade-off in synthetic data generation by proposing a differential privacy framework using Error Feedback SGD with reconstruction loss and noise injection. The method achieves state-of-the-art results on MNIST, Fashion-MNIST, and CelebA benchmarks under the same privacy budget.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes