Is Diffusion Model Safe? Severe Data Leakage via Gradient-Guided Diffusion Model
This work addresses a critical privacy issue for users of image processing systems by demonstrating severe data leakage risks, representing a significant advancement over existing methods.
The paper tackles the problem of privacy breaches in image processing systems by proposing a gradient-guided fine-tuning method using diffusion models to reconstruct high-resolution training images from leaked gradients, achieving recovery of images up to 512x512 pixels and outperforming state-of-the-art baselines in accuracy and efficiency.
Gradient leakage has been identified as a potential source of privacy breaches in modern image processing systems, where the adversary can completely reconstruct the training images from leaked gradients. However, existing methods are restricted to reconstructing low-resolution images where data leakage risks of image processing systems are not sufficiently explored. In this paper, by exploiting diffusion models, we propose an innovative gradient-guided fine-tuning method and introduce a new reconstruction attack that is capable of stealing private, high-resolution images from image processing systems through leaked gradients where severe data leakage encounters. Our attack method is easy to implement and requires little prior knowledge. The experimental results indicate that current reconstruction attacks can steal images only up to a resolution of $128 \times 128$ pixels, while our attack method can successfully recover and steal images with resolutions up to $512 \times 512$ pixels. Our attack method significantly outperforms the SOTA attack baselines in terms of both pixel-wise accuracy and time efficiency of image reconstruction. Furthermore, our attack can render differential privacy ineffective to some extent.