Is Diffusion Model Safe? Severe Data Leakage via Gradient-Guided Diffusion Model

2024-06-13 · Jiayang Meng, Tao Huang, Hong Chen, Cuiping Li

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.

📄 PDF Abstract BibTeX arXiv:2406.09484

Code (0)

등록된 구현이 없습니다.

Tasks

Image ReconstructionmodelReconstruction Attack

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Deep Leakage from Gradients

2019-06-21 · NeurIPS 2019 12 · Ligeng Zhu, Zhijian Liu, Song Han

Exchanging gradients is a widely used method in modern multi-node machine learning system (e.g., distributed training, collaborative learning). For a long time, people believed that gradients are safe to share: i.e., the…

Mjolnir: Breaking the Shield of Perturbation-Protected Gradients via Adaptive Diffusion

2024-07-07 · Xuan Liu, Siqi Cai, Qihua Zhou, Song Guo 외

Perturbation-based mechanisms, such as differential privacy, mitigate gradient leakage attacks by introducing noise into the gradients, thereby preventing attackers from reconstructing clients' private data from the leak…

Denoising Federated Learning

Gradients Stand-in for Defending Deep Leakage in Federated Learning

2024-10-11 · H. Yi, H. Ren, C. Hu, Y. Li 외

Federated Learning (FL) has become a cornerstone of privacy protection, shifting the paradigm towards localizing sensitive data while only sending model gradients to a central server. This strategy is designed to reinfor…

Federated Learning

Diffusion-SDPO: Safeguarded Direct Preference Optimization for Diffusion Models

2025-11-05 · Minghao Fu, Guo-Hua Wang, Tianyu Cui, Qing-Guo Chen 외 arxiv

Text-to-image diffusion models deliver high-quality images, yet aligning them with human preferences remains challenging. We revisit diffusion-based Direct Preference Optimization (DPO) for these models and identify a cr…

APRIL: Finding the Achilles' Heel on Privacy for Vision Transformers

2021-12-28 · CVPR 2022 1 · Jiahao Lu, Xi Sheryl Zhang, Tianli Zhao, Xiangyu He 외

Federated learning frameworks typically require collaborators to share their local gradient updates of a common model instead of sharing training data to preserve privacy. However, prior works on Gradient Leakage Attacks…