扩散模型安全吗？通过梯度引导扩散模型造成的严重数据泄露
Is Diffusion Model Safe? Severe Data Leakage via Gradient-Guided Diffusion Model
AI总结：
针对梯度泄露攻击受限于低分辨率的问题，提出梯度引导扩散模型微调的重建攻击，可从泄露梯度中窃取512×512高分辨率私有图像，并在精度、效率及抗差分隐私方面优于现有SOTA。
摘要：
梯度泄露已被认定为现代图像处理系统中隐私泄露的一个潜在来源，攻击者可从泄露的梯度中完全重建训练图像。然而，现有方法仅限于重建低分辨率图像，图像处理系统的数据泄露风险尚未得到充分探究。本文利用扩散模型，提出一种创新的梯度引导微调方法，并引入一种新型重建攻击，能够通过泄露的梯度从图像处理系统中窃取私有的高分辨率图像，从而造成严重数据泄露。我们的攻击方法易于实现，且几乎不需要先验知识。实验结果表明，当前重建攻击最多只能窃取分辨率为128×128像素的图像，而我们的攻击方法能够成功恢复并窃取分辨率最高达512×512像素的图像。在图像重建的像素级准确性和时间效率方面，我们的攻击方法均显著优于SOTA攻击基线。此外，我们的攻击可在一定程度上使差分隐私失效。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
