扩散模型的差分隐私微调
Differentially Private Fine-Tuning of Diffusion Models
AI总结：
针对扩散模型差分隐私微调中隐私与效用的权衡问题，提出一种参数高效微调策略，通过最小化可训练参数数量，在CelebA-64等数据集上以极小隐私预算实现SOTA合成性能。
摘要：
将差分隐私（Differential Privacy, DP）与扩散模型（Diffusion Models, DMs）相结合是一个充满前景但极具挑战的前沿领域，这主要是因为DMs强大的记忆能力带来了重大的隐私风险。差分隐私为在模型训练过程中保护单个数据点提供了一个严格的框架，其中差分隐私随机梯度下降（DP-SGD）是一种突出的实现方式。扩散方法将图像生成分解为迭代步骤，在理论上与DP的增量噪声添加机制非常契合。尽管存在这种天然的契合性，但DMs独特的架构需要定制化的方法来有效平衡隐私与效用的权衡。该领域的最新进展凸显了通过在公开数据（即ImageNet）上预训练并在私有数据上微调来生成高质量合成数据的潜力，然而，在优化DP设置中的权衡方面存在明显的研究空白，特别是在参数效率和模型可扩展性方面。我们的工作通过提出一种针对私有扩散模型优化的参数高效微调策略来解决这一问题，该策略最小化可训练参数的数量以增强隐私与效用的权衡。我们通过实验证明，我们的方法在DP合成中实现了最先进的性能，在广泛研究的数据集上显著超越了之前的基准（例如，在CelebA-64数据集上，仅使用0.47M个可训练参数，在较小的隐私预算下实现了比之前最先进方法超过35%的提升）。匿名代码可在 https://anonymous.4open.science/r/DP-LORA-F02F 获取。
英文摘要：
The integration of Differential Privacy (DP) with diffusion models (DMs) presents a promising yet challenging frontier, particularly due to the substantial memorization capabilities of DMs that pose significant privacy risks. Differential privacy offers a rigorous framework for safeguarding individual data points during model training, with Differential Privacy Stochastic Gradient Descent (DP-SGD) being a prominent implementation. Diffusion method decomposes image generation into iterative steps, theoretically aligning well with DP's incremental noise addition. Despite the natural fit, the unique architecture of DMs necessitates tailored approaches to effectively balance privacy-utility trade-off. Recent developments in this field have highlighted the potential for generating high-quality synthetic data by pre-training on public data (i.e., ImageNet) and fine-tuning on private data, however, there is a pronounced gap in research on optimizing the trade-offs involved in DP settings, particularly concerning parameter efficiency and model scalability. Our work addresses this by proposing a parameter-efficient fine-tuning strategy optimized for private diffusion models, which minimizes the number of trainable parameters to enhance the privacy-utility trade-off. We empirically demonstrate that our method achieves state-of-the-art performance in DP synthesis, significantly surpassing previous benchmarks on widely studied datasets (e.g., with only 0.47M trainable parameters, achieving a more than 35% improvement over the previous state-of-the-art with a small privacy budget on the CelebA-64 dataset). Anonymous codes available at https://anonymous.4open.science/r/DP-LORA-F02F.
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。
