Diffusion models have shown their effectiveness in generation tasks by well-approximating the underlying probability distribution. However, diffusion models are known to suffer from an amplified inherent bias from the training data in terms of fairness. While the sampling process of diffusion models can be controlled by conditional guidance, previous works have attempted to find empirical guidance to achieve quantitative fairness. To address this limitation, we propose a fairness-aware sampling method called \textit{attribute switching} mechanism for diffusion models. Without additional training, the proposed sampling can obfuscate sensitive attributes in generated data without relying on classifiers. We mathematically prove and experimentally demonstrate the effectiveness of the proposed method on two key aspects: (i) the generation of fair data and (ii) the preservation of the utility of the generated data.

翻译：扩散模型通过良好逼近潜在概率分布，在生成任务中展现出有效性。然而，已知扩散模型在公平性方面会放大训练数据中固有的偏差。尽管扩散模型的采样过程可通过条件引导进行控制，但以往研究尝试通过经验性引导实现量化公平性。针对这一局限性，我们提出一种名为"属性切换"机制的公平感知采样方法。该方法无需额外训练，即可在不依赖分类器的情况下混淆生成数据中的敏感属性。我们从数学上证明并在实验中验证了该方法在以下两个关键方面的有效性：（i）生成公平数据；（ii）保持生成数据的效用性。