发表机构
University of Arkansas; University of North Carolina at Charlotte（阿肯色大学; 北卡罗来纳大学夏洛特分校）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对文本到图像扩散模型公平性审计计算开销大的问题，提出基于因果抽象的审计工具，通过顶层模型高效预测跨引导尺度的公平性查询，并在Stable Diffusion 1.5和StayFair上验证了其准确性和效率。
AI 中文摘要
文本到图像扩散模型的公平性审计通常需要在多种采样配置下生成大量图像，这使得全面评估在计算上代价高昂。我们提出了一种基于因果抽象的审计工具，用于在分类器自由引导尺度干预下高效评估公平性。给定固定提示词和目标特征函数，我们将扩散过程表示为低层结构因果模型，并在抽象去噪状态上构建相应的顶层模型。我们刻画了投影因果结构，确立了公平性相关干预查询的可识别性，并提供了顶层模型保持该查询的充分条件。一个概率变换器将顶层模型实现为跨引导尺度的目标特征分布的摊销预测器。实验评估了分布保真度、公平性查询准确性和计算效率。我们展示了两个审计实例：一个使用标准Stable Diffusion 1.5，另一个使用StayFair（一种公平性增强的Stable Diffusion模型），以考察它们在不同引导尺度下的行为。
英文摘要
Fairness auditing of text-to-image diffusion models often requires generating large numbers of images across sampling configurations, making comprehensive evaluation computationally expensive. We propose a causal-abstraction-based audit instrument for efficiently evaluating fairness under interventions on the classifier-free guidance scale. Given a fixed prompt and a target feature function, we represent the diffusion process as a low-level structural causal model and construct a corresponding high-level model over abstract denoising states. We characterize the projected causal structure, establish identifiability of the fairness-relevant interventional query, and provide sufficient conditions under which the high-level model preserves this query. A probabilistic transformer implements the high-level model as an amortized predictor of target-feature distributions across guidance scales. Experiments evaluate distributional fidelity, fairness-query accuracy, and computational efficiency. We present two auditing demonstrations: one using standard Stable Diffusion 1.5 and another using StayFair, a fairness-enhanced Stable Diffusion model, to examine their behavior across guidance scales.
