提出一种无需训练的图像真伪检测框架，可输出可解释的概率分数。
RealStats: A Rigorous Real-Only Statistical Framework for Fake Image Detection
- 基于多个检测器的无训练统计量，通过假设检验生成置信度。
- 在多个数据集上实现95%以上的真实图像识别率，对分布偏移保持稳健。
- 适合需要可解释性与鲁棒性的真实场景应用，如媒体审核、司法取证。
随着生成模型持续演进，检测人工智能生成图像仍是关键挑战。尽管已有有效检测方法，但常缺乏形式化可解释性，且依赖对假内容的隐含假设，可能限制其对分布偏移的鲁棒性。本文提出一种严谨、基于统计的真伪图像检测框架，专注于生成相对于真实图像群体的可解释概率评分。该方法通过组合多个现有检测器的无训练统计量，计算一系列检验统计量的p值，并利用经典统计集成方法评估其与统一真实图像分布的吻合程度。该框架具备通用性、灵活性和无训练特性，适用于多样且不断演变的检测场景，显著提升检测鲁棒性。
原文摘要 · Abstract (English)
As generative models continue to evolve, detecting AI-generated images remains a critical challenge. While effective detection methods exist, they often lack formal interpretability and may rely on implicit assumptions about fake content, potentially limiting robustness to distributional shifts. In this work, we introduce a rigorous, statistically grounded framework for fake image detection that focuses on producing a probability score interpretable with respect to the real-image population. Our method leverages the strengths of multiple existing detectors by combining training-free statistics. We compute p-values over a range of test statistics and aggregate them using classical statistical ensembling to assess alignment with the unified real-image distribution. This framework is generic, flexible, and training-free, making it well-suited for robust fake image detection across diverse and evolving settings.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。