通过局部统计异常放大检测AI伪造图像，提升对细微缺陷的敏感度。
Micro-Defects Expose Macro-Fakes: Detecting AI-Generated Images via Local Distributional Shifts
- 引入可学习的局部取证签名，聚焦图像微小区域的统计异常。
- 利用最大均值差异量化真实与生成图像的分布差异，显著提升检测效果。
- 适合需要高精度识别深度伪造图像的研究者和安全应用开发者。
近年来的生成模型能够创造出高度逼真的图像，给区分真实与AI生成图像带来挑战。现有基于预训练特征提取器的检测方法往往过度依赖全局语义，难以捕捉关键的微小缺陷。本文提出一种名为微缺陷暴露宏观伪造（MDMF）的局部分布感知检测框架，将微观尺度的统计不规则性放大为宏观层面的分布差异。为避免局部取证线索被简单聚合所稀释，我们设计了可学习的补丁取证签名，将语义补丁嵌入投影至紧凑的取证潜在空间。随后使用最大均值差异（MMD）量化生成图像与真实图像间的分布差异。理论分析表明，当生成图像中存在局部取证信号时，基于补丁的建模能产生更显著的分布差异，从而实现更可靠的分离。大量实验表明，MDMF在多个基准上均持续优于基线检测器，验证了其通用有效性。
原文摘要 · Abstract (English)
Recent generative models can produce images that appear highly realistic, raising challenges in distinguishing real and AI-generated images. Yet existing detectors based on pre-trained feature extractors tend to over-rely on global semantics, limiting sensitivity to the critical micro-defects. In this work, we propose Micro-Defects expose Macro-Fakes (MDMF), a local distribution-aware detection framework that amplifies micro-scale statistical irregularities into macro-level distributional discrepancies. To avoid localized forensic cues being diluted by plain aggregation, we introduce a learnable Patch Forensic Signature that projects semantic patch embeddings into a compact forensic latent space. We then use Maximum Mean Discrepancy (MMD) to quantify distributional discrepancies between generated and real images. Our theory-grounded analysis shows that patch-wise modeling yields provably larger discrepancies when localized forensic signals are present in generated images, enabling more reliable separation from real images. Extensive experiments demonstrate that MDMF consistently outperforms baseline detectors across multiple benchmarks, validating its general effectiveness. Project page: https://zbox1005.github.io/MDMF-project/
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。