检测AI生成图像时，现有方法依赖全局伪影而非局部合成内容。
AI-Generated Image Detectors Overrely on Global Artifacts: Evidence from Inpainting Exchange
- 通过交换编辑区域外的原始像素，隔离全局伪影影响
- 顶级检测器准确率从91%暴跌至55%，接近随机水平
- 适合关注检测鲁棒性与内容感知模型的研究者
现代深度学习修复技术可实现逼真的局部图像修改，对可靠检测构成挑战。我们发现当前检测器主要依赖修复产生的全局伪影，而非局部合成内容。这是因为基于VAE的重建会在整张图像（包括未编辑区域）引发细微但普遍的频谱偏移。为此，我们提出Inpainting Exchange（INP-X）操作：在保留合成内容的同时，恢复非编辑区域的原始像素。我们构建了包含9万张图像的测试集（含真实、修复及交换图像），评估该现象。在此干预下，预训练的顶尖检测器（含商用模型）准确率大幅下降（如从91%降至55%），常接近随机水平。我们提供理论分析，指出该行为与VAE信息瓶颈导致的高频衰减相关。研究强调需发展内容感知检测方法。在本数据集上训练可提升泛化与定位能力。数据集与代码已公开于https://github.com/emirhanbilgic/INP-X。
原文摘要 · Abstract (English)
Modern deep learning-based inpainting enables realistic local image manipulation, raising critical challenges for reliable detection. However, we observe that current detectors primarily rely on global artifacts that appear as inpainting side effects, rather than on locally synthesized content. We show that this behavior occurs because VAE-based reconstruction induces a subtle but pervasive spectral shift across the entire image, including unedited regions. To isolate this effect, we introduce Inpainting Exchange (INP-X), an operation that restores original pixels outside the edited region while preserving all synthesized content. We create a 90K test dataset including real, inpainted, and exchanged images to evaluate this phenomenon. Under this intervention, pretrained state-of-the-art detectors, including commercial ones, exhibit a dramatic drop in accuracy (e.g., from 91\% to 55\%), frequently approaching chance level. We provide a theoretical analysis linking this behavior to high-frequency attenuation caused by VAE information bottlenecks. Our findings highlight the need for content-aware detection. Indeed, training on our dataset yields better generalization and localization than standard inpainting. Our dataset and code are publicly available at https://github.com/emirhanbilgic/INP-X.
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。