用二阶差异提升检测生成图像的准确率
A Difference-in-Difference Approach to Detecting AI-Generated Images
- 通过计算重建误差的差值，降低噪声干扰
- 在多个数据集上达到95%以上检测准确率
- 适合需要高可靠性的内容审核场景
扩散模型生成的图像已几乎无法与真实图像区分，引发滥用担忧。现有检测方法依赖输入图像与重建版本间的重建误差（一阶差异），但随着生成质量提升，该方法效果下降。本文提出一种新的双重差分方法：不直接使用重建误差，而是计算其差值（二阶差异），以实现方差压缩和检测精度提升。大量实验表明，该方法具备强泛化能力，在多种生成模型和数据集上均能可靠识别AI生成图像，检测准确率超过95%。
原文摘要 · Abstract (English)
Diffusion models are able to produce AI-generated images that are almost indistinguishable from real ones. This raises concerns about their potential misuse and poses substantial challenges for detecting them. Many existing detectors rely on reconstruction error -- the difference between the input image and its reconstructed version -- as the basis for distinguishing real from fake images. However, these detectors become less effective as modern AI-generated images become increasingly similar to real ones. To address this challenge, we propose a novel difference-in-difference method. Instead of directly using the reconstruction error (a first-order difference), we compute the difference in reconstruction error -- a second-order difference -- for variance reduction and improving detection accuracy. Extensive experiments demonstrate that our method achieves strong generalization performance, enabling reliable detection of AI-generated images in the era of generative AI.
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。