提出三种检测JPEG AI图像的取证线索，区分真实压缩与生成图像。
Three Forensic Cues for JPEG AI Images
- 利用色彩通道相关性识别JPEG AI预处理痕迹。
- 发现重复压缩后失真差异减小，可检测重压缩。
- 通过潜在空间量化特征区分真实图像与生成图像。
JPEG标准广受欢迎，如今基于AI的压缩方法'JPEG AI'即将标准化。该方法在比特率低一个数量级的情况下仍能提供出色的图像质量。然而，传统JPEG取证工具无法适用于JPEG AI，且其伪影易与深度伪造图像混淆，亟需新取证方法。本文首次提出三种针对JPEG AI的取证线索：首先，揭示预处理引入了原始图像中不存在的颜色通道相关性；其次，发现重复压缩导致失真差异减小，可用于检测重压缩；第三，利用潜在空间中的量化特征，可区分经JPEG AI压缩的真实图像与合成图像。所提方法具可解释性，旨在推动对AI压缩图像的进一步研究。
原文摘要 · Abstract (English)
The JPEG standard was vastly successful. Currently, the first AI-based compression method ``JPEG AI'' will be standardized. JPEG AI brings remarkable benefits. JPEG AI images exhibit impressive image quality at bitrates that are an order of magnitude lower than images compressed with traditional JPEG. However, forensic analysis of JPEG AI has to be completely re-thought: forensic tools for traditional JPEG do not transfer to JPEG AI, and artifacts from JPEG AI are easily confused with artifacts from artificially generated images (``DeepFakes''). This creates a need for novel forensic approaches to detection and distinction of JPEG AI images. In this work, we make a first step towards a forensic JPEG AI toolset. We propose three cues for forensic algorithms for JPEG AI. These algorithms address three forensic questions: first, we show that the JPEG AI preprocessing introduces correlations in the color channels that do not occur in uncompressed images. Second, we show that repeated compression of JPEG AI images leads to diminishing distortion differences. This can be used to detect recompression, in a spirit similar to some classic JPEG forensics methods. Third, we show that the quantization of JPEG AI images in the latent space can be used to distinguish real images with JPEG AI compression from synthetically generated images. The proposed methods are interpretable for a forensic analyst, and we hope that they inspire further research in the forensics of AI-compressed images.
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。