# Three Forensic Cues for JPEG AI Images

arXiv: https://arxiv.org/abs/2504.03191 · HTML: https://mlsanity.com/paper/2504.03191/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 18 of its 45 references that are in the map.
- First posted on arXiv 4 Apr 2025.

## Builds on (most cited first, 18 of 18)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Variational image compression with a scale hyperprior](https://mlsanity.com/paper/1802.01436/) (2018)
- [Joint Autoregressive and Hierarchical Priors for Learned Image Compression](https://mlsanity.com/paper/1809.02736/) (2018)
- [Leveraging Frequency Analysis for Deep Fake Image Recognition](https://mlsanity.com/paper/2003.08685/) (2020)
- [High-Fidelity Generative Image Compression](https://mlsanity.com/paper/2006.09965/) (2020)
- [On the detection of synthetic images generated by diffusion models](https://mlsanity.com/paper/2211.00680/) (2022)
- [Full Resolution Image Compression with Recurrent Neural Networks](https://mlsanity.com/paper/1608.05148/) (2016)
- [Intriguing properties of synthetic images: from generative adversarial networks to diffusion models](https://mlsanity.com/paper/2304.06408/) (2023)
- [High-Fidelity Image Compression with Score-based Generative Models](https://mlsanity.com/paper/2305.18231/) (2023)
- [RIGID: A Training-free and Model-Agnostic Framework for Robust AI-Generated Image Detection](https://mlsanity.com/paper/2405.20112/) (2024)
- [Aligned and Non-Aligned Double JPEG Detection Using Convolutional Neural Networks](https://mlsanity.com/paper/1708.00930/) (2017)
- [Training Strategies and Data Augmentations in CNN-based DeepFake Video Detection](https://mlsanity.com/paper/2011.07792/) (2020)
- [Block-level Double JPEG Compression Detection for Image Forgery Localization](https://mlsanity.com/paper/2003.09393/) (2020)
- [Is JPEG AI going to change image forensics?](https://mlsanity.com/paper/2412.03261/) (2024)
- [JPEG AI Image Compression Visual Artifacts: Detection Methods and Dataset](https://mlsanity.com/paper/2411.06810/) (2024)
- [A Taxonomy of Miscompressions: Preparing Image Forensics for Neural Compression](https://mlsanity.com/paper/2409.05490/) (2024)
- [Exploring adversarial robustness of JPEG AI: methodology, comparison and new methods](https://mlsanity.com/paper/2411.11795/) (2024)
- [Forensic Considerations for the High Efficiency Image File Format (HEIF)](https://mlsanity.com/paper/2006.08060/) (2020)

## Abstract (arXiv)

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.