Is JPEG AI going to change image forensics?

TL;DR

This paper examines how JPEG AI, a neural image compression standard, impacts image forensics by reducing detector performance and highlighting the need for more robust forensic methods.

Contribution

It provides a comprehensive analysis of JPEG AI's counter-forensic effects, demonstrating its impact on existing forensic detectors and emphasizing the need for improved techniques.

Findings

JPEG AI reduces the accuracy of state-of-the-art forensic detectors

Neural compression artifacts mimic manipulation signatures

Forensic tools need to adapt to neural compression artifacts

Abstract

In this paper, we investigate the counter-forensic effects of the new JPEG AI standard based on neural image compression, focusing on two critical areas: deepfake image detection and image splicing localization. Neural image compression leverages advanced neural network algorithms to achieve higher compression rates while maintaining image quality. However, it introduces artifacts that closely resemble those generated by image synthesis techniques and image splicing pipelines, complicating the work of researchers when discriminating pristine from manipulated content. We comprehensively analyze JPEG AI's counter-forensic effects through extensive experiments on several state-of-the-art detectors and datasets. Our results demonstrate a reduction in the performance of leading forensic detectors when analyzing content processed through JPEG AI. By exposing the vulnerabilities of the available forensic tools, we aim to raise the urgent need for multimedia forensics researchers to include JPEG AI images in their experimental setups and develop robust forensic techniques to distinguish between neural compression artifacts and actual manipulations.