Is JPEG AI going to change image forensics?
Edoardo Daniele Cannas, Sara Mandelli, Nata\v{s}a Popovi\'c, Ayman, Alkhateeb, Alessandro Gnutti, Paolo Bestagini, Stefano Tubaro

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…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsDigital Media Forensic Detection
