Skip to main content

Research Repository

Advanced Search

Exploring Dataset Diversity for GenAI Image Tampering Localisation in Digital Forensics

Thomson, Matthew; McKeown, Sean; Macfarlane, Rich; Leimich, Petra

Authors

Matthew Thomson



Abstract

Generative Artificial Intelligence (GenAI) has significantly increased the sophistication and ease of image tampering techniques, posing challenges for digital forensics in identifying manipulated images. A lack of dataset standardisation hinders the ability to effectively benchmark and compare GenAI detection and localisation techniques, reducing their reliability in digital forensic applications. This paper aims to address this gap by exploring the need for standardised criteria for datasets in digital forensics for benchmarking detection techniques through preliminary experiments.

To address the limited diversity in existing datasets, a small-scale dataset consisting of 240 tampered images, 20 masks and 20 authentic images was developed. This dataset includes four subject image classes (animals, objects, persons, scenery) and three inpainting tools (GLIDE, GalaxyAI, Photoshop). The dataset was tested against 13 localisation algorithms from the Image Forensics MATLAB Toolbox to determine the influencing components that should be considered in the standardisation of testing environments.

Among classes, the animals and persons categories achieved the highest F1-Scores and had a consistently higher performance over the other classes. Of the tools, GLIDE-generated images were consistently shown to be the most challenging to detect. These results lay the groundwork for identifying a set of criteria to develop robust testing environments, enabling the development of more accurate and reliable GenAI tampering detection and localisation techniques.

Citation

Thomson, M., McKeown, S., Macfarlane, R., & Leimich, P. (2025, April). Exploring Dataset Diversity for GenAI Image Tampering Localisation in Digital Forensics. Presented at The Digital Forensics Research Conference Europe (DFRWS EU 2025) Digital Forensics Doctoral Symposium (DFDS), Brno, Czech Republic

Presentation Conference Type Conference Paper (published)
Conference Name The Digital Forensics Research Conference Europe (DFRWS EU 2025) Digital Forensics Doctoral Symposium (DFDS)
Start Date Apr 1, 2025
End Date Apr 4, 2025
Acceptance Date Dec 14, 2024
Deposit Date Jan 10, 2025
Publisher Association for Computing Machinery (ACM)
Peer Reviewed Peer Reviewed
Keywords Digital Forensics, Artificial Intelligence (AI), Generative AI (GenAI), AI Manipulation, Inpainting, Image Forgery Localisation

This file is under embargo due to copyright reasons.

Contact repository@napier.ac.uk to request a copy for personal use.





You might also like



Downloadable Citations