The misuse of generative AI in online disinformation campaigns highlights the urgent need for transparent and explainable detection systems. In this work, we investigate how detectors for AI-generated images can be more effective in providing human-understandable explanations for their predictions. To this end, we develop a suite of detectors with various architectures and fine-tuning strategies, trained on our large-scale photorealistic fake image dataset, AIText2Image, and assess their performance on state-of-the-art text-to-image AI generators. We integrate 16 different explainable AI (XAI) methods into our detection framework, and the visual explanations are comprehensively refined and evaluated through a novel approach that prioritizes human understanding of AI-generated images, using both textual and visual responses collected from a survey of 100 participants. This framework offers insights into visual-language cues in fake image detection and into the clarity of XAI methods from a human perspective, measuring the alignment of XAI outputs with human preferences.
@article{arxiv.2605.06143,
title = {AI-Generated Images: What Humans and Machines See When They Look at the Same Image},
author = {Silvia Poletti and Justin Ilyes and Marcel Hasenbalg and David Fischinger and Martin Boyer},
journal= {arXiv preprint arXiv:2605.06143},
year = {2026}
}
Comments
Included in the main conference proceedings published by Springer Nature (CCIS Series)