This report provides a comprehensive analysis of the advancements in artificial image generation, deepfake detection, and explainable AI (XAI) techniques for this detection task. It is prepared by the Fraunhofer IOSB in collaboration with the German Federal Office for Information Security (BSI), aiming to address the challenges posed by AI-generated image content. The report was produced as part of BSI’s Project 658 (RealOrRender) and presents the results of work package 2.
This publication is provided in English only. This is due to its nature as a scientific publication and in alignment with standard practice in the research field of generative AI, where publications are published in English and where this work is to be placed contextually.