SuSy

First Author on (Bernabeu-Pérez et al., 2025) as part of the HPAI Group at Barcelona Supercomputing Center (Nov 2023 – Jan 2025), published at ECML PKDD 2025. Awarded the Best Applied AI Master’s Thesis Award (2024) by the Catalan Association of Artificial Intelligence and the Best Poster Award at the 18th RES Users Conference.

Developed SuSy, an open-source synthetic image detector built from the insights of this work.

Abstract

The continued release of increasingly realistic image generation models creates a demand for synthetic image detectors. To build effective detectors we must first understand how factors like data source diversity, training methodologies and image alterations affect their generalization capabilities. This work conducts a systematic analysis and uses its insights to develop practical guidelines for training robust synthetic image detectors. Model generalization capabilities are evaluated across different setups (e.g. scale, sources, transformations) including real-world deployment conditions. Through an extensive benchmarking of state-of-the-art detectors across diverse and recent datasets, we show that while current approaches excel in specific scenarios, no single detector achieves universal effectiveness. Critical flaws are identified in detectors, and workarounds are proposed to enable the deployment of real-world detector applications enhancing accuracy, reliability and robustness beyond the limitations of current systems.