{"ID":3050034,"CreatedAt":"2026-06-04T02:13:16.786527022Z","UpdatedAt":"2026-06-06T11:59:53.540122282Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2606.04863","arxiv_id":"2606.04863","title":"IRIS-GAN: Staged Specialist Detection of Deepfake Faces","abstract":"We introduce IRIS-GAN, a specialist forensic detector for synthetic face images under cross-generator shift. Rather than addressing universal synthetic-image detection, we focus on faces generated by generative adversarial networks (GANs), which are state-of-the-art in deepfake content, and train the detector through staged exposure to increasingly demanding GAN families while retaining earlier generators. The final model reaches fake-detection rates above 99% across the GAN families considered and classifies an external real-face dataset with 98.9% accuracy. Grad-CAM analysis further reveals measurable generator-dependent spatial response patterns, which remain informative for a secondary heatmap-only classifier. Out-of-family tests on diffusion-generated faces confirm that IRIS-GAN is a specialist detector, with some capability to reach non-GAN deepfakes. These results establish staged training as an effective strategy for robust GAN-face forensics.","short_abstract":"We introduce IRIS-GAN, a specialist forensic detector for synthetic face images under cross-generator shift. Rather than addressing universal synthetic-image detection, we focus on faces generated by generative adversarial networks (GANs), which are state-of-the-art in deepfake content, and train the detector through s...","url_abs":"https://arxiv.org/abs/2606.04863","url_pdf":"https://arxiv.org/pdf/2606.04863v1","authors":"[\"Jaume M. Trenchs\",\"Veronica Sanz\"]","published":"2026-06-03T13:29:24Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Diffusion Model\",\"Generative Adversarial Network\"]","has_code":false}