This paper proposes an original approach for the automatic detection of AI-generated images, using features derived from noise residuals artefacts. Contrary to most current research that leverages sophisticated deep learning models to further improve performance, this study highlights the distinct noise residual characteristics in deepfakes, facilitating the identification of AI-generative images. Our findings highlight some limitations of image models, which can be used for forensic analysis and for future AI-based text-to-image generative models. Broad numerical results on a large and diverse dataset show the interest of the identified features as well as the relevance of the present method.