Orazio Pontorno, Mattia Litrico, Luca Guarnera, Mario Valerio Giuffrida, Sebastiano Battiato.\u00a0A\u03bcFlow: Leveraging Average Images for Improving Generalisation of Deepfake Faces Detectors.\u00a0European Conference in Computer Vision (2026).<\/p>\n\n\n\n
![\"\"](\"https:\/\/www.valeriogiuffrida.academy\/wp\/wp-content\/uploads\/2026\/08\/image_2026-08-20_113722308.png\")
<\/figure>\n\n\n<\/div>\n\n\n\nAbstract<\/h3>\n\n\n\n
Current generative models, including GANs and diffusion models, have reached an outstanding level of photorealism, posing significant risks to privacy and security. To ensure real-world applicability, deepfake detectors must generalise effectively to unseen generators. However, most existing approaches rely on supervised training with both real and fake images, which limits their generalisation especially across generators categories (e.g. GANs vs DMs). In this work, we introduce\u00a0\u03bcFlow, a one-class deepfake detector trained only on real images without relying on pseudo-deepfakes or synthetic artifacts. Our approach builds on the observation that averaging multiple images amplifies consistent generative traces, producing highly discriminative feature representations. We leverage this property by modelling the distribution of features extracted from averaged images and training a normalizing flow to align the feature space of individual images with this distribution. This alignment yields a likelihood-based criterion that separates real and fake samples while promoting strong generalisation. We evaluate\u00a0\u03bcFlow on a fully out-of-distribution setting, where both real and fake datasets are unseen during training. Experimental results show that our method significantly outperforms SOTA detectors. Project page: https:\/\/opontorno.github.io\/MuFlow.<\/p>\n<\/div>\n<\/div>\n\n\n\n
<\/p>\n","protected":false},"excerpt":{"rendered":"
Generating realistic images to accurately predict changes in the structure of brain MRI can be a crucial tool for clinicians. Such applications can help assess patients\u2019 outcomes and analyze how diseases progress at the individual level. However, existing methods developed for this task present some limitations. Some approaches attempt to model the distribution of MRI scans directly by conditioning the model on patients\u2019 ages, but they fail to explicitly capture the relationship between structural changes in the brain and time intervals, especially on age-unbalanced datasets. Other approaches simply rely on interpolation between scans, which limits their clinical application as they do not predict future MRIs. To address these challenges, we propose a Temporally-Aware Diffusion Model (TADM), which introduces a novel approach to accurately infer progression in brain MRIs. TADM learns the distribution of structural changes in terms of intensity differences between scans and combines the prediction of these changes with the initial baseline scans to generate future MRIs. Furthermore, during training, we propose to leverage a pre-trained Brain-Age Estimator (BAE) to refine the model\u2019s training process, enhancing its ability to produce accurate MRIs that match the expected age gap between baseline and generated scans. Our assessment, conducted on 634 subjects from the OASIS-3 dataset, uses similarity metrics and region sizes computed by comparing predicted and real follow-up scans on 3 relevant brain regions. TADM achieves large improvements over existing approaches, with an average decrease of 24% in region size error and an improvement of 4% in similarity metrics. These evaluations demonstrate the improvement of our model in mimicking temporal brain neurodegenerative progression compared to existing methods. We believe that our approach will significantly benefit clinical applications, such as predicting patient outcomes or improving treatments for patients. Our code is publicly available at https:\/\/github.com\/MattiaLitrico\/TADM-Temporally-Aware-Diffusion-Model-for-Neurodegenerative-Progression-on-Brain-MRI.<\/p>\n","protected":false},"author":1,"featured_media":1039,"parent":918,"menu_order":330,"comment_status":"closed","ping_status":"closed","template":"","meta":{"_acf_changed":false,"footnotes":""},"class_list":["post-1036","page","type-page","status-publish","has-post-thumbnail","hentry"],"acf":[],"_links":{"self":[{"href":"https:\/\/www.valeriogiuffrida.academy\/wp\/wp-json\/wp\/v2\/pages\/1036","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.valeriogiuffrida.academy\/wp\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/www.valeriogiuffrida.academy\/wp\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/www.valeriogiuffrida.academy\/wp\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.valeriogiuffrida.academy\/wp\/wp-json\/wp\/v2\/comments?post=1036"}],"version-history":[{"count":1,"href":"https:\/\/www.valeriogiuffrida.academy\/wp\/wp-json\/wp\/v2\/pages\/1036\/revisions"}],"predecessor-version":[{"id":1038,"href":"https:\/\/www.valeriogiuffrida.academy\/wp\/wp-json\/wp\/v2\/pages\/1036\/revisions\/1038"}],"up":[{"embeddable":true,"href":"https:\/\/www.valeriogiuffrida.academy\/wp\/wp-json\/wp\/v2\/pages\/918"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.valeriogiuffrida.academy\/wp\/wp-json\/wp\/v2\/media\/1039"}],"wp:attachment":[{"href":"https:\/\/www.valeriogiuffrida.academy\/wp\/wp-json\/wp\/v2\/media?parent=1036"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}