2025/05/16 by Florinel-Alin Croitoru, Croitoru, Florinel-Alin, Vlad Hondru +9
Computer Science · #Artificial Intelligence (cs.AI) #Computer Vision and Pattern Recognition (cs.CV) #Digital Media Forensic Detection #FOS: Computer and information sciences #Generative Adversarial Networks and Image Synthesis #Image and Video Quality Assessment #Machine Learning (cs.LG) #Multimedia (cs.MM)
paper · pdf · doi:10.48550/arxiv.2505.11109
openalex publication_date 2025/05/16 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
We present the first large-scale open-set benchmark for multilingual audio-video deepfake detection. Our dataset comprises over 250 hours of real and fake videos across eight languages, with 60% of data being generated. For each language, the fake videos are generated with seven distinct deepfake generation models, selected based on the quality of the generated content. We organize the training, validation and test splits such that only a subset of the chosen generative models and languages are available during training, thus creating several challenging open-set evaluation setups. We perform experiments with various pre-trained and fine-tuned deepfake detectors proposed in recent literature. Our results show that state-of-the-art detectors are not currently able to maintain their performance levels when tested in our open-set scenarios. We publicly release our data and code at: https://huggingface.co/datasets/unibuc-cs/MAVOS-DD.