20.500.12556/RUL-171520 Robust cross-dataset deepfake detection with multitask self-supervised learning Deepfake detection is increasingly critical due to the rise of manipulated media. Existing methods often require extensive datasets and struggle with interpretability issues. To address these issues, this study introduces a novel one-class approach for detecting and localizing deepfake artifacts in videos, using authentic images to generate manipulated data for training. By integrating segmentation and leveraging convolutional neural networks with visual transformers, the method predicts both the presence and location of the generated manipulations. Experiments on seven deepfake datasets and emerging diffusion-based manipulations show that our approach consistently outperforms existing methods, demonstrating superior accuracy and localization capabilities. deepfake detection one-class learning segmentation localization zaznavanje globokih ponaredkov enorazredno učenje segmentacija lokalizacija true false true Angleški jezik Slovenski jezik Članek v reviji 2025-08-28 07:18:47 2025-08-28 07:18:48 2025-09-05 03:50:14 0000-00-00 00:00:00 2025 0 0 Str. 1-6 no. Vol. 2025 0000-00-00 Zaloznikova Objavljeno NiDoloceno 0000-00-00 0000-00-00 0000-00-00 004.93 2405-9595 10.1016/j.icte.2025.02.011 227912963 RAZ_Batagelj_Borut_2025.pdf RAZ_Batagelj_Borut_2025.pdf 1 2DE3980DE23EED21D98F2852C895ECD9 f34e9f3d1af25022f04268845ce3d11296d7c91f032740e2496c220d4ca5f170 da036c46-83ce-11f0-9328-0050569b8976 https://repozitorij.uni-lj.si/Dokument.php?lang=slv&id=214880 https://www.sciencedirect.com/science/article/pii/S240595952500027X?via%3Dihub 1 59b242e6-83ce-11f0-9328-0050569b8976 https://repozitorij.uni-lj.si/Dokument.php?lang=slv&id=214879 Fakulteta za računalništvo in informatiko Fakulteta za elektrotehniko 0 0 0