Robust cross-dataset deepfake detection with multitask self-supervised learning

Batagelj, Borut (author), Kronovšek, Andrej (author), Štruc, Vitomir (author), Peer, Peter (author)

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.

• Language: English
• Keywords: deepfake detection, one-class learning, segmentation, localization
• Work type: Article
• Typology: 1.01 - Original Scientific Article
• Organization: FRI - Faculty of Computer and Information Science ; FE - Faculty of Electrical Engineering
• Publication status: Published
• Publication version: Version of Record
• Year: 2025
• Number of pages: Str. 1-6
• Numbering: Vol. , no.
• PID: 20.500.12556/RUL-171520
• UDC: 004.93
• ISSN on article: 2405-9595
• DOI: 10.1016/j.icte.2025.02.011
• COBISS.SI-ID: 227912963
• Publication date in RUL: 28.08.2025

Record is a part of a journal

• Title: ICT express
• Publisher: Elsevier
• ISSN: 2405-9595
• COBISS.SI-ID: 526132505

Licences

• License: CC BY-NC-ND 4.0, Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International
• Link: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Description: The most restrictive Creative Commons license. This only allows people to download and share the work for no commercial gain and for no other purposes.

Secondary language

• Language: Slovenian
• Keywords: zaznavanje globokih ponaredkov, enorazredno učenje, segmentacija, lokalizacija