Using Log Scaled Fourier Transformations for Deepfake Detection
Abstract
Deepfakes, synthetic pieces of media, have taken over our online ecosystem in recent years, posing a significant threat to our digital security. This paper discusses the idea of implementing a log-based fourier transformation for deepfake detection. By converting images to the frequency domain during preprocessing, the transformation highlights subtle imbalances across the pixel patterns of deep fake images. Experimental results show noticeable changes in transformed deepfakes. Further research measured high accuracy for models trained and tested on frequency images. In conclusion, these results show a promising future for frequency analysis, at the forefront in deepfake detection.
Downloads
Published
Data Availability Statement
The dataset used to trained the model is publicly available here. The model code, that I wrote, is not publicly available.
Issue
Section
License
Copyright (c) 2026 Intersect: The Stanford Journal of Science, Technology, and Society
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
Authors who publish with this journal agree to the following terms:- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
