# Frequency Masking for Universal Deepfake Detection Source: [Frequency Masking for Universal Deepfake Detection]() Collection index: [llms.txt]() Data updated: 2025-10-27T06:29:09.138Z Authors: Chandler Timm Doloriel, Ngai-Man Cheung Published: 2024-01-12T11:02:12.000Z ## Abstract We study universal deepfake detection. Our goal is to detect synthetic images from a range of generative AI approaches, particularly from emerging ones which are unseen during training of the deepfake detector. Universal deepfake detection requires outstanding generalization capability. Motivated by recently proposed masked image modeling which has demonstrated excellent generalization in self-supervised pre-training, we make the first attempt to explore masked image modeling for universal deepfake detection. We study spatial and frequency domain masking in training deepfake detectors. Based on empirical analysis, we propose a novel deepfake detector via frequency masking. Our focus on frequency domain is different from the majority, which primarily target spatial domain detection. Our comparative analyses reveal substantial performance gains over existing methods. Code and models are publicly available. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [AI-generated Video Detection on VidProM 2024 (test)](): AI-generated Video Detection; VidProM 2024 (test); Accuracy (Pika): 50.07. - [Video Forgery Detection on VidProm](): Video Forgery Detection; VidProm; Pika Score: 50.07. ## Original sources and implementation [Original paper]() [PDF]()