FSBI: Deepfakes Detection with Frequency Enhanced Self-Blended Images

TL;DR

This paper proposes FSBI, a deepfake detection method that uses frequency-enhanced self-blended images and wavelet transforms to improve detection accuracy and generalization across datasets.

Contribution

Introduces a novel FSBI approach utilizing self-blended images and frequency features for more robust deepfake detection, outperforming existing methods.

Findings

Outperforms state-of-the-art techniques on FF++ and Celeb-DF datasets.

Effective in cross-dataset evaluation scenarios.

Utilizes wavelet transforms to extract discriminative frequency features.

Abstract

Advances in deepfake research have led to the creation of almost perfect manipulations undetectable by human eyes and some deepfakes detection tools. Recently, several techniques have been proposed to differentiate deepfakes from realistic images and videos. This paper introduces a Frequency Enhanced Self-Blended Images (FSBI) approach for deepfakes detection. This proposed approach utilizes Discrete Wavelet Transforms (DWT) to extract discriminative features from the self-blended images (SBI) to be used for training a convolutional network architecture model. The SBIs blend the image with itself by introducing several forgery artifacts in a copy of the image before blending it. This prevents the classifier from overfitting specific artifacts by learning more generic representations. These blended images are then fed into the frequency features extractor to detect artifacts that can not be detected easily in the time domain. The proposed approach has been evaluated on FF++ and Celeb-DF datasets and the obtained results outperformed the state-of-the-art techniques with the cross-dataset evaluation protocol.