FFR_FD: Effective and Fast Detection of DeepFakes Based on Feature Point Defects

TL;DR

This paper introduces FFR_FD, a fast and effective DeepFake detection method based on feature point defects, outperforming many existing DNN-based approaches with lower computational costs.

Contribution

The paper presents a novel feature point-based descriptor, FFR_FD, for DeepFake detection, which is efficient, effective, and applicable across various datasets.

Findings

FFR_FD outperforms many state-of-the-art DNN models.

DeepFake faces have fewer feature points than real faces.

The method is computationally efficient and suitable for mobile applications.

Abstract

The internet is filled with fake face images and videos synthesized by deep generative models. These realistic DeepFakes pose a challenge to determine the authenticity of multimedia content. As countermeasures, artifact-based detection methods suffer from insufficiently fine-grained features that lead to limited detection performance. DNN-based detection methods are not efficient enough, given that a DeepFake can be created easily by mobile apps and DNN-based models require high computational resources. For the first time, we show that DeepFake faces have fewer feature points than real ones, especially in certain facial regions. Inspired by feature point detector-descriptors to extract discriminative features at the pixel level, we propose the Fused Facial Region_Feature Descriptor (FFR_FD) for effective and fast DeepFake detection. FFR_FD is only a vector extracted from the face, and it can be constructed from any feature point detector-descriptors. We train a random forest classifier with FFR_FD and conduct extensive experiments on six large-scale DeepFake datasets, whose results demonstrate that our method is superior to most state of the art DNN-based models.