Recognition: unknown
Exposing DeepFake Videos By Detecting Face Warping Artifacts
read the original abstract
In this work, we describe a new deep learning based method that can effectively distinguish AI-generated fake videos (referred to as {\em DeepFake} videos hereafter) from real videos. Our method is based on the observations that current DeepFake algorithm can only generate images of limited resolutions, which need to be further warped to match the original faces in the source video. Such transforms leave distinctive artifacts in the resulting DeepFake videos, and we show that they can be effectively captured by convolutional neural networks (CNNs). Compared to previous methods which use a large amount of real and DeepFake generated images to train CNN classifier, our method does not need DeepFake generated images as negative training examples since we target the artifacts in affine face warping as the distinctive feature to distinguish real and fake images. The advantages of our method are two-fold: (1) Such artifacts can be simulated directly using simple image processing operations on a image to make it as negative example. Since training a DeepFake model to generate negative examples is time-consuming and resource-demanding, our method saves a plenty of time and resources in training data collection; (2) Since such artifacts are general existed in DeepFake videos from different sources, our method is more robust compared to others. Our method is evaluated on two sets of DeepFake video datasets for its effectiveness in practice.
This paper has not been read by Pith yet.
Forward citations
Cited by 6 Pith papers
-
Venus-DeFakerOne: Unified Fake Image Detection & Localization
DeFakerOne integrates InternVL2 and SAM2 into a single model that achieves state-of-the-art results on 39 detection and 9 localization benchmarks for unified fake image detection and localization.
-
Which Face and Whose Identity? Solving the Dual Challenge of Deepfake Proactive Forensics in Multi-Face Scenarios
DAWF embeds identity watermarks via a parallel multi-face architecture and uses selective loss to answer which face was forged and whose identity was used.
-
Unveiling Deepfakes: A Frequency-Aware Triple Branch Network for Deepfake Detection
A frequency-aware triple-branch network with mutual information-based decoupling and fusion losses achieves state-of-the-art deepfake detection across six benchmarks.
-
DeFakeQ: Enabling Real-Time Deepfake Detection on Edge Devices via Adaptive Bidirectional Quantization
DeFakeQ introduces an adaptive bidirectional quantization method tailored for deepfake detectors that maintains detection accuracy while enabling real-time performance on resource-constrained edge devices.
-
Attribution-Guided Multimodal Deepfake Detection via Cross-Modal Forensic Fingerprints
AMDD achieves 99.7% balanced accuracy and 99.8% AUC on FakeAVCeleb by using cross-modal forensic fingerprint consistency loss to align generator-specific artifacts across modalities while also reporting 95.9% attribut...
-
M3D-Net: Multi-Modal 3D Facial Feature Reconstruction Network for Deepfake Detection
M3D-Net reconstructs 3D facial features from RGB images and fuses them with RGB features through attention-based modules to achieve claimed state-of-the-art deepfake detection.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.