Open AccessProceedings Article
Exposing DeepFake Videos By Detecting Face Warping Artifacts
Yuezun Li,Siwei Lyu +1 more
- 01 Nov 2018
pp 46-52
TL;DR: A new deep learning based method that can effectively distinguish AI-generated fake videos from real videos is described, which saves a plenty of time and resources in training data collection and is more robust compared to others.
read more
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.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
iCaps-Dfake: An Integrated Capsule-Based Model for Deepfake Image and Video Detection
TL;DR: A new deepfake detection approach, iCaps-Dfake, is proposed that competes with state-of-the-art techniques of deepfake video detection and addresses their low generalization problem.
47
Detecting deepfake videos based on spatiotemporal attention and convolutional LSTM
TL;DR: In this article , a novel Xception-LSTM algorithm is proposed by using spatiotemporal attention mechanism and convolutional long short-term memory (ConvLSTMs).
47
Deepfakes Generation and Detection: A Short Survey
TL;DR: In this paper , the authors present an overview of the techniques and works that have been carried out in recent years for deepfake and face manipulations, including identity swap, face reenactment, attribute manipulation, and entire face synthesis.
A review on fake news detection 3T’s: typology, time of detection, taxonomies
Shubhangi Rastogi,Divya Bansal +1 more
TL;DR: A comprehensive overview of false news detection can be found in this article , where the authors provide a clarity to problem definition by explaining different types of false information (like fake news, rumor, clickbait, satire, and hoax) with real-life examples.
UIA-ViT: Unsupervised Inconsistency-Aware Method based on Vision Transformer for Face Forgery Detection
Wanyi Zhuang,Qi Chu,Zhentao Tan,Qiankun Liu,Haojie Yuan,Changtao Miao,Zixiang Luo,Nenghai Yu +7 more
- 23 Oct 2022
TL;DR: A novel Unsupervised Inconsistency-Aware method based on Vision Transformer is proposed, called UIA-ViT, which only makes use of video-level labels and can learn inconsistency-aware feature without pixel-level annotations.
46
References
•Posted Content
Deep Residual Learning for Image Recognition
TL;DR: This work presents a residual learning framework to ease the training of networks that are substantially deeper than those used previously, and provides comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth.
117.9K
•Proceedings Article
Very Deep Convolutional Networks for Large-Scale Image Recognition
Karen Simonyan,Andrew Zisserman +1 more
- 04 Sep 2014
TL;DR: This work investigates the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting using an architecture with very small convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers.
102.6K
•Posted Content
Image-to-Image Translation with Conditional Adversarial Networks
TL;DR: Conditional Adversarial Network (CA) as discussed by the authors is a general-purpose solution to image-to-image translation problems, which can be used to synthesize photos from label maps, reconstructing objects from edge maps, and colorizing images, among other tasks.
15.5K
Dlib-ml: A Machine Learning Toolkit
TL;DR: dlib-ml contains an extensible linear algebra toolkit with built in BLAS support, and implementations of algorithms for performing inference in Bayesian networks and kernel-based methods for classification, regression, clustering, anomaly detection, and feature ranking.
•Proceedings Article
Unsupervised Image-to-Image Translation Networks
Ming-Yu Liu,Thomas M. Breuel,Jan Kautz +2 more
- 02 Mar 2017
TL;DR: This work makes a shared-latent space assumption and proposes an unsupervised image-to-image translation framework based on Coupled GANs that achieves state-of-the-art performance on benchmark datasets.