Exposing Deep Fakes Using Inconsistent Head Poses

Xin Yang; Yuezun Li; Siwei Lyu

doi:10.1109/icassp.2019.8683164

Abstract

In this paper, we propose a new method to expose AI-generated fake face images or videos (commonly known as the Deep Fakes). Our method is based on the observations that Deep Fakes are created by splicing synthesized face region into the original image, and in doing so, introducing errors that can be revealed when 3D head poses are estimated from the face images. We perform experiments to demonstrate this phenomenon and further develop a classification method based on this cue. Using features based on this cue, an SVM classifier is evaluated using a set of real face images and Deep Fakes.

Keywords

Artificial intelligenceComputer scienceComputer visionFace (sociological concept)Support vector machineFacial recognition systemClassifier (UML)Face detectionPattern recognition (psychology)Deep learningHead (geology)Geology

Affiliated Institutions

Related Publications

From few to many: illumination cone models for face recognition under variable lighting and pose

Athinodoros S. Georghiades , Peter N. Belhumeur , David Kriegman

We present a generative appearance-based method for recognizing human faces under variation in lighting and viewpoint. Our method exploits the fact that the set of images of an ...

2001 IEEE Transactions on Pattern Analysis... 4906 citations

Deepfake Video Detection Using Recurrent Neural Networks

David Güera , Edward J. Delp

In recent months a machine learning based free software tool has made it easy to create believable face swaps in videos that leaves few traces of manipulation, in what are known...

2018 1117 citations

MesoNet: a Compact Facial Video Forgery Detection Network

Darius Afchar , Vincent Nozick , Junichi Yamagishi +1 more

This paper presents a method to automatically and efficiently detect face\ntampering in videos, and particularly focuses on two recent techniques used to\ngenerate hyper-realist...

2018 2018 IEEE International Workshop on I... 1471 citations

The SVM-Minus Similarity Score for Video Face Recognition

Lior Wolf , Noga Levy

Challenge, but also an opportunity to eliminate spurious similarities. Luckily, a major source of confusion in visual similarity of faces is the 3D head orientation, for which i...

2013 66 citations

Unsupervised Joint Alignment of Complex Images

Gary B. Huang , Vidit Jain , Erik Learned-Miller

Many recognition algorithms depend on careful positioning of an object into a canonical pose, so the position of features relative to a fixed coordinate system can be examined. ...

2007 344 citations

Publication Info

Year: 2019
Type: article
Pages: 8261-8265
Citations: 988
Access: Closed

External Links

View on DOI.org

Social Impact

Altmetric

Exposing Deep Fakes Using Inconsistent Head Poses

PlumX Metrics

Social media, news, blog, policy document mentions

Citation Metrics

988

OpenAlex

Cite This

APA Style

                            
                                    Xin Yang, 
                                
                                    Yuezun Li, 
                                
                                    Siwei Lyu
                                
                            (2019). 
                            Exposing Deep Fakes Using Inconsistent Head Poses. 
                            
                            , 8261-8265.
                            https://doi.org/10.1109/icassp.2019.8683164

Identifiers

DOI: 10.1109/icassp.2019.8683164