Microsoft Research wants to make face-swapping deepfakes easier, but also make forged face swapping images easier to detect

2 min. read

Published onJanuary 7, 2020

published onJanuary 7, 2020

Share this article

Read our disclosure page to find out how can you help Windows Report sustain the editorial teamRead more

A pair of research papers jointly published by Microsoft Research and Peking University purpose a new face swapping AI in addition to a new facial forgery detector (viaVentureBeat). Both tools offer high-quality results relative to other services available, all while maintaining similar performance and can do so with substantially less data.

FaceShifteris the proposed face-swapping solution. Like its alternatives such as Reflect and FaceSwap, the newer tool is able to account for many variations including color, lighting, facial expression and other attributes. What sets it apart, however, is that the tool can also account for posture and angular differences, according to the authors of the published paper.

Faceshifter takes advantage of a generative adversarial network, or GAN, in which a generator ties to fool with a discriminator that the image is authentic. In contrast to existing tools, it also doesn’t need foreknowledge of the methods used in face-swapping or human supervision, instead creating grayscale images to determine if it can be decomposed into the two blended images from various sources.

In addition to the FaceShifter, the purposedFace X-Rayis a tool that detects counterfeit facial images. Face swaps and image manipulations are somewhat common for malicious purposes, which is what lead to the research and creation of the new AI tool for detecting fake images. The tool doesn’t use any previous knowledge on image manipulation, and was trained using FaceForensics++, a large video catalog with over a thousand original clips.

As it turn out, the tool was able to distinguish previously unseen images, and was able to reliably predict bending regions, although the team noted that this also means that it might not be able to detect wholly synthetic image and that it could potentially be defeated by adversarial samples.

What do you think about these new face-swapping and forgery detector tools? Feel free to leave a comment down below.

Radu Tyrsina

Radu Tyrsina has been a Windows fan ever since he got his first PC, a Pentium III (a monster at that time).

For most of the kids of his age, the Internet was an amazing way to play and communicate with others, but he was deeply impressed by the flow of information and how easily you can find anything on the web.

Prior to founding Windows Report, this particular curiosity about digital content enabled him to grow a number of sites that helped hundreds of millions reach faster the answer they’re looking for.

User forum

0 messages

Sort by:LatestOldestMost Votes

Comment*

Name*

Email*

Commenting as.Not you?

Save information for future comments

Comment

Radu Tyrsina

With KB5043178 to Release Preview Channel, Microsoft advises Windows 11 users to plug in when the battery is low#

Copilot in Outlook will generate personalized themes for you to customize the app#

Microsoft will raise the price of its 365 Suite to include AI capabilities#

Death Stranding Director’s Cut is now Xbox X|S at a huge discount#

Outlook will let users create custom account icons so they can tell their accounts apart easier#

Microsoft Research wants to make face-swapping deepfakes easier, but also make forged face swapping images easier to detect#

With KB5043178 to Release Preview Channel, Microsoft advises Windows 11 users to plug in when the battery is low

Copilot in Outlook will generate personalized themes for you to customize the app

Microsoft will raise the price of its 365 Suite to include AI capabilities

Death Stranding Director’s Cut is now Xbox X|S at a huge discount

Outlook will let users create custom account icons so they can tell their accounts apart easier

Microsoft Research wants to make face-swapping deepfakes easier, but also make forged face swapping images easier to detect