‘Deepfake’ technology can now create real-looking human faces

A new study from Nvidia researchers show just how far artificial image-generation technology has come in recent years.

  • In 2014, researchers introduced a novel approach to generating artificial images through something called a generative adversarial network.
  • Nvidia researchers combined that approach with something called style transfer to create AI-generated images of human faces.
  • This year, the Department of Defense said it had been developing tools designed to detect so-called 'deepfake' videos.

A new paper from researchers at Nvidia shows just how far AI image generation technology has come in the past few years. The results are pretty startling.

Take the image below. Can you tell which faces are real?

Karros et al.

Actually, all of the above images are fake, and they were produced by what the researchers call a style-based generator, which is a modified version of the conventional technology that's used to automatically generate images. To sum up quickly:

In 2014, a researcher named Ian Goodfellow and his colleagues wrote a paper outlining a new machine learning concept called generative adversarial networks. The idea, in simplified terms, involves pitting two neural networks against each other. One acts as a generator that looks at, say, pictures of dogs and then does its best to create an image of what it thinks a dog looks like. The other network acts as a discriminator that tries to tell fake images from real ones.

At first, the generator might produce some images that don't look like dogs, so the discriminator shoots them down. But the generator now knows a bit about where it went wrong, so the next image it creates is slightly better. This process continues until, in theory, the generator creates a good image of a dog.

What the Nvidia researchers did was add to their generative adversarial network some principles of style transfer, a technique that involves recomposing one image in the style of another. In style transfer, neural networks look at multiple levels of an image in order to discriminate between the content of the picture and its style, e.g. the smoothness of lines, thickness of brush stroke, etc.

Here are a couple examples of style transfer.

In the Nvidia study, the researchers were able to combine two real images of human faces to generate a composite of the two. This artificially generated composite had the pose, hair style, and general face shape of the source image (top row), while it had the hair and eye colors, and finer facial features, of the destination image (left-hand column).

The results are surprisingly realistic, for the most part.

Karros et al.

​Concerns over 'deepfake' technology

The ability to generate realistic artificial images, often called deepfakes when images are meant to look like recognizable people, has raised concern in recent years. After all, it's not hard to imagine how this technology could allow someone to create a fake video of, say, a politician saying something abhorrent about a certain group. This could lead to a massive erosion of the public's willingness to believe anything that's reported in the media. (As if concerns about 'fake news' weren't enough.)

To keep up with deepfake technology, the Department of Defense has been developing tools designed to detect deepfake videos.

"This is an effort to try to get ahead of something," said Florida senator Marco Rubio in July. "The capability to do all of this is real. It exists now. The willingness exists now. All that is missing is the execution. And we are not ready for it, not as a people, not as a political branch, not as a media, not as a country."

However, there might be a paradoxical problem with the government's effort.

"Theoretically, if you gave a [generative adversarial network] all the techniques we know to detect it, it could pass all of those techniques," David Gunning, the DARPA program manager in charge of the project, told MIT Technology Review. "We don't know if there's a limit. It's unclear."

Should you defend the free speech rights of neo-Nazis?

Former president of the ACLU Nadine Strossen discusses whether our society should always defend free speech rights, even for groups who would oppose such rights.

Sponsored by Charles Koch Foundation
  • Former ACLU president Nadine Strossen understands that protecting free speech rights isn't always a straightforward proposition.
  • In this video, Strossen describes the reasoning behind why the ACLU defended the free speech rights of neo-Nazis in Skokie, Illinois, 1977.
  • The opinions expressed in this video do not necessarily reflect the views of the Charles Koch Foundation, which encourages the expression of diverse viewpoints within a culture of civil discourse and mutual respect.
Keep reading Show less

Where the evidence of fake news is really hiding

When it comes to sniffing out whether a source is credible or not, even journalists can sometimes take the wrong approach.

Sponsored by Charles Koch Foundation
  • We all think that we're competent consumers of news media, but the research shows that even journalists struggle with identifying fact from fiction.
  • When judging whether a piece of media is true or not, most of us focus too much on the source itself. Knowledge has a context, and it's important to look at that context when trying to validate a source.
  • The opinions expressed in this video do not necessarily reflect the views of the Charles Koch Foundation, which encourages the expression of diverse viewpoints within a culture of civil discourse and mutual respect.
Keep reading Show less

Apple co-founder says we should all ditch Facebook — permanently

Steve Wozniak doesn't know if his phone is listening, but he's minimizing risks.

Photo by Bryan Steffy/Getty Images
Technology & Innovation
  • Steve Wozniak didn't hold back his feelings about the social media giant when stopped at an airport.
  • The Apple co-founder admitted that devices spying on his conversations is worrisome.
  • Wozniak deleted his Facebook account last year, recommending that "most people" should do the same.
Keep reading Show less

It’s just a sheet of glass. With AI.

A new paradigm for machine vision has just been demonstrated.

Image source: aleknext/Shutterstock
Technology & Innovation
  • Scientists have invented a way for a sheet of glass to perform neural computing.
  • The glass uses light patterns to identify images without a computer or power.
  • It's image recognition at the speed of light.
Keep reading Show less