‘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."

​There are two kinds of failure – but only one is honorable

Malcolm Gladwell teaches "Get over yourself and get to work" for Big Think Edge.

Big Think Edge
  • Learn to recognize failure and know the big difference between panicking and choking.
  • At Big Think Edge, Malcolm Gladwell teaches how to check your inner critic and get clear on what failure is.
  • Subscribe to Big Think Edge before we launch on March 30 to get 20% off monthly and annual memberships.
Keep reading Show less

Why are so many objects in space shaped like discs?

It's one of the most consistent patterns in the unviverse. What causes it?

Videos
  • Spinning discs are everywhere – just look at our solar system, the rings of Saturn, and all the spiral galaxies in the universe.
  • Spinning discs are the result of two things: The force of gravity and a phenomenon in physics called the conservation of angular momentum.
  • Gravity brings matter together; the closer the matter gets, the more it accelerates – much like an ice skater who spins faster and faster the closer their arms get to their body. Then, this spinning cloud collapses due to up and down and diagonal collisions that cancel each other out until the only motion they have in common is the spin – and voila: A flat disc.

Scientists study tattooed corpses, find pigment in lymph nodes

It turns out, that tattoo ink can travel throughout your body and settle in lymph nodes.

17th August 1973: An American tattoo artist working on a client's shoulder. (Photo by F. Roy Kemp/BIPs/Getty Images)
popular

In the slightly macabre experiment to find out where tattoo ink travels to in the body, French and German researchers recently used synchrotron X-ray fluorescence in four "inked" human cadavers — as well as one without. The results of their 2017 study? Some of the tattoo ink apparently settled in lymph nodes.


Image from the study.

As the authors explain in the study — they hail from Ludwig Maximilian University of Munich, the European Synchrotron Radiation Facility, and the German Federal Institute for Risk Assessment — it would have been unethical to test this on live animals since those creatures would not be able to give permission to be tattooed.

Because of the prevalence of tattoos these days, the researchers wanted to find out if the ink could be harmful in some way.

"The increasing prevalence of tattoos provoked safety concerns with respect to particle distribution and effects inside the human body," they write.

It works like this: Since lymph nodes filter lymph, which is the fluid that carries white blood cells throughout the body in an effort to fight infections that are encountered, that is where some of the ink particles collect.

Image by authors of the study.

Titanium dioxide appears to be the thing that travels. It's a white tattoo ink pigment that's mixed with other colors all the time to control shades.

The study's authors will keep working on this in the meantime.

“In future experiments we will also look into the pigment and heavy metal burden of other, more distant internal organs and tissues in order to track any possible bio-distribution of tattoo ink ingredients throughout the body. The outcome of these investigations not only will be helpful in the assessment of the health risks associated with tattooing but also in the judgment of other exposures such as, e.g., the entrance of TiO2 nanoparticles present in cosmetics at the site of damaged skin."

Photo by Alina Grubnyak on Unsplash
Mind & Brain

Do human beings have a magnetic sense? Biologists know other animals do. They think it helps creatures including bees, turtles and birds navigate through the world.

Keep reading Show less