‘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.

‘Deepfake’ technology can now create real-looking human faces
Karros et al.
  • 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."

Every 27.5 million years, the Earth’s heart beats catastrophically

Geologists discover a rhythm to major geologic events.

Credit: desertsolitaire/Adobe Stock
Surprising Science
  • It appears that Earth has a geologic "pulse," with clusters of major events occurring every 27.5 million years.
  • Working with the most accurate dating methods available, the authors of the study constructed a new history of the last 260 million years.
  • Exactly why these cycles occur remains unknown, but there are some interesting theories.
Keep reading Show less

Interoception: how to improve your "gut feeling"

When we rely on the conscious mind alone, we lose; but when we listen to the body, we gain a winning edge.

Credit: Anthony Tran via Unsplash
Personal Growth
  • Our surroundings contain far more information than our conscious minds can process.
  • Our non-conscious minds are constantly gathering information and identifying patterns.
  • By being interoceptively attuned — that is, aware of the inner state of the body — we can tap into what our non-conscious mind is trying to tell us.
Keep reading Show less

Making memories actually involves breaking our DNA, study shows

Brain cells snap strands of DNA in many more places and cell types than researchers previously thought.

Mind & Brain

The urgency to remember a dangerous experience requires the brain to make a series of potentially dangerous moves: Neurons and other brain cells snap open their DNA in numerous locations — more than previously realized, according to a new study — to provide quick access to genetic instructions for the mechanisms of memory storage.

Keep reading Show less
Surprising Science

Babble hypothesis shows key factor to becoming a leader

Research shows that those who spend more time speaking tend to emerge as the leaders of groups, regardless of their intelligence.

Quantcast