Don't miss the latest stories
Advertise Newsletter
Network
  • The Creative Finder
  • The Bazaar
  • Deals
  • Status Is Down
Community
  • Sign up / Log in
  • Discussion Forums
  • Calendar of Events
NEW

Follow

Share this

Artificial Intelligence
Media
Photography
Technology
Trivia
  • Technology
  • Trivia
MENU
  • Advertise with us
  • Submit tip/feedback
  • Work with us
  • Subscribe to newsletter
  • Subscribe to RSS
Advertise here
Advertisement

The Giveaway That A ‘Person’ In A Photo Is An AI-Generated Fake

By Ell Ko, 27 Sep 2021

Subscribe to newsletter
Like us on Facebook

AI-generated faces. Images created via Face Generator

With years of practice up its sleeves, artificial intelligence (AI) is now able to generate faces that look so real, it’s almost indistinguishable from actual people’s photographs.

But the key is in the word “almost.”

There’s one little telltale flaw, and that’s in the window to the soul: eyes. The generative adversarial networks (GANs) that produce these synthetic faces struggle to replicate some facial features that aren’t always the same, or at least similar-looking.

GANs work via the person behind the operation feeding images of real faces into a neural network, then getting it to generate its own faces after it has “learned” what features like eyes and noses look like and where they tend to be located on the face.

Then, these generated images are tested against a different neural network, which is tasked with spotting the fakes. Sort of like a peer review, it’ll enable the first network to “learn” from its mistakes to be able to generate better faces in the future.

But, like the best of us, these aren’t perfect. Things like glasses, earrings, and nose piercings all end up looking a little questionable, to put it nicely.

Advertisement
Advertisement


Apart from these elements, another thing the GANs struggle with is coming up with regularly-shaped pupils. Ours are often circular or elliptical. AI-generated faces end up with wonky-looking ones, sort of like misshaped pancakes.

This was discovered by a team led by Hui Guo at the State University of New York. In a paper stating their findings, the researchers explain that “this phenomenon is caused by the lack of physiological constraints in the GAN models.”


Image via Guo et. al

Who knew it could’ve been that easy?

While it’s good to know that we can spot if someone in an image is actually non-existent, the knowledge that has been shared today will also reach the creators of GAN-generated faces, who will undoubtedly find a workaround. But who’s to say that another small telltale flaw won’t pop up in the future?

And the cycle continues.



[via Boing Boing, images via Face Generator and Guo et. al]
Receive interesting stories like this one in your inbox
Advertise here

More related news

Advertise here
Also check out these recent news
Web Design
Link to news page

When Your Website Goes Down, This Is the Page Customers Meet Instead

2027
Link to news page

2027 Already Has A Color Of The Year And It’s Beginning On ‘Grounded’ Territory

IKEA
Link to news page

IKEA & Xbox Press Play On Furniture & Storage Inspired By The Iconic Controller

Fashion
Link to news page

Vogue Presents ‘United Flags of Fashion’ With Top Designers For All 50 States

Coca-Cola
Link to news page

Coca-Cola Pours Fresh Life Into Its Iconic Branding With Worldwide Redesign