The images are created through algorithms known as Generative Adversarial Networks (GANs), which feature two computer programs, the generator and the discriminator, that compete against each other using commonalities in data sets from real faces to generate artificial ones that grow in refinement over time.
The results are shocking.
While most of the images look authentic, there are sometimes glitches in the matrix.
All in all, the technology—which was introduced in 2014—has gotten more sophisticated with time. This GAN (called StyleGAN) for faces was developed in part by a Graphic Processing Unit Company called Nvidia. That sophistication could lead to some sinister developments down the line.
For instance, deep fakes—computer-generated images of recognizable people superimposed over videos—have been used for everything from fake sex tapes to fake news. The growing ubiquity of the technology could pose a problem when a populace can't trust their own eyes or ears.
It's because of this that Uber software engineer Phillip Wang decided to launch This Person Does Not Exist.
Wang said:
“I have decided to dig into my own pockets and raise some public awareness for this technology. Faces are most salient to our cognition, so I’ve decided to put that specific pre-trained model up. Each time you refresh the site, the network will generate a new facial image from scratch from a 512 dimensional vector.”
As usually happens with innovations like this, it's unlikely that the technology behind StyleGAN will recede, so people should heed Wang's warning and get ahead of it before they can be deceived.
Keep reading...
Show less
SECONDNEXUS
percolately
georgetakei
comicsands
George's Reads
