Researchers Develop Glasses Frames That Fool Facial Recognition Technology Want to fool facial recognition software? Try some groovy glasses. It turns out patterned glasses can lead the program to misidentify people.
NPR logo

Researchers Develop Glasses Frames That Fool Facial Recognition Technology

  • Download
  • <iframe src="https://www.npr.org/player/embed/500810484/500810485" width="100%" height="290" frameborder="0" scrolling="no" title="NPR embedded audio player">
  • Transcript
Researchers Develop Glasses Frames That Fool Facial Recognition Technology

Researchers Develop Glasses Frames That Fool Facial Recognition Technology

Researchers Develop Glasses Frames That Fool Facial Recognition Technology

  • Download
  • <iframe src="https://www.npr.org/player/embed/500810484/500810485" width="100%" height="290" frameborder="0" scrolling="no" title="NPR embedded audio player">
  • Transcript

Want to fool facial recognition software? Try some groovy glasses. It turns out patterned glasses can lead the program to misidentify people.

SIMON SCOTT, HOST:

Facial recognition systems can feel a little creepy. Software that sees you digitally, then identifies who it thinks you are. But a team of researchers at Carnegie Mellon University have developed a tortoise shell pattern that can be stuck over glasses to fool facial recognition software, even lead it to make the wrong identification. I like to imagine the software confusing my face with, you know, Colin Firth or B.J. Liederman, who writes our theme music.

The researchers presented a paper at the 2016 Computer and Communications Security Conference. New Scientist explains the frames overlay the face with pixels that perturb the software's calculations. A normal printer can run off a copy of the pattern for just 22 cents. What's to prevent criminals from printing copies, pasting them on glasses and sticking up banks? The researchers say the pattern only works in limited security systems, but wouldn't a pair of Groucho glasses do just about the same thing?

Copyright © 2016 NPR. All rights reserved. Visit our website terms of use and permissions pages at www.npr.org for further information.

NPR transcripts are created on a rush deadline by Verb8tm, Inc., an NPR contractor, and produced using a proprietary transcription process developed with NPR. This text may not be in its final form and may be updated or revised in the future. Accuracy and availability may vary. The authoritative record of NPR’s programming is the audio record.