None of Your Pixelated or Blurred Information Will Stay Safe On The Internet (qz.com)

The University of Texas at Austin and Cornell University are saying blurred or pixelated images are not as safe as they may seem. As machine learning technology improves, the methods used to hide sensitive information become less secure. Quartz reports: Using simple deep learning tools, the three-person team was able to identify obfuscated faces and numbers with alarming accuracy. On an industry standard dataset where humans had 0.19% chance of identifying a face, the algorithm had 71% accuracy (or 83% if allowed to guess five times). The algorithm doesn't produce a deblurred image -- it simply identifies what it sees in the obscured photo, based on information it already knows. The approach works with blurred and pixelated images, as well as P3, a type of JPEG encryption pitched as a secure way to hide information. The attack uses Torch (an open-source deep learning library), Torch templates for neural networks, and standard open-source data. To build the attacks that identified faces in YouTube videos, researchers took publicly-available pictures and blurred the faces with YouTube's video tool. They then fed the algorithm both sets of images, so it could learn how to correlate blur patterns to the unobscured faces. When given different images of the same people, the algorithm could determine their identity with 57% accuracy, or 85% percent when given five chances. The report mentions Max Planck Institute's work on identifying people in blurred Facebook photos. The difference between the two research is that UT and Cornell's research is much more simple, and "shows how weak these privacy methods really are."

Comments

I felt a disturbance in the force.

[Hognoxious]

The algorithm doesn't produce a deblurred image

I felt a great disturbance in the force, as if a million Japanese porn fans cried out in disappointment.

Re:Not too surprising...

[AmiMoJo]

That pixelated images are insecure has been known about for years. I seem to recall it was even mentioned on Slashdot. There are many other attacks, for example if you have text (like a number plate) you can just try running a dictionary attack of images through a pixelation filter and select the closest matching result.

Black bars have always been the preferred method.