back to article Pixellation popped: AI can ID you, even after PhotoShop phuzzing

Pixellating images turns out to be a dodgy way of obfuscating identities, say researchers from the University of Texas and Cornell Tech who reckon computers can be trained to identify the “protected” people. There's an "if" here, namely that pixellation can be popped if an "attacker” has a set of clear shots to practice on. If …

  1. Anonymous Coward
    Anonymous Coward

    reCAPTCHA

    "The attack can also work for recovering text or handwriting that's been obfuscated"

    So 'reCAPTCHA' and its friends are borked?

    Hmm the rise of the bots posting for us

    :(

  2. Anonymous Coward
    Anonymous Coward

    Easy solution

    just replace the faces that were going to be pixellated with those of the latest celeb wannabe.

    After all they seem to want to do anything they can to get their mugshots in the media so why not help them along the way. A win-win solution I'd say.

    The pixelators will also have to start removing/editing all their Tattoo's as well. They are also a dead (Sic) give away.

    From the skin on show this summer those of us who don't have any artwork will soon be an endangered breed.

    1. poohbear

      Re: Easy solution

      Tattoo: a way to mark slaves.

  3. Pascal Monett Silver badge

    In short

    Instead of pixellating, just replace face by a swath of any uniform color.

    No way anyone will recognize anything then.

  4. allthecoolshortnamesweretaken Silver badge

    "There's an "if" here, namely that pixellation can be popped if an "attacker” has a set of clear shots to practice on. If they do, and the AI has access to to those shots, forget about facial blocking as an anonymity mechanism."

    Which means this is a "learning" system that compares sets of data. A very clever implementation, but still not AI, at least not above the "trained monkey" level.

  5. Paratrooping Parrot
    Paris Hilton

    What about numberplates?

    I always "paint" white on top of number plates rather than blurring them. I guess that is immune to the algorithm.

    1. Nick Ryan Silver badge

      Re: What about numberplates?

      Perhaps against a number plate recognition algorithm, however against a car recognition algorithm less likely to be immune. First consider the dataset, as in how many of your car (same make, body shape and colour) were produced - except for the most popular car this number will be surprisingly low. Then consider any after market modifications, such as hanging ornaments (or their absence), stickers or even the odd scrape, some of which would require a relatively high resolution image, and your car is not as generic as you might think it is and therefore it should be relatively unique.

  6. Aqua Marina

    Haven't people been doing this for years?

    So they've taught the computer to slightly cross it's eyes, go just out of focus and then you can make out who it is?

  7. Canker

    Interesting opportunity to frame someone

    So... you headswap in photoshop, then pixelate.

    If done well, it'd be virtually impossible to tell it had been photoshopped at all and the AI will conveniently finger your chosen fall guy for whatever crime the image depicts.

    Frame your enemies today with the technology of the future!

  8. Anonymous Coward
    Anonymous Coward

    Pr0n

    No good for un-pixelating Japanese censored porn then!

  9. M Gale

    Obviously too many pixels then. Increase quantization until the AI (and everyone else) can't classify Jack from Jill.

    Isn't some quantization part of how some convolutional neural networks work anyway? Easier to work with a 64x64px image than a 6400x6400px one.

  10. JeffyPoooh Silver badge
    Pint

    Time to stop the willful ignorance with Neural Nets

    "We do not even need to understand..."

    Stupid.

    Have a look at Google Deep Dream, and review the available videos that explain what's going on.

    The conclusion is obvious.

    With a suitable Neural Net debugging / emulating / visualization development environment, based on the blatantly obvious concepts exposed by Deep Dream, it would be perfectly practical for a more rigorous engineering review and modeling of any given neural network.

    The pathetic and lame approach of skipping the engineering design review are now over. Mindlessly claiming joyful ignorance of the network weightings, the meanings of each node, their connections, and the true scope and coverage of the solution space, is hereby unacceptable for any serious application.

    You never know until it's too late if your system can distinguish clear sky from white truck.

    It's time to call B.S. on the willful ignorance of Neural Network programming.

  11. computinghomer

    Yet another fear my magic article. Horsepucky. The pixelation destroys fundamental information from the image. Even knowing the algorithm used to perform pixelation will not allow full recovery or even ensure significant recovery.

    1. Cuddles Silver badge

      "The pixelation destroys fundamental information from the image. Even knowing the algorithm used to perform pixelation will not allow full recovery or even ensure significant recovery."

      Indeed. The only thing proved by recovering a pixelated image is that it wasn't pixelated enough in the first place. I suppose it's vaguely interesting if a computer can identify an image that's messed up enough that a human can't, but since we're dealing with a process that destroys information it's utterly trivial to do so in a way that guarantees nothing can ever recover enough information to identify anything.

  12. SteveK

    The solution

    All photos containing people whose identities need to be obscured must be re-enacted in Playmobil.

  13. tr1ck5t3r

    "The only difficult part, in dealing with photos, is that the attacker would need to trawl social media for a “set of possible faces that may appear in a given photo”."

    Not very good. Try developing an AI to reveal whats behind your frosted glass windows. Throw in night vision and infrared camera's to get a 24x7 video feed, but you do need HD cams or better. Training is simple if you think about it.

POST COMMENT House rules

Not a member of The Register? Create a new account here.

  • Enter your comment

  • Add an icon

Anonymous cowards cannot choose their icon

Biting the hand that feeds IT © 1998–2019