News for hackers. Stuff that matters.
Re:Fawkes: Image “Cloaking” for Personal Privacy by keehun on Wednesday July 22, 2020 @11:16AM (#23917904)
I was immediately was curious how it would protect against image compression and/or otherwise de-noising these protection pixel changes. Their paper does address this question, and for those that are interested:

    Even image compression cannot defeat our cloak.
    We use progressive JPEG [57], reportedly used
    by Facebook and Twitter, to compress the images
    in our dataset. The image quality, as standard
    by Independent JPEG Group [1], ranges from 5 to
    95 (lower value = higher compression). As shown
    in Figure 15, image compression decreases the
    protection success rate, but more significantly
    degrades normal classification accuracy.
I wonder how it works, but it works.

p.s. Mobile friendly copy-paste: "Even image compression cannot defeat our cloak. We use progressive JPEG [57], reportedly used by Facebook and Twitter, to compress the images in our dataset. The image quality, as standard by Independent JPEG Group [1], ranges from 5 to 95 (lower value = higher compression). As shown in Figure 15, image compression decreases the protection success rate, but more significantly degrades normal classification accuracy."

Re:Fawkes: Image “Cloaking” for Personal Privacy by zitterbewegung on Wednesday July 22, 2020 @01:44PM (#23919580)
They create a picture that is designed to fool facial recognition systems and then they will test it against JPEG and other image compression techniques and then run the facial recognition on the compressed version and if both of them pass then they don't change the image.

If the procedure fails then the GAN will know this and it would change the output so that it would pass both outcomes.

Re:Fawkes: Image “Cloaking” for Personal Privacy by hwillis on Wednesday July 22, 2020 @06:54PM (#23922455)
It doesn't use a GAN. I haven't read the paper closely, but is uses a feature extracting network and then tries to modify the features to match a different person. It doesn't try to take advantage of degenerative states in existing networks.

I think it does things like subtly change the shape of your eyes and whatnot. That makes people consistently difficult to pick out of a large set of unmodified faces, but a hu man still finds the images recognizable because they're comparing it to a smaller set.

They didn't create the model by training it on the facial recognizers they tested against, and they tested with several different feature extractors.

Re:Fawkes: Image “Cloaking” for Personal Privacy by withjive on Wednesday July 22, 2020 @12:17PM (#23918597)
They are lucky in this case because compression does defeat the cloak to some degree— However, compression at those levels also defeats the ability of Facebook to accurate identify you.
Re:Fawkes: Image “Cloaking” for Personal Privacy by turdnagel on Wednesday July 22, 2020 @12:36PM (#23918792)
How about a 1px Gaussian blur? Haven't read the paper but I had the same thought. Seems way too tenuous.
Re:Fawkes: Image “Cloaking” for Personal Privacy by gruez on Wednesday July 22, 2020 @01:14PM (#23919243)
from the paper:

> However,we find that none of these transformations defeat our cloaks. The protection success rate remains 100% even when data augmentation is applied to cloaked images5. Ap-plying Gaussian blurring degrades normal accuracy by up to18% (as kernel size increases) while cloak protection success rate remains>98% (see Figure13). Adding Gaussian noise to images merely disrupts normal classification accuracy –the cloak protection success rate remains above 100% as the standard deviation of the noise distribution increases(seeFigure14). Even image compression cannot defeat our cloak.We use progressive JPEG [57], reportedly used by Facebookand Twitter, to compress the images in our dataset. The im-age quality, as standard by Independent JPEG Group [1],ranges from 5 to 95 (lower value = higher compression). As shown in Figure15, image compression decreases the pro-tection success rate, but more significantly degrades normal classification accuracy.

Re:Fawkes: Image “Cloaking” for Personal Privacy by ZeikJT on Thursday July 23, 2020 @07:24PM (#23933924)
You don't even have to read the paper, it's in the FAQs: "Can't you just apply some filter, or compression, or blurring algorithm, or add some noise to the image to destroy image cloaks?"

Short answer: No not really. Long answer: Look at the FAQs :)