Live data from Hacker News

Fawkes: Image “Cloaking” for Personal Privacy

sandlab.cs.uchicago.edu

111–120 of 122 posts

Re: Fawkes: Image “Cloaking” for Personal Privacy

#111

Earlier quoted context omitted.

Fair shake, this time I cropped the image too so that it wasn't looking at any of the boundary to identify it either. Here's the original image: https://imgur.com/a/Td4rhoy And the cloaked: https://imgur.com/a/cPCiCZo These were both saved as JPG with compression level 8/12. I searched for the cloaked crop (96.jpg) first this time: https://imgur.com/a/FSehQWO And the original crop (10.jpg) next: https://imgur.com/a/y…

The goal, afaik, is to stop facial detection software from learning to recognize you and put a face to a name, not to frustrate visual similarity searches. The images are supposed to be visually similar -- so similar that they're indistinguishable to a human viewer. Surveillance software that purports to accurately identify a person across multiple images is not just looking for the same content with some visually in…

Since visual similarity uses similar feature vectors to facial recognition it calls into question their whole theory of operation.

Re: Fawkes: Image “Cloaking” for Personal Privacy

#112

Earlier quoted context omitted.

Why cut and mirror? Can't you just mirror? Wouldn't this be the same as just looking at someone's face in the mirror?

No, he's not saying to flip, he's saying that the left and right halves of your face aren't symmetrical, and it's very uncanny valley if you view a portrait of a person with symmetrical left and right halves. https://www.google.com/search?q=symmetrical+left+and+right+f...

Oh, I see, thanks.

Re: Fawkes: Image “Cloaking” for Personal Privacy

#113
post #64
post #61

Earlier quoted context omitted.

There is a problem there that your pics are already out and you can no longer update them....

If you use a new cloaking image for each picture you upload to social then they will all be embedded in a different location for a given feature extractor and an adversary wouldn’t be able to reverse search for linked pictures—that’s at least my understanding of how the method would need to be used. But if you keep using the same cloaking image, your adversary could definitely learn that process and effectively undo…

Cool. So it would prevent someone from learning my face from a collection of photos on my profile. That makes more sense...

Re: Fawkes: Image “Cloaking” for Personal Privacy

#115
post #78

Earlier quoted context omitted.

From the linked article: Q: Can't you just apply some filter, or compression, or blurring algorithm, or add some noise to the image to destroy image cloaks? A: As counterintuitive as this may be, the high level answer is no simple tools work to destroy the perturbation that form image cloaks. To make sense of this, it helps to first understand that Fawkes does not use high-intensity pixels, or rely on bright patterns…

It was pretty frustrating that they did not readily offer any example images for inspection, so against my better judgement I downloaded their binaries to run some experiements. First, a source image at an approximate resolution that you might find on a social networking site: https://imgur.com/a/9szcC1m Text output of the tool, which ran for about 3 minutes: https://imgur.com/a/fZtfrmm The resulting cloaked image: h…

You're not testing against facial recognition models.

"similar image" search generally uses "perceptual hashing" which is not related to facial recognition, and not really a privacy risk.

You're not testing against what this tool was designed to defeat :-/

Re: Fawkes: Image “Cloaking” for Personal Privacy

#116
post #8

Color me extremely skeptical. A low-pass filter will make short work of any "tiny, pixel-level" changes designed to thwart ML. After all, one of the most tell-tale identifiers (space between eyes/nose/mouth) is still plainly observable and unaltered in the "cloaked" image. If a human's neural network can correctly correlate the before/after examples, so can a computer's. They might have found an issue with some moder…

Haven't read the paper yet but sure will do. I wonder how it works, that so many face rec implementations are fooled but I don't know how similar they work. I would have guessed they know which features are extracted and modify the relevant regions.

I guess that face rec software will quickly adapt though. That said, we have invisible watermarks that are very resistant to compression or other filters.

Re: Fawkes: Image “Cloaking” for Personal Privacy

#117
post #78

Earlier quoted context omitted.

From the linked article: Q: Can't you just apply some filter, or compression, or blurring algorithm, or add some noise to the image to destroy image cloaks? A: As counterintuitive as this may be, the high level answer is no simple tools work to destroy the perturbation that form image cloaks. To make sense of this, it helps to first understand that Fawkes does not use high-intensity pixels, or rely on bright patterns…

It was pretty frustrating that they did not readily offer any example images for inspection, so against my better judgement I downloaded their binaries to run some experiements. First, a source image at an approximate resolution that you might find on a social networking site: https://imgur.com/a/9szcC1m Text output of the tool, which ran for about 3 minutes: https://imgur.com/a/fZtfrmm The resulting cloaked image: h…

When I look at the cloaked image it seems that the tool is doing something legit. It's actually changing the shape of the face ever so slightly, rather than playing tricks with noise.

I echo the sentiment of other posters regarding reverse-image search. The original image should not be available to match against. That would be operator failure.

Re: Fawkes: Image “Cloaking” for Personal Privacy

#118

Earlier quoted context omitted.

Why cut and mirror? Can't you just mirror? Wouldn't this be the same as just looking at someone's face in the mirror?

No, he's not saying to flip, he's saying that the left and right halves of your face aren't symmetrical, and it's very uncanny valley if you view a portrait of a person with symmetrical left and right halves. https://www.google.com/search?q=symmetrical+left+and+right+f...

Almost all of these (including the example on QI) are just poor editing. There are some examples in those results where it's been done properly, with symmetrical lighting, and the results look... almost exactly the same as the original. Unsurprisingly.

Re: Fawkes: Image “Cloaking” for Personal Privacy

#120
post #65
post #15

Github link: https://github.com/Shawn-Shan/fawkes

has anyone tried with their own image? How did it go?

I can't speak for how effective Fawkes is but I can speak for the process. I just tried this out with 4 images.

One thing that I took notice of was how long the program ran on my computer. It took about 5 and a half minutes to obfuscate 4 images on an i9-9900K with the cpu was pegged at 100% the entire time. I can't imagine how long this would take on a low end laptop: especially if I needed to cloak a lot of images in bulk.

Another thing I noticed is that the discoloration that is applied to the final images can be easily mistaken for bruising. If I were to see someones post on social media and they looked like my results I'd be inclined to think that the poster is recovering from a bad fight or is a victim of abuse.

Other than those two little nit picks the tool is pretty cool! However I don't think I will be using it myself due to the second point.

Post reply on HN