Fawkes: Image “Cloaking” for Personal Privacy • Hacker News Board

Re: Fawkes: Image “Cloaking” for Personal Privacy

#11

Post by Nasrudith » Wed, Jul 22, 2020, 3:53 PM UTC

I can't help but roll my eyes at the the introduction's "unregulated facial recognition software" part of the introduction. That is a meaningless term given the lack of regulation in the first place examples and says in itself nothing about the effectiveness. The "Clipper Chips" infamous Skipjack was regulated. It annoys me mostly because meaningless rhetoric looks like they have no defensible stance.

That rant aside I am curious if this technique will lead to more resilent facial recognition and image parsing techniques to find the shape. Obviously the fact humans can still recognize it is a hint there is some other algorithim possible.

Re: Fawkes: Image “Cloaking” for Personal Privacy

#12

Post by Immortal333 » Wed, Jul 22, 2020, 3:55 PM UTC

This is tested on existing models/Face Recognition API which means locked pre-trained models. So, They might have learned way to add pixels such that model outputs very different embedding. This is know issue in deep learning [0][1][2].

I believe, Model trained on cloaked images would defeat its purpose and make this technique useless.

[0] Su, Jiawei, Danilo Vasconcellos Vargas, and Kouichi Sakurai. "One pixel attack for fooling deep neural networks." IEEE Transactions on Evolutionary Computation 23.5 (2019): 828-841.

[1] Guo, Chuan, et al. "Countering adversarial images using input transformations." arXiv preprint arXiv:1711.00117 (2017).

[2] Liu, Yanpei, et al. "Delving into transferable adversarial examples and black-box attacks." arXiv preprint arXiv:1611.02770 (2016).

Re: Fawkes: Image “Cloaking” for Personal Privacy

#13

Post by katakuchi » Wed, Jul 22, 2020, 3:57 PM UTC

"when someone tries to identify you using an unaltered image of you [...] they will fail."

I wonder how this holds up when someone takes a photo of that 'protected image'. I can imagine that if these miniscule pixel-scaled changes aren't visible to the naked eye, my crappy 6 megapixel camera will overlook it as well. If I then proceed to feed that image into my image recognition algorithm, is it still protected?

Re: Fawkes: Image “Cloaking” for Personal Privacy

#14

Post by Immortal333 » Wed, Jul 22, 2020, 4:00 PM UTC

gnabgib wrote: post #2

Also 7 days ago[1][2][3] but no upvote love so far. Which is curious given the (possibly short term, until these images join training corpus?) privacy benefits [1]: https://news.ycombinator.com/item?id=23845760 [2]: https://news.ycombinator.com/item?id=23842016 [3]: https://news.ycombinator.com/item?id=23837565

It might be possible that these people have tried on more platforms (Face recognition APIs) but only reported those where they got good accuracy in terms of defeating system.

I personally would like to see tests done on facebook by uploading these images and checking if it can recognize it.

Re: Fawkes: Image “Cloaking” for Personal Privacy

#15

Post by fooxed » Wed, Jul 22, 2020, 4:00 PM UTC

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

Re: Fawkes: Image “Cloaking” for Personal Privacy

#16

Post by Nasrudith » Wed, Jul 22, 2020, 4:02 PM UTC

data_spy wrote: post #6

101008 wrote: post #4

It'd be great to have an app on Android that applies this to every photo I take with my camera.

Agreed. I would use it, unless it was made by Facebook, Amazon, Google or Apple.

Stupid thought - technically couldn't any implementation include some sort of deliberate covert stenographic key? Granted that would likely be more "narrow down the implementation" without it being detectable via hashes per instance output.

Re: Fawkes: Image “Cloaking” for Personal Privacy

#17

Post by blindmonk3000 » Wed, Jul 22, 2020, 4:10 PM UTC

Here is a good video describing how this might work. Near the end he shows that even printing out an image that has been "cloaked" and viewing it from different angles can still fool a neural network classifier.

https://www.youtube.com/watch?v=4rFOkpI0Lcg

Re: Fawkes: Image “Cloaking” for Personal Privacy

#18

Post by yalogin » Wed, Jul 22, 2020, 4:10 PM UTC

This is awesome and really promising. But the fundamental fact about machine learning is its supposed to approximate/model any scenario so the basic premise of ML would defeat this isn't it? Its a matter of time before someone creates a face recognition model to defeat this.

Re: Fawkes: Image “Cloaking” for Personal Privacy

#19

Post by djyaz1200 » Wed, Jul 22, 2020, 4:12 PM UTC

Looks like it is obfuscating asymmetry. In addition to the intended effect it could also make people more attractive.

Re: Fawkes: Image “Cloaking” for Personal Privacy

#20

Post by withjive » Wed, Jul 22, 2020, 4:17 PM UTC

keehun wrote: post #3

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…

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.