Just dont forget the good old purge of exif as well.
Fawkes: Image “Cloaking” for Personal Privacy
21–30 of 122 posts
Re: Fawkes: Image “Cloaking” for Personal Privacy
#22This 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.
In theory, yes, you can feed these new distorted images into a new model and defeat the cloaking.
In practice, building new training sets is much more expensive than slightly changing the cloaking algorithm.
Re: Fawkes: Image “Cloaking” for Personal Privacy
#23"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?
They go over the effects of compression - which they say only degrades the protection - but at the same time also degrades the identification accuracy of the AI model.
So if your crappy 6 megapixel camera cannot take a clear shot of the cloaked pixels - or effectively applying a blur filter - would also affect the AI detection.
Re: Fawkes: Image “Cloaking” for Personal Privacy
#24This 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.
In theory, yes, you can feed these new distorted images into a new model and defeat the cloaking. In practice, building new training sets is much more expensive than slightly changing the cloaking algorithm.
That is awesome. I need to read the paper. Really promising. Are you the author btw?
Re: Fawkes: Image “Cloaking” for Personal Privacy
#25This 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…
This should be somewhat mitigated if you keep using different cloaking images, no?
Re: Fawkes: Image “Cloaking” for Personal Privacy
#26This might work today, but it won’t work tomorrow.
This is just one side of a GAN, on the next iteration, it will be defeated.
Bottom line is that if a human can recognize, then it is possible for a machine as well.
Also, given that the big networks can just keep throwing more resources at it (I.e. GPT-3), it’s just a matter of increasing the network size to improve feature redundancy.
Re: Fawkes: Image “Cloaking” for Personal Privacy
#27I 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…
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
#28The more people start using this service, the better the AI will learn the differences between real and cloaked images. So eventually anybody can run an unaltered photo of yours through the cloak and it will match up.
Re: Fawkes: Image “Cloaking” for Personal Privacy
#29Just defeated it on a dataset of 10k face images. Accuracy drops 7 +- 2%. Had to tweak some params, but that's it.
Re: Fawkes: Image “Cloaking” for Personal Privacy
#30Once this technique gets enough attention, a detector for it will be built. Even if the face cannot be recognized, a profile with such picture may be flagged for more scrutiny. This reminds me of using TOR that hides what you visit, and yet likely puts you into a watchlist for surveillance.
I think that a simpler and more robust strategy to achieve good privacy is avoid posting personal information online and social media altogether.