31–40 of 92 posts
While all this stuff around deep fakes and its detection is interesting I'm still left wondering why we don't use cryptography to prove if an image is authentic or not.
While all this stuff around deep fakes and its detection is interesting I'm still left wondering why we don't use cryptography to prove if an image is authentic or not.
For instance, say that Joe makes a deepfake and then signs it with his key. Sure, it's beyond doubt (assuming keys weren't leaked, etc) that Joe either took or created the picture, but that doesn't in itself tell you whether Joe made a deepfake or not.
It's the same as in supposed blockchain logistics operations. If Fred the farmer says he harvested x bags worth of grain but some were stolen before he could ship them, there's no way to mathematically verify whether the theft actually took place or the harvest just came up short.
In both cases you're going to need some kind of monitoring, and that's the purpose deepfake detection algorithms would serve.
It's hard to see this as much anything but snake oil. While the technique allegedly allows you to target multiple models, it still requires you to know what adversarial model you're targeting before the fact. If the adversary sees there's visible artifacts they'll just change a few parameters or use a different model and be good to go none the less. In short, while this might be academically interesting, I can't help…
Considering that training a model costs thousands of dollars, and that people reuse models instead of training from scratch, I somewhat disagree with this in general, for now.
But this specific technique implies the attacker sees the result, which means they can try different models, until one does not produce artifacts.
It's hard to see this as much anything but snake oil. While the technique allegedly allows you to target multiple models, it still requires you to know what adversarial model you're targeting before the fact. If the adversary sees there's visible artifacts they'll just change a few parameters or use a different model and be good to go none the less. In short, while this might be academically interesting, I can't help…
It's hard to see this as much anything but snake oil. While the technique allegedly allows you to target multiple models, it still requires you to know what adversarial model you're targeting before the fact. If the adversary sees there's visible artifacts they'll just change a few parameters or use a different model and be good to go none the less. In short, while this might be academically interesting, I can't help…
> I can't help but feel that this is a futile field to work in. Considering that training a model costs thousands of dollars, and that people reuse models instead of training from scratch, I somewhat disagree with this in general, for now. But this specific technique implies the attacker sees the result, which means they can try different models, until one does not produce artifacts.
The better you can detect deepfakes, the better deepfakes will be using that method as discriminator.
It's hard to see this as much anything but snake oil. While the technique allegedly allows you to target multiple models, it still requires you to know what adversarial model you're targeting before the fact. If the adversary sees there's visible artifacts they'll just change a few parameters or use a different model and be good to go none the less. In short, while this might be academically interesting, I can't help…
A few weeks ago, there was a post here about that guy who deepfaked female profile pictures. He showed that the visible artifacts go away by merely scaling up the number of parameters in the model. Give it a few years and these fake images will be impossible to detect unless we agree on some way of cryptographically signing images from real cameras.
Ok, so that's tongue in cheek and we'd see some artifacts there but the general principle works. You could intercept the signal from the CCD, or just extract the signing key from the camera's ROM, etc etc.
It's hard to see this as much anything but snake oil. While the technique allegedly allows you to target multiple models, it still requires you to know what adversarial model you're targeting before the fact. If the adversary sees there's visible artifacts they'll just change a few parameters or use a different model and be good to go none the less. In short, while this might be academically interesting, I can't help…