News for hackers. Stuff that matters.
Re:New deepfake detector can spot a real/fake video based on... by BoorishBears on Friday November 18, 2022 @05:34PM (#33663491)
Not really special in the case of ML.

Before deepfakes, if you wanted to claim a video was doctored in court, you'd find an expert on video editing and have them testify.

But the same knowledge that allowed them to identify a doctored video (like 50hz/60hz hum) could be in an adversarial manner to create a very convincing video.

At most deepfakes democratize that "knowledge" in the form of a model, so it still works both ways.

Re:New deepfake detector can spot a real/fake video based on... by JadeNB on Friday November 18, 2022 @06:26PM (#33664390)
> But the same knowledge that allowed them to identify a doctored video (like 50hz/60hz hum) could be in an adversarial manner to create a very convincing video.

I don't think it's automatically true that being good at spotting fakes means that you're good at generating fakes. For example, I suspect that I, like most humans, would be pretty good at spotting humanoid robots at the current level of terminology. However, that does not suggest that I would be particularly good at creating humanoid robots that would evade detection.

Re:New deepfake detector can spot a real/fake video based on... by BoorishBears on Friday November 18, 2022 @06:51PM (#33664706)
That's why I specified an example that requires a domain expert, you could have a very poorly done fake video that anyone can tell is fake too.
Re:New deepfake detector can spot a real/fake video based on... by JadeNB on Friday November 18, 2022 @06:57PM (#33664781)
> That's why I specified an example that requires a domain expert, you could have a very poorly done fake video that anyone can tell is fake too.

But my example also satisfies that criterion. I (and most humans) am a domain expert at identifying humans, but that doesn't mean I would be good at faking a human.

Re:New deepfake detector can spot a real/fake video based on... by thaumasiotes on Friday November 18, 2022 @07:29PM (#33665123)
> I (and most humans) am a domain expert at identifying humans, but that doesn't mean I would be good at faking a human.

I don't think you're thinking about this enough. If you make one effort to create something that looks like a human, you'll do a terrible job unless you are already a skilled artist.

But that doesn't support your claims here. We have a scenario where you've prepared a fake human and attempted to pass it off as real. The only way this could actually happen is if you looked at your own handiwork and it passed quality tests. And since you're good at identifying humans, that necessarily means that your fake human is a high-quality imitation. If it were terrible, you'd look at it and realize it couldn't be passed off as real.

Re:New deepfake detector can spot a real/fake video based on... by BoorishBears on Friday November 18, 2022 @06:58PM (#33664794)
I really didn't think I needed to specify domain expert at faking humans.

I said video editor not video watcher.

Re:New deepfake detector can spot a real/fake video based on... by JadeNB on Friday November 18, 2022 @09:36PM (#33666200)
> I said video editor not video watcher.

The specific claim with which I was disagreeing was:

> But the same knowledge that allowed them to identify a doctored video (like 50hz/60hz hum) could be [used] in an adversarial manner to create a very convincing video.

You said the knowledge that allows one to identify a doctored video can be used to create a convincing video, and it's that claim with which I'm disagreeing, in the sense that I claim that it's possible to have a wealth of knowledge that allows one to identify a doctored video, and yet not to be able to create a convincing video.