There's a newer model that can be used pre-trained and doesn't need to be retrained for each face pair: https://nirkin.com/fsgan/
But for now deepfakes seem like a 2018 meme that died out.
Creating a deepfake took two weeks and cost $552
71–80 of 119 posts
Re: Creating a deepfake took two weeks and cost $552
#72Earlier quoted context omitted.
I feel like that ship sailed a while ago with Photoshop being around. I think the problem now is you can do the same with videos and the technology is more commoditized so you don’t have to be very knowledgeable to do these things.
People predicted that Photoshop was the end of truth, that journalism could no longer be trusted, that photographic evidence at criminal trials would be inadmissible. None of that actually happened because people learned to be skeptical, and to care about who took the photo, the chain of custody, and the controls to prevent digital alteration. Maybe we need something similar but more rigorous for video. The camera it…
> Maybe we need something similar but more rigorous for video.
Is there evidence that deepfake videos will be worse than photos? My (naive) sense is that even for an AI, editing a photo will always be easier than editing a video with sound.
If Photoshop and deep-fake images aren't a problem, shouldn't we be less concerned about video?
Re: Creating a deepfake took two weeks and cost $552
#73Earlier quoted context omitted.
I'm under the impression that these things are easier to come infinitesimally close to, but very hard to get right: i.e. the old uncanny valley problem. A reporter with $500 can get very close, but a team of PhD with thousands of dollars and a lot of time may never be able to produce something that'll convince the public. I'm NOT claiming that this is the case, I'm just saying we don't have a reason to believe why th…
I'd really hesitate to bet on never in this case--even if never were scoped to mean not within 20 years. There really are two separate questions though: - Can experts with a big budget create videos that even equally expert analysis can't tell from the real thing? (Maybe yes, maybe no. But it's hard. - With modest skill and budget, are people increasingly able to create fake videos that stand up a cursory glance and…
My point is, there is no close or far in this business. It's binary, either it looks real, or it doesn't. If your intention is to make deepfake to put it in a movie, video game or any other entertainment system, then sure you're right.
But that already exists, DeepFake isn't a fundamental development for that. What is the "big thing" about deepfake is that we can imitate speeches of people in leadership positions. For this, we can get really really close; but it's unclear if it'll ever be realistic enough to be a problem in court cases, politics etc...
Re: Creating a deepfake took two weeks and cost $552
#74Earlier quoted context omitted.
I feel like that ship sailed a while ago with Photoshop being around. I think the problem now is you can do the same with videos and the technology is more commoditized so you don’t have to be very knowledgeable to do these things.
People predicted that Photoshop was the end of truth, that journalism could no longer be trusted, that photographic evidence at criminal trials would be inadmissible. None of that actually happened because people learned to be skeptical, and to care about who took the photo, the chain of custody, and the controls to prevent digital alteration. Maybe we need something similar but more rigorous for video. The camera it…
>>None of that actually happened because people learned to be skeptical, and to care about who took the photo, the chain of custody, and the controls to prevent digital alteration.
This may be true in courts of law, but it absolutely is not when it comes to general public consumption of pictures.
Re: Creating a deepfake took two weeks and cost $552
#75interesting conclusion:
> In the long run, the larger risk may be that public attitudes swing too far in the opposite direction: that the possibility of deepfakes completely destroys public trust in video evidence. Certain politicians are already in the habit of dismissing media criticism as "fake news." That tactic will only become more effective as public awareness of deepfake technology grows.
Deepfakes themselves will not disrupt democracies or cause the much anticipated chaos. Deepfakes are in fact pointless for agitprop / disinfo campaigns:
"cheapfakes beat deepfakes" --@thegrugq
https://twitter.com/thegrugq/status/1206404680223358976
https://medium.com/@thegrugq/cheap-fakes-beat-deep-fakes-b1a...
What is fascinating (and uncommon) is, that the damage isn't delivered with any specific deepfake itself. But the mere awareness that the technology exists, and that they could _potentially_ be used, is enough to change our risk perception. Even if the ratio cheapfakes/deepfakes usage in actual disinfo campaigns remains tiny percentage, deepfakes make much better headlines. (in a similar way the infosec industry is obsessed with 0days - but most of the risks are coming from people clicking on links in email)
Maybe one day we will look at deepfakes like "art". If pictures and videos can be art, and if "all art is propaganda" (see Orwell), then deepfakes too should be considered art, no?
Re: Creating a deepfake took two weeks and cost $552
#76Earlier quoted context omitted.
What I find most worrying is the 2nd order consequence of not being able to trust pictures anymore.
https://www.history.com/news/josef-stalin-great-purge-photo-... Photo editing has been used pretty much since the beginning of mainstream photography. You should never "trust" pictures for anything serious if you don't have absolute trust in the source.
I don't completely agree, good quality photo editing, even in this day and age, is not that mainstream. You need a decent amount of skill to edit a good quality picture in a way that won't look obviously fake. Pre-digital-photography it was only possible for skilled people with a significant amount of resources (like the Soviet government, no doubt).
Besides it's one thing to edit a still image and a whole other to forge a long video, complete with audio. Look at those movies these past few years using 3D models to insert younger versions of actors (Terminator and Star Wars come to mind). They must have invested millions into it, they have very talented artists and it's pretty good but it's still quite easy to spot the fakeness of it.
Re: Creating a deepfake took two weeks and cost $552
#77The central technique used in DeepFakes is fascinating. Initially I assumed they were using Generative Adversarial Networks (GANs). But — and someone can correct if I’m wrong — Deep Fakes use two Autoencoders. So essentially you’re training a network how to compress an image down to a very tiny representation, and then uncompress it as accurately to the original as possible. You train two of these: one for the origin…
Autoencoders aren't even the best dimensionality reduction technique. Where are UMAP powered "manifold" fakes?
Re: Creating a deepfake took two weeks and cost $552
#78Earlier quoted context omitted.
If you post a ridiculous quote, say it’s from Obama, then provide a link to a video where Obama says that quote, more people believe you. People already believe tabloid journalism. Just because you might exclusively trust NYTimes doesn’t mean easily accessible mechanisms for fabricating evidence aren’t a problem for a massive chunk of the world population. And what about when this happens at a state-sponsored level (…
I don't think the argument is that deepfakes won't matter. It's that they don't represent a new paradigm, but are instead just an additional medium (video) which must be more scrutinized than before. Long have documents and news been the subject of fraud. And for a few decades photo alterations have been common. Now we are adding video to the list. But there is nothing new about the faking of libelous material (eg Ki…
Video is massively different for swaying public opinion. There’s a reason most news on Facebook/Instagram is in the form of 15-60 second video montages. People can tune in quickly, get information passively, and leave. Video isn’t just “another item on the list”. It’s the most powerful means of sharing information we have.
How many people do you think actually read those “Killian documents”? How many people do you think a state-sponsored social media campaign built on the most accessible media would reach?
Re: Creating a deepfake took two weeks and cost $552
#79The central technique used in DeepFakes is fascinating. Initially I assumed they were using Generative Adversarial Networks (GANs). But — and someone can correct if I’m wrong — Deep Fakes use two Autoencoders. So essentially you’re training a network how to compress an image down to a very tiny representation, and then uncompress it as accurately to the original as possible. You train two of these: one for the origin…
Autoencoders aren't even the best dimensionality reduction technique. Where are UMAP powered "manifold" fakes?
UMAP is, sadly, extraordinarily slow, plus the inverse mapping is not clear.
Re: Creating a deepfake took two weeks and cost $552
#80This work is just at the research stage right now and isn’t available as consumer software, but it probably won’t be long until similar services go public.