Live data from Hacker News

To uncover a deepfake video call, ask the caller to turn sideways

metaphysic.ai

181–190 of 285 posts

Re: To uncover a deepfake video call, ask the caller to turn sideways

#181
It reminds me of the meme where guys sing over "Evanescence - Bring Me To Life" with the snapchat gender swap filter on. The female vocals are done facing the camera, showing a female face, the male vocals are done sideways. Turning sideways effectively disables the filter, showing the real (male) face.

Just look it up, (or go there if you feel lazy https://digg.com/2019/bring-me-to-life-gender-swap )

Re: To uncover a deepfake video call, ask the caller to turn sideways

#182

Earlier quoted context omitted.

This is why I got really upset when my employer said the swimsuit competition segment of the interview was past its time. Its time is now!

I can wear a swimsuit, but the person verifying the video is not going to enjoy seeing me in a swimsuit, at all.

Don’t worry, we won’t add it to the training models.

Re: To uncover a deepfake video call, ask the caller to turn sideways

#183
post #18

Source: I work in the field. This is a current limitation, and an artifact of the data+method but not something that should be relied upon. If we do some adversary modelling, we can find two ways to work around this: 1) actively generate and search for such data; perhaps expensive for small actors but not well equipped malicious ones. 2) wait for deep learning to catch up, e.g. by extending NERFs (neural radiance fie…

OK, you passed the yokogao test. Now take a crayon and draw an X on your cheek.

Re: To uncover a deepfake video call, ask the caller to turn sideways

#185

Slightly more robust method... Ask the caller to move out of the frame and then back in again. You will see a noticable 'step' as the face that is partially in the frame suddenly gets detected as a face and the deepfake is applied. The only way around this is to crop the input video quite heavily - by at least one face diameter, which is a lot if the user is near the camera.

> The only way around this is to crop the input video quite heavily

I mean that sounds a lot easier than making deep fakes work well with profile data surely?

Re: To uncover a deepfake video call, ask the caller to turn sideways

#186
post #18

Source: I work in the field. This is a current limitation, and an artifact of the data+method but not something that should be relied upon. If we do some adversary modelling, we can find two ways to work around this: 1) actively generate and search for such data; perhaps expensive for small actors but not well equipped malicious ones. 2) wait for deep learning to catch up, e.g. by extending NERFs (neural radiance fie…

> so don't base your secops around this.

If it's a high-threat context I don't think live video should be relied on regardless of deep fakes. Bribing or coercing the person is always an alternative when the stakes are high.

Re: To uncover a deepfake video call, ask the caller to turn sideways

#187

Earlier quoted context omitted.

“The Impossible Mission Force has the technical capabilities to copy anyone’s face and imitate their voice, so don’t base your secops around someone’s appearance.” … yes, because that worked well.

> … yes, because that worked well. Just to be clear, Mission Impossible is not a documentary.

It is however, a lower bound on whether it is the case that something is a reasonably forseeable/precedented area of research.

After all, if the artist can imagine and build a story around it, there'll be an engineer somewhere who'll go "Ah, what the hell, I could do that."

*By Golblum/Finnagle's Law, it is guaranteed said Engineer will not contemplate whether they should before implementing it, and distributing it to the world.

This another example of why we can't have nice things.

Re: To uncover a deepfake video call, ask the caller to turn sideways

#188
post #18

Source: I work in the field. This is a current limitation, and an artifact of the data+method but not something that should be relied upon. If we do some adversary modelling, we can find two ways to work around this: 1) actively generate and search for such data; perhaps expensive for small actors but not well equipped malicious ones. 2) wait for deep learning to catch up, e.g. by extending NERFs (neural radiance fie…

> Will "turning sideways to spot a deepfake" be a valid test in 5 years? Prolly no, so don't base your secops around this.

couldn't the same thing be said about passwords, 2FA with SMS or asymmetric cryptography?

meanwhile real IDs have been easy to replicate for decades, but are still good enough for the job.

Re: To uncover a deepfake video call, ask the caller to turn sideways

#189
post #18

Source: I work in the field. This is a current limitation, and an artifact of the data+method but not something that should be relied upon. If we do some adversary modelling, we can find two ways to work around this: 1) actively generate and search for such data; perhaps expensive for small actors but not well equipped malicious ones. 2) wait for deep learning to catch up, e.g. by extending NERFs (neural radiance fie…

>Will "turning sideways to spot a deepfake" be a valid test in 5 years? Prolly no, so don't base your secops around this.

We'll just ask them to do "the Linda Blair". If they can turn their head 360 degrees, prolly a deepfake ;P

Re: To uncover a deepfake video call, ask the caller to turn sideways

#190
post #83
post #57

Earlier quoted context omitted.

[flagged]

Would you please stop posting unsubstantive and/or flamebait comments to HN? You've been doing it repeatedly, it's against the site guidelines, we end up banning such accounts, and we've had to warn you more than once before. If you'd please review https://news.ycombinator.com/newsguidelines.html and stick to the rules when posting here, we'd appreciate it. Note this one, just to pick one example: " Eschew flamebait.…

Not sure what to say to this one. Women can get sensitive, if requests of them can be seen in an unpleasant light. Women have also been historically tricked into posing for cameras, had their images misused, and are often quite sensitive about it.

I thought my comment was legit, and on topic. If one is going to implement a policy where people have to slowly move their camera around their body, there may be severe misunderstandings ... and an inability to clarify if a bad response runs-away on twitter and such.

Support persons should be carefully coached on how to handle this.

I guess all I can say here is, I didn't mean this to be so controversial.

Sorry.

Post reply on HN