Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

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

metaphysic.ai

Post reply on HN
Print view View original

201–210 of 285 posts

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

#201

Post by jjk166 »

robocat wrote: post #151
jjk166 wrote: post #53

Probably a more robust test would be asking the caller to run their hand through their hair a few times. Maybe you could pre-render a few samples, but it would be trivial to request the person pass their hands through their hair in a specific way, or simply do it again after their hair is already messed up a bit from the first time. It could still be defeated by the caller having the same hair style (or wearing a goo…

> run their hand through their hair That would have trouble passing anti-discrimination requirements: disability (no hands), medical (bandanna covering cancer treatment hair loss), religious (burka, rasta, yarmulke, sheitel), racist (cornrow). And trouble with: dreadlocks (can’t run fingers through), bald headed guys (as mentioned by sibling comment), and people with hairdo’s (coiffure, hairspray, topknots, plaits et…

It doesn't need to be literally their hand through their hair, it just needs to be some action which is easy to perform but complicated to photo-realistically simulate in real time from an arbitrary starting condition. Have them tug on their clothes to see how the fabric moves, have them or a caretaker turn a nearby light on and off such that their illumination changes, etc.

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

#202

Post by jksmith »

Strom wrote: post #113
sbszllr wrote: 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…

> This is a current limitation The thing with any AI/ML tech is that current limitations are always underplayed by proponents. Self-driving cars will come out next year, every year. I'd say that until the tech actually exists, this is a great way to detect live deepfakes. Not using the technique just because maybe sometime in the future it won't work isn't very sound. For an extreme opponent you may need additional s…

This may be like a proof of work cryptography issue, except the burden of work is on the deep fake. Just ask a battery of questions, just like out of a Bladerunner scene or whatever. This is still the problem with AI. It depends on tons of datasets and connectivity. Human data and human code are kind of the same. Even individually, we can start with jackshit and still come up with an answer, whether right or wrong. Ah, Lisp.

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

#205

Post by anticristi »

Nowado wrote: post #156
Strom wrote: post #113

Earlier quoted context omitted.

> This is a current limitation The thing with any AI/ML tech is that current limitations are always underplayed by proponents. Self-driving cars will come out next year, every year. I'd say that until the tech actually exists, this is a great way to detect live deepfakes. Not using the technique just because maybe sometime in the future it won't work isn't very sound. For an extreme opponent you may need additional s…

In terms of this particular tech previous obvious limitation, namely no blinking, worked for something like a quarter from discovery. Venn diagram of people who someone wants to trick by this particular tech, those who read any security guidelines and those worthy of applying this kind of approach to in the first place is however pretty narrow for the foreseeable future. It's more of a narrative framing device to tal…

Exactly! Our SecOps includes seeing people regularly. Until deep fakes can fake accents, tone, body language and jokes, we're safe. :)

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

#206

Post by anticristi »

pclmulqdq wrote: post #169
Strom wrote: post #113

Earlier quoted context omitted.

> This is a current limitation The thing with any AI/ML tech is that current limitations are always underplayed by proponents. Self-driving cars will come out next year, every year. I'd say that until the tech actually exists, this is a great way to detect live deepfakes. Not using the technique just because maybe sometime in the future it won't work isn't very sound. For an extreme opponent you may need additional s…

The only person who is promising self driving cars next year (and has done so every year for the past 5 years) is Elon Musk. Most respectable self-driving car companies are both further along than Tesla and more realistic about their timelines.

Self-driving cars are common in Europe for decades. We just use the less cool term "subway" for them.

Sorry, I couldn't resist. :)

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

#207

Post by partdavid »

TillE wrote: post #147
elicash wrote: post #12

Earlier quoted context omitted.

Here's what Meta's blenderbot replied with: "The Tokyo tower is taller than the eiffel tower. Interesting facts like that interest me. Do you know about it?"

I'm not surprised that it responded with a random unrelated fact, but it is funny that the second sentence is incredibly awkward, and the last one isn't really coherent English. Just a total AI meltdown from one simple question.

People need to know about the CAN EAT MORE.

https://www.youtube.com/watch?v=CIoBSYpgYRw

For me, I call these Eliza-isms, since it reminds me of its simple formulas like "Can you tell me more about ___" that people got so much mileage out of.

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

#209

Post by anticristi »

ErikCorry wrote: post #177
WalterBright wrote: post #73

Earlier quoted context omitted.

I wonder how good the deepfake would be for things it didn't have training data on. For example, making an extreme grimace. Or have the caller insert a ping pong ball in his cheek to continue, or pull his face with his fingers. One thing I notice with colorized movies is the color of the actor's teeth tends to flicker between grey and ivory. I wonder if there are similar artifacts with deep fakes.

"Please put one finger behind each ear and flap them at me."

I had to laugh with tears at this one. :)

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

#210

Post by hugobitola »

sbszllr wrote: 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…

What if the real person draws something on his face? Does the deepfake algorithm removes it from the resulting image? Can you ask the caller to draw a line on his face with a pen as a test?
Post reply on HN