Omg, looking forward to Yoga-based Captchas in the future: That ain't looking like a proper downward dog to me, pal, no access for you
To uncover a deepfake video call, ask the caller to turn sideways
31–40 of 285 posts
Re: To uncover a deepfake video call, ask the caller to turn sideways
#32deepfakes done in a unethical way is a real threat indeed. This paper shows how to identify some of them.
And metaphysics.ai are doing something a bit different. Let's wait and see.
Re: To uncover a deepfake video call, ask the caller to turn sideways
#33Re: To uncover a deepfake video call, ask the caller to turn sideways
#34Is audio harder to fake than video? I was watching the Keanu one and wondered if it is harder to real time fake Keanu’s voice than his face?
Re: To uncover a deepfake video call, ask the caller to turn sideways
#35Deepfake models are trained on very similar data. They don't generalize well, usually. E.g. we take lots of data from YouTube videos of a single person under a specific condition (same time, same day, same haircut etc.)
I know that as I spent quite some time researching these models and worked on a deepfake detection startup. Purely looking at it from a technological side, it's a cat mouse game. Similar to an antivirus software. A new method appears to create deepfakes. A new detection method is required.
However, we can also make use of the models to not properly generalize and their limitations of the training process. Anything that is out of distribution (very rare occurrence in training data) will be hard for the model: - blinking (if the model has ever only seen single frames it will create rather random unusual blinking behavior - turn around (as mentioned by the author, side views are rarer in the web) - take off your glasses - slap your cheek - draw something on your cheek - take scissors and cut a piece of your hair
The last two would be especially difficult and funny (:
Re: To uncover a deepfake video call, ask the caller to turn sideways
#36Re: To uncover a deepfake video call, ask the caller to turn sideways
#37Source: 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…
As far as I can see, secops is an eternal cat-and-mouse game.
job security
Re: To uncover a deepfake video call, ask the caller to turn sideways
#38Serendipitously over the weekend I was thinking about a future where for key sensitive data access (e.g. production main) you may need to have a quick 5 minute call (4th factor, "3D verification") where you would be asked to turn on your camera and be asked to answer some simple question and in different positions... Main thinking was how out of control it would get, it would probably end up looking like anti-cheat s…
> Main thinking was how out of control it would get…
From a job listing, circa 2024:
- Job may require occasional lifting. (No more than 20kg)
- Expected to travel up to 25% of the year.
- Proprietary access control requires users be able to do handstands and/or simple juggling. (Feats subject to change)
- EEOC employer.
Re: To uncover a deepfake video call, ask the caller to turn sideways
#39Hybrid Video/audio/semantic Captcha, perhaps? An audio prompt like 'Using your hand, repeat the numbers that I am signaling. Use set of fingers from what I am using'.
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!
Re: To uncover a deepfake video call, ask the caller to turn sideways
#40Source: 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…
As far as I can see, secops is an eternal cat-and-mouse game.
Literally an arms race.