[rdrdg]

Currently, we are consider image, video and audio data types. This multi-modal idea sounds interesting none the less, thanks for sharing :)

[spuz]

There are companies that already provide this kind of service so it might be interesting for you to combine efforts:

https://www.youtube.com/watch?v=e0elNU0iOMY

[jka]

Thanks! You're welcome. The noise signature could be included in-band, and wouldn't necessarily require multiple machine learning models to verify.

[suryaknr]

You're right, in-band noise signatures is a pretty cool idea. We take inspiration from digital signal processing techniques when building our ML products.

[jka]

Grand. Take with a grain of salt, but it's possible you could find https://osf.io/m43tg/ worth a look.