Bonus: zkpod.ai & Attested Audio Experiment with Daniel Kang

Transcript

in last week's episode Kobe and I talked about zkpod.ai the voice AI trained on transcripts from our show and using both my and Kobe's voice to share insights and answer questions about ZK topics if you haven't yet checked it out please do head over to zkpod.ai now this is a bonus episode following up on that topic so we want to introduce a collaboration that we're doing with Daniel Kang from UIUC he's been on the show before and he's someone who's working in the intersection of ZK and AI with our project we aim to use ZK snarks to prove that some piece of audio is from us that is from the original podcast audio and to distinguish this from the zkpod.ai generated audio this is similar to his previous work on image provenance now

applied to audio and it's something that we think could be relevant for Content creators as well as just being a cool demonstration of how ZK can be used in combination with or to differentiate us from AI now here is my interview with Daniel Kang all about our attested audio experiment thank you so I'm really happy to have Daniel Kung professor of computer science at UIUC back on the show Welcome Back Daniel thank you thank you for having me it's a pleasure to be here this comes right after this interview I just did with Kobe all about zkpod.ai we've been doing a project together around the zkpod.ai project and I wanted to bring you on to be able to talk a bit more about that yeah I'm super excited to be on to chat about the project we've been working on which you can almost think of as the

opposite or the antagonist to zkplot.ai so it'll be an interesting mix yeah when you were last on this show we talked a lot about the work you had done around image provenance what we want to talk about today is actually the work we're doing together around ckpod.ai which is about audio provenance share a little bit about what you've been working on on that front yeah I've been working uh to so this is this actually Dives directly into the wider range of use cases that I just mentioned and I've been working closely with you Anna to produce a demonstration which will be hopefully live when this podcast airs the demonstration we're doing is that in the last podcast we mentioned that if we have an attested source of images in particular camera you can do things like prove private edits now similarly for

audio if you have a tested source of audio for example a microphone you can do something similar and so this way you can prove that you produce a specific clip of audio using a real microphone and furthermore there are ways to link that specific level audio to a specific microphone that you own so others can't spoof your Hardware but tested microphones yeah unfortunately these microphones don't exist and I think that's partially because it's consumer demand yeah and so one of the things that we're trying to do with our project is to show that there are really cool applications and what we've done is that we've released an example of simulating the attested microphone and combining this with a zero knowledge

proof as AK snark that three sources of audio uh you Anna me and Kobe were combined honestly um and the way that we did that was to instead of having the attested microphone we'll have signed that initial audio it's sort of emulating it but yeah this is definitely meant as a demonstration to show kind of like the flow through that's absolutely correct and for the time being we're using uh our ethereum uh private keys to emulate the tested sensor yeah totally is there some sort of alteration on these clips is there anything that like or could there be sort of alterations edits or you know audio compression something like that done and still maintain that

zkp through it yeah so there are many circumstances where you don't want to release the entire original audio for example let's say that I accidentally said uh some private information say my phone number and I want to cut it out of the clip you can do these kinds of edits using these ZK snarks and still prove that they came from the original attested microphone and so for example I'm not sure how much I should reveal about your podcast Anna but sometimes there are parts that are clipped out uh due to uh you know flubs yes definitely even with those edits I guess we could still using this system potentially prove that the original audio files came from us that's correct that's the amazing thing about these zero knowledge

proofs and one of the reasons I'm so excited about this technology yeah I think by the time we air this we will have this work and we'll be adding this in the show notes if people want to find out more but maybe we can also talk a little bit about the challenges and the limitations of this as we said this is an experiment and a demonstration but yeah what's still challenging with some system like this yeah so the the first obvious challenge that we mentioned is that we currently don't have a tested microphones so this is not something that we can deploy in the wild today although I hope that this will increase in this prevalence over the next few years cool another common uh concern that's brought up with the tested sensors of broadly speaking is the ability to basically play a recording uh

whether this be uh say taking a picture of a picture or in the case of a microphone play an audio clip and then recording it with an attested microphone yeah that's right so these are very valid concerns and there's a number of ways that we can go about addressing these it's actually easier to explain for images one thing you can do for cameras is to also include a depth sensor which actually many phones do today and include the depth information with the pixels and so this way you can tell that you didn't take an image of something that was flat now for audio there's uh there's no such a specific equivalent but you could imagine combining the attested microphone with something like an attested video camera and then proving using say zkml that the

lip movement matches up with the audio that was produced and also combined this with a depth sensor to prevent recording this works as long as there's no deep fake of the video as well I guess yeah that's right so if you just if you just have the camera this uh only works if you don't have a deep thick of the video okay uh but if you have the depth sensor as well this prevents things like a deep thick of a video which is played on a 2d screen are there any other limitations like why can't we today already use this with like a full episode say yeah the other big limitation is uh the computational complexity in producing these proofs unfortunately they're still quite expensive but due to the amazing work of well a lot of people in this space uh you know ranging from Academia to

Industry to Independent researchers the cost of proving is going down dramatically and I expect that to be to change in the next six to 12 months as well so hopefully a lot of these challenges will be overcome due to advances in hardware and also uh the ZK snark proving systems totally yeah just to mention for this particular experiment we used a clip that I think is 30 seconds long and how long did that take uh I don't have the exact number off the top of my head I think it takes around 20 minutes to prove for 30 seconds so this is about a 40 times blow up in in time but as I mentioned that there's lots of work both ranging all the way from the proving systems to the hardware that'll bring this down and so even if you just apply work that's being

developed today that cost will go down by maybe about five to ten times nice thanks Daniel thanks for sharing this with us and for coming back on the show yeah thank you for having me foreign s up our bonus episode all about the attested audio experiment if you want to keep tabs on the project be sure to follow ZK pod AI on Twitter and we should be posting any updates over there so yeah thanks for listening