Where ZK and ML intersect with Yi Sun and Daniel Kang
Zero Knowledge
00:00
Detecting Deep Fakes in Machine Learning
In some earlier papers, if I remember correctly, the Bonet paper and others was that they required the image to have public data to generate the proof. And so a lot of what you did was getting around that. One problem for both a tested image edits and also for machine learning is that you might want to hide some parts of the input. So in our work, we also introduced this for the ZKML space as well where you can compute a commitment in our case, a hash of the weights and reveal that. Because the commitment is binding, it forces the API provider to hash the weights,. then you can be assured that they're around the correct model.
Transcript
Play full episode
