Where ZK and ML intersect with Yi Sun and Daniel Kang
Zero Knowledge
Zero Knowledge Machine Learning (ZKML) and its Practical Application
ZKML aims to generate zero knowledge proofs that a machine learning model has run on specific input data. This method inherits the benefits of zero knowledge proofs such as succinctness, zero knowledge, completeness, and soundness. One practical application of ZKML is to prove the accurate execution of machine learning models, especially when the models are operated behind an API interface. For instance, it can be used to verify that an ML provider is keeping their model weights confidential when processing external data.
00:00
Transcript
Play full episode
Remember Everything You Learn from Podcasts
Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.
