Time Slot: Track 2 17:00-1730 Language: Cantonese Speaker: Dr. Cathie So | Privacy & Scaling Explorations Team (Ethereum Foundation) | Hong Kong
In this hands-on workshop, participants will gain practical experience in building ZKML circuits using the keras2circom and/or EZKL transpiler. We will begin with an overview of the current state of zero-knowledge machine learning and its practical applications in protecting sensitive data and models. Then, using the keras2circom/EZKL library, we will walk through the process of converting a machine learning model in Python to a ZK circuit. Participants will have the opportunity to modify the circuit for specific use cases, such as IPFS CID matching and hash commitment, to enhance data and model integrity. By the end of the workshop, participants will have a better understanding of how to build zero-knowledge machine learning circuits and apply them to protect sensitive data and models. No prior experience with ZK is necessary, but familiarity with machine learning libraries is recommended.
Dr. Cathie So
Cathie is a ZKML researcher at Privacy & Scaling Explorations Team (Ethereum Foundation), exploring the potential of verifiable computation with privacy in the blockchain. A serial hackathon winner, she believes ZKML is key to transitioning from Web2 to Web3.