Scaling up Trustless Neural Network Inference with Zero-Knowledge Proofs

ZKPs

Workshop 1 — SLS/Community Room, Floor 2

112

Scaling up Trustless Neural Network Inference with Zero-Knowledge Proofs

Talk

Beginner

ZKPs: Privacy, Identity, Infrastructure, & More

Day 3Thu, Oct 1314:15 - 14:3015 Mins

Mark as interesting

Attend Session

Export to Calendar

Room Details

Description

We present the first ZK-SNARK proof of valid inference for a full resolution ImageNet model. We will describe the arithmetization and quantization optimizations enabling us to SNARK large neural networks as well as a software package enabling transpilation from off-the-shelf models to halo2 circuits. We design protocols using our circuits to verify machine learning model predictions and accuracy and present concrete estimates of overhead costs based on our circuit implementations. This is joint

Recording

thumbnail

Visit the Devcon Archive to watch the recording.

Powered by Swarm & Etherna.