SNNzkSNARK An Efficient Design and Implementation of a Secure Neural Network Verification System Using zkSNARKs [Slides]

Abstract

zkSNARKS can be described as zero-knowledge: No secret information is revealed by the proof; Succinct: The size of the proof that is generated is small; Non-interactive: no challenge-response protocol; and ARgument of Knowledge: It is computationally intractable for the prover to produce a fake proof.