Zero Knowledge Arguments for Verifiable SamplingDownload PDF

Published: 04 Nov 2021, Last Modified: 15 May 2023PRIML 2021 PosterReaders: Everyone
Keywords: Zero Knowledge Proofs, Differential Privacy, Sampling
Abstract: In privacy-preserving machine learning, it is less obvious to verify correct behavior of participants because they are not supposed to reveal their inputs in cleartext to other participants. It is hence important to make federated machine learning robust against data poisoning and related attacks. While input data can be related to a distributed ledger (blockchain), a less studied input is formed by the random sampling parties perform. In this paper, we describe strategies based on zero knowledge proofs to allow parties to prove they perform sampling (and other computations) correctly. We sketch a number of alternative ways to implement our idea and provide some preliminary experimental results.
Paper Under Submission: The paper is NOT under submission at NeurIPS
1 Reply