Zero Knowledge Arguments for Verifiable Sampling - Archive ouverte HAL Access content directly
Poster Communications Year :

Zero Knowledge Arguments for Verifiable Sampling

(1) , (1)
1
César Sabater
Jan Ramon

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.
Fichier principal
Vignette du fichier
main.pdf (179.05 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03464840 , version 1 (03-12-2021)

Identifiers

  • HAL Id : hal-03464840 , version 1

Cite

César Sabater, Jan Ramon. Zero Knowledge Arguments for Verifiable Sampling. NeurIPS 2021 Workshop Privacy in Machine Learning, Dec 2021, Sydney (Virtual), Australia. . ⟨hal-03464840⟩
49 View
63 Download

Share

Gmail Facebook Twitter LinkedIn More