Download PDFOpen PDF in browser

Secure Multiparty Computation for Privacy-Preserving Collaborative AI in Industrial IoT

EasyChair Preprint 13619

19 pagesDate: June 10, 2024

Abstract

Secure Multiparty Computation (MPC) has emerged as a promising solution for privacy-preserving collaborative Artificial Intelligence (AI) in the context of Industrial Internet of Things (IoT). Industrial IoT brings numerous benefits, but it also raises concerns about data privacy and security. Traditional approaches to collaborative AI involve sharing sensitive data among multiple parties, which can compromise privacy and expose valuable information to unauthorized access.

 

This abstract highlights the potential of MPC for addressing these challenges. MPC allows parties to jointly compute an AI model without revealing individual inputs, ensuring privacy and confidentiality. It leverages secure protocols, cryptographic techniques, trusted computing environments, and data anonymization to enable secure collaboration.

Keyphrases: Industrial IoT, Secure Multiparty Computation, Security, collaboration, data privacy, privacy preserving

BibTeX entry
BibTeX does not have the right entry for preprints. This is a hack for producing the correct reference:
@booklet{EasyChair:13619,
  author    = {Godwin Olaoye and Harold Jonathan},
  title     = {Secure Multiparty Computation for Privacy-Preserving Collaborative AI in Industrial IoT},
  howpublished = {EasyChair Preprint 13619},
  year      = {EasyChair, 2024}}
Download PDFOpen PDF in browser