Ensuring Trustworthy Neural Network Training via Blockchain

Edgar Navarro, Kyle J. Standing, Gaby G. Dagher, Tim Andersen

Research output: Chapter in Book/Report/Conference proceedingChapter

Abstract

As Artificial Intelligence prevalence grows, it highlights the risk in relying on compromised models, thereby fueling a growing need to ensure the integrity of trained AI models. In this paper, we present a novel blockchain-based system, designed to authenticate the integrity of trained neural network models. The system addresses the risk of manipulation of a model by strategically re-computing intervals of the training process. Further, the blockchain network provides a traceable, immutable, trusted ledger for cataloging the intricate processes of training and validation. We consider two primary entities involved: ‘submitters’, who submit trained models, and ‘verifiers’, who re-train distinct sections of the submitted models to validate their integrity. The design of the blockchain system emphasizes efficiency by selectively targeting a portion of all training intervals. This is made possible through the use of an innovative weight-analysis algorithm, which applies an Absolute Change approach to identify outliers. We implement our solution to demonstrate that the proposed blockchain system is robust, and the weight-analysis algorithm is accurate and scalable.

Original languageAmerican English
Title of host publication2023 IEEE 5th International Conference on Cognitive Machine Intelligence (CogMI)
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages31-40
Number of pages10
ISBN (Electronic)9798350323832
DOIs
StatePublished - 1 Jan 2023
Event5th IEEE International Conference on Cognitive Machine Intelligence, CogMI 2023 - Atlanta, United States
Duration: 1 Nov 20233 Nov 2023

Publication series

NameProceedings - 2023 IEEE 5th International Conference on Cognitive Machine Intelligence, CogMI 2023

Conference

Conference5th IEEE International Conference on Cognitive Machine Intelligence, CogMI 2023
Country/TerritoryUnited States
CityAtlanta
Period1/11/233/11/23

Keywords

  • blockchain
  • machine learning
  • neural networks

EGS Disciplines

  • Computer Sciences

Fingerprint

Dive into the research topics of 'Ensuring Trustworthy Neural Network Training via Blockchain'. Together they form a unique fingerprint.

Cite this