Physical data auditing for attack detection in cyber-manufacturing systems: Blockchain for machine learning process

Jinwoo Song, Diksha Shukla, Mingtao Wu, Vir V. Phoha, Young B. Moon

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Auditing physical data using machine learning can enhance the security in Cyber-Manufacturing System (CMS). However, the physical data processing itself is prone to cyber-attacks. Connections based on the internet in CMS opens the route for adversaries to compromise the attack detection system itself. To prevent data from malicious data injection in CMS, this paper proposes an enhanced Simple Convolutional Neural Network (SCNN) based attack detection system employing a blockchain. There are three contributions of this paper: (i) introducing a secure attack detection system using blockchain, (ii) optimizing the cost and time for CMS by training on the simulated images, and (iii) presenting a real-time attack detection system for CMS by simplifying the convolutional neural network. The paper demonstrates the effectiveness of the blockchain implementation by presenting the comparative performance analysis of the proposed attack detection system with and without blockchain implementation using an example of a simulated attack on the machine learning process.

Original languageEnglish (US)
Title of host publicationAdvanced Manufacturing
PublisherAmerican Society of Mechanical Engineers (ASME)
ISBN (Electronic)9780791859384
DOIs
StatePublished - Jan 1 2019
EventASME 2019 International Mechanical Engineering Congress and Exposition, IMECE 2019 - Salt Lake City, United States
Duration: Nov 11 2019Nov 14 2019

Publication series

NameASME International Mechanical Engineering Congress and Exposition, Proceedings (IMECE)
Volume2B-2019

Conference

ConferenceASME 2019 International Mechanical Engineering Congress and Exposition, IMECE 2019
CountryUnited States
CitySalt Lake City
Period11/11/1911/14/19

Keywords

  • Blockchain
  • Cyber-Manufacturing System
  • Image Classification
  • Machine Learning
  • Physical Auditing
  • Testbed

ASJC Scopus subject areas

  • Mechanical Engineering

Fingerprint Dive into the research topics of 'Physical data auditing for attack detection in cyber-manufacturing systems: Blockchain for machine learning process'. Together they form a unique fingerprint.

  • Cite this

    Song, J., Shukla, D., Wu, M., Phoha, V. V., & Moon, Y. B. (2019). Physical data auditing for attack detection in cyber-manufacturing systems: Blockchain for machine learning process. In Advanced Manufacturing (ASME International Mechanical Engineering Congress and Exposition, Proceedings (IMECE); Vol. 2B-2019). American Society of Mechanical Engineers (ASME). https://doi.org/10.1115/IMECE2019-10442