Securing Machine Learning Supply Chains

Abstract

Recent cyber-attacks on supply chains such as the large-scale SolarWinds attack are gaining the attention of cybersecurity experts. Supply chain attacks are growing in frequency and are taking advantage of the trust that organizations put in the dependencies of their supply. The machine learning supply chain is incredibly vulnerable to this category of attack because of the large number of dependencies utilized. We demonstrate a weakness in a machine learning supply chain by attacking the models parameters. We then demonstrate how an organization can implement secure checkpoints that generate integrity metadata and detect this class of attack before proceeding to the next phase in the supply chain.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Sep 01, 2021
Accession Number
AD1164482

Entities

People

  • Joshua D. Strubel

Organizations

  • Naval Postgraduate School

Tags

Communities of Interest

  • Autonomy
  • Cyber

DTIC Thesaurus Topics

  • Agile Software Development
  • Artificial Intelligence
  • Computer Languages
  • Computer Programming
  • Computer Programs
  • Computer Science
  • Computers
  • Cyberattacks
  • Cybersecurity
  • Data Storage Systems
  • Failure Mode And Effect Analysis
  • Information Systems
  • Machine Learning
  • Network Science
  • Neural Networks
  • Operating Systems
  • Software Development
  • Standards
  • Supply Chain
  • Supply Chain Management

Fields of Study

  • Computer science

Readers

  • Agent-Based Social Robotics and Mobile-Assisted Learning in Virtual Environments.
  • Cybersecurity.
  • Systems Analysis and Design

Technology Areas

  • AI & ML
  • AI & ML - Neural Networks
  • Cyber