The Impact of Platform Vulnerabilities in AI Systems

Abstract

Artificial intelligence has become increasingly prevalant through the past five years, even resulting in a national strategy for artificial intelligence. With such widespread usage, it is critical that we understand the threats to AI security. Historically, research on security in AI systems has focused on vulnerabilities in the training algorithm (e.g., adversarial machine learning), or vulnerabilities in the training process (e.g., data poisoning attacks). However, there has not been much research on how vulnerabilities in the platform on which the AI system runs can impact the classification results. In this work, we study the impact of platform vulnerabilities on AI systems. We divide the work into two major part: a concrete proof-of-concept attack to prove the feasibility and impact of platform attack, and a higher-level qualitative analysis to reason about the impact of large vulnerability classes on AI systems. We demonstrate an attack on the Microsoft Cognitive Toolkit which results in targeted misclassification, leveraging a memory safety vulnerability in a third party library. Furthermore, we provide a general classification of system vulnerabilities and their impacts on AI systems specifically.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Sep 01, 2020
Accession Number
AD1143307

Entities

People

  • Ashley Kim

Organizations

  • Massachusetts Institute of Technology

Tags

Communities of Interest

  • Autonomy
  • Cyber
  • Engineered Resilient Systems

DTIC Thesaurus Topics

  • Artificial Intelligence
  • Artificial Intelligence Software
  • Automata Theory
  • Computational Science
  • Computer Languages
  • Computer Programming
  • Computer Science
  • Computers
  • Data Mining
  • Dimensionality Reduction
  • Electrical Engineering
  • Information Science
  • Information Systems
  • Machine Learning
  • Network Science
  • Neural Networks
  • Operating Systems

Fields of Study

  • Computer science

Readers

  • Distributed Systems and Data Platform Development
  • Neural Network Machine Learning.
  • Political Violence and Terrorism Studies.

Technology Areas

  • AI & ML
  • AI & ML - DoD AI Strategy
  • AI & ML - Neural Networks