Exploring the Removal of Bit-Planes for Increased Adversarial Robustness (Preprint)

Abstract

Machine Learning has been found to be a very valuable and powerful tool, that will almost certainly see an increase in use in the future. However, it has also been found to have some vulnerabilities that could be exploited. This is concerning overall, but particularly important if the machine learning model is being used for safety-critical, but even for non-safety-critical applications. Many defenses have been worked on to combat this issue, but most defenses seem to be broken shortly after being proposed. These defenses are also typically very resource hungry as well as cause normal performance to drop. In this work, we present several ideas as to how to make robust models using fewer resources and without impacting clean performance. We explore several different combinations of defenses as well as metrics to determine the impact of the attacks on metrics besides just accuracy.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
May 10, 2023
Accession Number
AD1200986

Entities

People

  • Alex Hildenbrandt
  • Ashley Diehl
  • Christopher Menart
  • Hannah Richards
  • Melissa Robertson
  • Robert Canady

Organizations

  • Air Force Research Laboratory
  • Brigham Young University
  • Vanderbilt University

Tags

Communities of Interest

  • Air Platforms
  • Autonomy
  • Sensors

DTIC Thesaurus Topics

  • Accuracy
  • Air Force
  • Air Force Facilities
  • Air Force Research Laboratories
  • Artificial Intelligence Software
  • Autonomy
  • Computer Languages
  • Detectors
  • Electronic Mail
  • Image Classification
  • Learning
  • Machine Learning
  • Military Research
  • Natural Language Processing
  • Neural Networks
  • Perturbations
  • Probability
  • Recognition
  • Sensor Fusion
  • Synthetic Aperture Radar
  • Training
  • United States

Fields of Study

  • Computer science

Readers

  • Agent-Based Social Robotics and Mobile-Assisted Learning in Virtual Environments.
  • Educational Psychology
  • Public Financial Management and Budgeting

Technology Areas

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