Deceiving Neural Networks in Common Applications

Abstract

As neural networks are deployed to solve a wide variety of problems, it becomes increasingly important to understand what can cause them to fail. The goal of our project is to cause neural networks to perform poorly via adversarial methods that are more destructive than previous state-of-the-art approaches. Specifically, we have drastically improved adversarial attacks on images of faces in order to avoid detection by facial recognition, and we have carried out the first successful data-poisoning attacks for reinforcement learning.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jul 12, 2021
Accession Number
AD1149669

Entities

People

  • Harrison D Foley

Organizations

  • United States Naval Academy

Tags

Communities of Interest

  • Autonomy
  • Cyber
  • Energy and Power Technologies

DTIC Thesaurus Topics

  • Artificial Intelligence
  • Artificial Intelligence Computing
  • Artificial Intelligence Software
  • Automata Theory
  • Computers
  • Data Mining
  • Dimensionality Reduction
  • Facial Recognition
  • Image Classification
  • Information Processing
  • Information Science
  • Information Systems
  • Machine Learning
  • Network Science
  • Neural Networks
  • Probability
  • Recognition
  • Reinforcement Learning
  • Self Organizing Systems
  • Supervised Machine Learning
  • United States
  • United States Naval Academy

Fields of Study

  • Computer science

Readers

  • Cybersecurity.
  • Neural Network Machine Learning.
  • Systems Analysis and Design

Technology Areas

  • AI & ML
  • AI & ML - Neural Networks