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.
Document Details
- Document Type
- Technical Report
- Publication Date
- Jul 12, 2021
- Accession Number
- AD1149669
Entities
People
- Harrison D Foley
Organizations
- United States Naval Academy