Skip to content

Evaluating the Use of Fast Adversarial Training in Defending Against Adversarial Patch Attacks

Notifications You must be signed in to change notification settings

pedromsferraz/AdversarialTrainingVsPatchAttacks

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

2 Commits
 
 
 
 
 
 

Repository files navigation

Evaluating the Use of Fast Adversarial Training in Defending Against Adversarial Patch Attacks

This project was developed as the Final Project for the Introduction to Machine Learning (CS680) course at the University of Waterloo.

In this study, we investigated the use of Fast Adversarial Training (FAST-AT) and Fast Bi-level AT (FAST-BAT) to defend against adversarial patch attacks. Our results showed that models trained using these methods significantly increased their accuracy when subjected to adversarial patch attacks, indicating that they had gained robustness against these attacks despite not being explicitly trained to defend against them. These findings demonstrate the potential of FAST-AT and FAST-BAT to enhance the robustness of Deep Neural Networks against a variety of adversarial attacks.

About

Evaluating the Use of Fast Adversarial Training in Defending Against Adversarial Patch Attacks

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published