Skip to content

Adversarial Training for Enhanced Image Recognition Security

Notifications You must be signed in to change notification settings

iamazizhaider/CNN-Adversarial-Training

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

3 Commits
 
 
 
 
 
 
 
 

Repository files navigation

EE-433: Deep Learning

Semester Project

Adversarial Training for Enhanced Image Recognition Security

Abstract

This project focuses on enhancing the security of Convolutional Neural Networks (CNNs), against adversarial attacks in image recognition tasks. We explore two adversarial attacks in our project which are Fast Gradient Sign Method (FGSM) and L0 Norm. Through experimentation we showed that mixing adversarial images with normal training data can improve system’s accuracy against adversarial attacks . Additionally, we propose leveraging the model itself to generate adversarial images for improved defense using PyTorch Framework. We demonstrate the effectiveness of these techniques in strengthening the model resilience against attacks and increase its robustness.

Team Members

Arooj Fatima (2020-EE-152A)
Ali Hussain (2020-EE-168A)
Muhammad Aziz Haider (2020-EE-172A)
Subhan Mansoor (2020-EE-175A)

Submitted to

Dr. Ahsan Tahir (Course Instructor)

About

Adversarial Training for Enhanced Image Recognition Security

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published