Btech thesis report on adversarial attack detection and purification of adverserially attacked images

TL;DR

This thesis explores methods to detect and purify adversarially attacked images using AutoEncoders, aiming to improve the robustness of machine learning models against subtle input perturbations.

Contribution

Introduces two novel AutoEncoder-based techniques for detecting and purifying adversarial attacks on images, enhancing model security.

Findings

Effective detection of adversarial images using proposed AutoEncoder methods

Successful purification of attacked images to restore model accuracy

Improved robustness of models against adversarial perturbations

Abstract

This is Btech thesis report on detection and purification of adverserially attacked images. A deep learning model is trained on certain training examples for various tasks such as classification, regression etc. By training, weights are adjusted such that the model performs the task well not only on training examples judged by a certain metric but has an excellent ability to generalize on other unseen examples as well which are typically called the test data. Despite the huge success of machine learning models on a wide range of tasks, security has received a lot less attention along the years. Robustness along various potential cyber attacks also should be a metric for the accuracy of the machine learning models. These cyber attacks can potentially lead to a variety of negative impacts in the real world sensitive applications for which machine learning is used such as medical and transportation systems. Hence, it is a necessity to secure the system from such attacks. Int this report, I focus on a class of these cyber attacks called the adversarial attacks in which the original input sample is modified by small perturbations such that they still look visually the same to human beings but the machine learning models are fooled by such inputs. In this report I discuss 2 novel ways to counter the adversarial attack using AutoEncoders, 1) by detecting the presence of adversaries and 2) purifying these adversaries to make target classification models robust against such attacks.