Deep Learning Defenses Against Adversarial Examples for Dynamic Risk Assessment

TL;DR

This paper investigates defenses against adversarial attacks on deep neural networks used in critical risk assessment tasks, demonstrating improved robustness without sacrificing accuracy on medical imaging data.

Contribution

It implements and evaluates multiple defense strategies against adversarial attacks, enhancing model robustness in sensitive applications like healthcare.

Findings

Defense methods increased model robustness

Accuracy was maintained after applying defenses

Approach applicable to various datasets and models

Abstract

Deep Neural Networks were first developed decades ago, but it was not until recently that they started being extensively used, due to their computing power requirements. Since then, they are increasingly being applied to many fields and have undergone far-reaching advancements. More importantly, they have been utilized for critical matters, such as making decisions in healthcare procedures or autonomous driving, where risk management is crucial. Any mistakes in the diagnostics or decision-making in these fields could entail grave accidents, and even death. This is preoccupying, because it has been repeatedly reported that it is straightforward to attack this type of models. Thus, these attacks must be studied to be able to assess their risk, and defenses need to be developed to make models more robust. For this work, the most widely known attack was selected (adversarial attack) and several defenses were implemented against it (i.e. adversarial training, dimensionality reduc tion and prediction similarity). The obtained outcomes make the model more robust while keeping a similar accuracy. The idea was developed using a breast cancer dataset and a VGG16 and dense neural network model, but the solutions could be applied to datasets from other areas and different convolutional and dense deep neural network models.