Improving Deep Learning Model Robustness Against Adversarial Attack by Increasing the Network Capacity

TL;DR

This paper investigates enhancing deep learning model robustness against adversarial attacks by increasing network capacity, supported by experimental analysis and practical recommendations.

Contribution

It introduces a method of increasing network capacity to improve robustness, with experimental validation demonstrating its effectiveness.

Findings

Enhanced robustness against adversarial attacks

Network capacity increase improves security

Provides practical guidelines for model design

Abstract

Nowadays, we are more and more reliant on Deep Learning (DL) models and thus it is essential to safeguard the security of these systems. This paper explores the security issues in Deep Learning and analyses, through the use of experiments, the way forward to build more resilient models. Experiments are conducted to identify the strengths and weaknesses of a new approach to improve the robustness of DL models against adversarial attacks. The results show improvements and new ideas that can be used as recommendations for researchers and practitioners to create increasingly better DL algorithms.