Please use this identifier to cite or link to this item:
Title: Exploring the vulnerabilities and enhancing the adversarial robustness of deep neural networks
Authors: Bai, Tao
Keywords: Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence
Engineering::Computer science and engineering::Computing methodologies::Image processing and computer vision
Issue Date: 2022
Publisher: Nanyang Technological University
Source: Bai, T. (2022). Exploring the vulnerabilities and enhancing the adversarial robustness of deep neural networks. Doctoral thesis, Nanyang Technological University, Singapore.
Abstract: Deep learning, especially deep neural networks (DNNs), is at the heart of the current rise of artificial intelligence, and the major breakthroughs in the last few years have been made by DNNs. It has been demonstrated in recent works that DNNs are vulnerable to human-crafted adversarial examples, which look normal in human eyes. Such adversarial instances can fool and mislead DNNs to misbehave as adversaries expected, causing serious consequences for various DNN-based applications in our daily life. To this end, this thesis dedicates to revealing the vulnerabilities of deep learning algorithms and developing defense strategies for combating adversaries effectively. We study current DNNs from the perspective of security with two sides: attack and defense. On the attack front, we explore the possibility of attacks against DNNs during test time with two types of adversarial examples: adversarial perturbations and adversarial patches. On the defense front, we develop solutions to defend against adversarial examples and investigate the robustness-preserving distillation techniques.
DOI: 10.32657/10356/160963
Schools: School of Computer Science and Engineering 
Rights: This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License (CC BY-NC 4.0).
Fulltext Permission: open
Fulltext Availability: With Fulltext
Appears in Collections:SCSE Theses

Page view(s)

Updated on Oct 3, 2023

Download(s) 50

Updated on Oct 3, 2023

Google ScholarTM




Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.