UWSpace will be migrating to a new version of its software from July 29th to August 1st. UWSpace will be offline for all UW community members during this time.

Show simple item record

dc.contributor.authorYou, Yuzhe
dc.date.accessioned2023-06-28 20:11:22 (GMT)
dc.date.available2024-06-28 04:50:04 (GMT)
dc.description.abstractAdversarial machine learning (AML) focuses on studying attacks that can fool machine learning algorithms into generating incorrect outcomes as well as the defenses against worst-case attacks to strengthen the adversarial robustness of machine learning models. Specifically for image classification tasks, it is difficult to comprehend the underlying logic behind adversarial attacks due to two key challenges: 1) the attacks exploiting “non-robust” features that are not human-interpretable and 2) the perturbations applied being almost imperceptible to human eyes. We propose an interactive visualization system, AdvEx, that presents the properties and consequences of evasion attacks as well as provides data and model performance analytics on both instance and population levels. We quantitatively and qualitatively assessed AdvEx in a two-part evaluation including user studies and expert interviews. Our results show that AdvEx is effective both as an educational tool for understanding AML mechanisms and a visual analytics tool for inspecting machine learning models, which can benefit both AML learners and experienced practitioners.en
dc.publisherUniversity of Waterlooen
dc.subjectinformation visualizationen
dc.subjectexplainable AIen
dc.subjectadversarial attacksen
dc.subjectmachine learningen
dc.titleAdvEx: Interactive Visual Explorations of Adversarial Evasion Attacksen
dc.typeMaster Thesisen
uws-etd.degree.departmentDavid R. Cheriton School of Computer Scienceen
uws-etd.degree.disciplineComputer Scienceen
uws-etd.degree.grantorUniversity of Waterlooen
uws-etd.degreeMaster of Mathematicsen
uws-etd.embargo.terms1 yearen
uws.contributor.advisorZhao, Jian
uws.contributor.affiliation1Faculty of Mathematicsen

Files in this item


This item appears in the following Collection(s)

Show simple item record


University of Waterloo Library
200 University Avenue West
Waterloo, Ontario, Canada N2L 3G1
519 888 4883

All items in UWSpace are protected by copyright, with all rights reserved.

DSpace software

Service outages