Backdoor Attack on gaze estimation

Bachelor thesis (2023)

Authors

Y. Reda Electrical Engineering, Mathematics and Computer Science

Contributors

L. Du Embedded Systems - EEMCS (supervisor 1)
G. Lan Embedded Systems - EEMCS (supervisor 2)
X. Zhang Pattern Recognition and Bioinformatics - EEMCS (supervisor 2)
Faculty
Electrical Engineering, Mathematics and Computer Science
Copyright: © 2023 Yuji Reda
Gaze estimation Convolutional Neural Network Backdoor Attacks Badnets
More Info
expand_more

Published Date

25-06-2023

Language

English

Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Faculty

Electrical Engineering, Mathematics and Computer Science

Abstract

Badnets are a type of backdoor attack that aims at manipulating the behavior of Convolutional Neural Networks. The training is modified such that when certain triggers appear in the inputs the CNN is going to behave accordingly. In this paper, we apply this type of backdoor attack to a regression task on gaze estimation. We examine different triggers to discover which of them lead to better performance and thus infer which trigger aspects one can take the most advantage from. It turns out that placing frames around and drawing multiple lines across the images are the most effective for the training of Badnets.

Files

CSE3000_report.pdf
(.pdf | 5.33 Mb)