Abstract

This project proposes a new self-supervised ad-blocker to minimize the amount of human effort required to effectively combat pushed advertisements. Current ad-blocker models are expensive to develop and not always effective in identifying advertisements. We investigated the possibility of solving these problems with the introduction of a deep learning, self-supervised ad-blocker model. More specifically, the proposed ad-blocker will be trained in a self-supervised fashion to tackle the issue of lacking labelled training data. The proposed solution was prototyped using Pytorch and achieved a detection accuracy of 81% on a diverse selection of popular websites.

Faculty Advisor/Mentor

Rui Ning

Document Type

Paper

Disciplines

Information Security

DOI

10.25776/qwre-ck73

Publication Date

11-2021

Upload File

wf_yes

Share

COinS
 

Self-Supervised Perceptual Ad-Blocker

This project proposes a new self-supervised ad-blocker to minimize the amount of human effort required to effectively combat pushed advertisements. Current ad-blocker models are expensive to develop and not always effective in identifying advertisements. We investigated the possibility of solving these problems with the introduction of a deep learning, self-supervised ad-blocker model. More specifically, the proposed ad-blocker will be trained in a self-supervised fashion to tackle the issue of lacking labelled training data. The proposed solution was prototyped using Pytorch and achieved a detection accuracy of 81% on a diverse selection of popular websites.