The scam filter that fights back

Bachelor thesis (2016)

Contributors

G.J.P.M. Houben (mentor)
Programme
Web Information Systems (EEMCS) (TU Delft)
Copyright: © 2016 The Author(s)
More Info
expand_more

Published Date

29-06-2016

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.

Programme

Web Information Systems

Abstract

Filtering out scam mails and deleting them does not hurt a scammer in any way, but wasting their time by sending fake replies does. As the amount of replies grows, the amount of time a scammer has to spend responding to e-mails increases. This bachelor project has created a revolutionary system that recommends replies that can be sent to answer a scam mail. This makes it very easy for users to waste a scammer's time and destroy their business model. The project has a unique adaptation of the Elo rating system, which is a very popular algorithm used by systems ranging from chess to League of Legends. A Google Chrome plugin was developed with user friendliness in mind, to let people reply to scam mails quickly. To gather replies, a crowdsourcing website, which also trains the Elo system, was set up. Finally, a Python server connects all the parts, allowing for cross platform communication.