University of Twente Student Theses
Fighting Phishing at the Website Host
Eyk, Jan-Niclas van (2023) Fighting Phishing at the Website Host.
|
PDF
6MB |
| Abstract: | The Anti Phishing Working Group (APWG) regularly reports an increase in phishing attacks. Recent events, such as the COVID-19 pandemic, forced more people to use the internet, making phishing more interesting and amplifying the aforementioned trend. Users can protect themselves client-side by relying on built-in browser security mechanisms or installing additional extensions to identify dangerous websites. However, this shifts the responsibility to each end-user. This work focuses on finding ways to detect phishing at the website host instead. All users are protected by such mechanisms, making it more efficient than client-side detection. The website host also has access to data not commonly available to clients, which could help to improve the classification process. CodeSandbox’s platform regularly is exploited by phishers as a free website host. Their data is used to create a machine learning system that helps to classify phishing before it is able to fool victims. With the XGBoost classifier achieving a balanced accuracy of 90.64%, the results are comparable to academic literature. |
| Item Type: | Essay (Master) |
| Clients: | CodeSandbox B.V., Amsterdam, Netherlands |
| Faculty: | EEMCS: Electrical Engineering, Mathematics and Computer Science |
| Subject: | 54 computer science |
| Programme: | Computer Science MSc (60300) |
| Link to this item: | https://purl.utwente.nl/essays/94455 |
| Export this item as: | BibTeX EndNote HTML Citation Reference Manager |
Show download statistics for this publication
Show download statistics for this publicationRepository Staff Only: item control page