Name
Abstract | ||
|---|---|---|
Phishing is a type of malicious attack that involves the fooling of unsuspecting victims into providing or sharing personal information such as names, addresses, and banking information, which may lead to damages to the individual such as identity theft and financial losses. To combat phishing attacks, there have been many strides toward the use of newer technologies instead of conventional approaches such as personnel training and physical security. These technologies involve a proactive approach towards identifying Phishing websites that utilize machine learning and have become more and more efficient. In this paper, a more proactive and online machine learning approach is proposed that utilize features that have been well-accepted among industries and academia. Within the algorithm, prioritizing of features will he broken up into layers, and the output of the tool will he a digital tag that could be included in web browsers for quick identification and classification. If a site is tagged, the website owner will have the opportunity to legitimize the website through a detailed informational session and will allow them to fix any features that may be classified as malevolent in nature. |
Year | DOI | Venue |
|---|---|---|
2019 | 10.1109/GCWkshps45667.2019.9024428 | 2019 IEEE GLOBECOM WORKSHOPS (GC WKSHPS) |
Keywords | DocType | ISSN |
phishing, social engineering, machine learning, Phishiank, openfish, Alexa | Conference | 2166-0069 |
Citations | PageRank | References |
0 | 0.34 | 0 |
Authors | ||
2 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Daniel Brites | 1 | 0 | 0.34 |
| Mingkui Wei | 2 | 0 | 0.34 |