TypoWriter: A Tool to Prevent Typosquatting

Typosquatting is a form of internet cybersquatting generated from the mistakes (typos) made by internet users while typing a website address. It often leads the user to another unintended website. Sometimes it is exploited by cybersquatters to attract website traffic by redirecting common typos of popular websites to some other sites with malicious contents. A possible solution is defensive registration of similar domains and redirecting requests to the original site. This would be affordable for the owner of the original domain if a short list of such probable typo domain names can be predicted. Existing works on typosquatting mostly try to detect typo sites by analyzing logs. However, to the best of our knowledge, none of them can predict probable typo variations of a given URL at pre-registration phase. In this paper, we present TypoWriter, an RNN based error prediction tool to fill this gap. TypoWriter achieves a good performance in terms of successful predictions that match with the ground-truth. It is compared with five widely used typo generation tools and substantial improvement is observed.

I. Introduction

Usage of the Internet has been growing rapidly all over the world for several years. This has resulted in the increase of number of websites and visits to them. A possible way of visiting a website is by typing its URL on a browser. While typing the URL, users often make mistakes (typo) and hence cannot visit the desired website. The situation gets worse when the mistaken URL leads to a different website which the user does not intend to visit. Sometimes perpetrators exploit this phenomenon and purposefully register domain name that resembles common typing or spelling mistakes of a popular website. Two different domain names may be similar in various ways. Some domain names are visually similar, some are phonetically, and some names may result from spelling error of others. Many non-English popular names can be written with different spelling that are phonetically similar. Typosquatting is a form of cyber attack that uses these similarities to confuse valuable customers of popular domains.