CLASSIFICATION OF MALICIOUS URLS FOR WEB USING RIPPER ALGORITHM

Ergugneet Kaur ,Jaswinder Singh

doi:10.26483/ijarcs.v8i7.4141

Abstract

Now a days Web data is the most discussed topic. In various fields related to internet produces data of thousands of gigabytes every minute. Various applications uses multimedia data sharing procedure. So data will automatically be of bulk amount. This bulk amount of data is hard to process, takes longer time of search this much large data. RIPPER (Repeated Incremental Pruning to Produce Error Reduction) is one of the Classification rule algorithm.

Highlights

1.1 Web Data Web related data is the application of specialized tools through which large amount of data will be processed
Because data produced in different mediums like audio, videos, text etc. this type of data is produced in billions of bytes every hour
In a multi-class situation, the rules generated from the RIPPER algorithm are ranked in ascending order based on the number of examples in the class

Summary

Introduction

1.1 Web Data Web related data is the application of specialized tools through which large amount of data will be processed. That list of malicious and legitimate URL can be identified[7]. Those which pass the contents description will be put into the legitimate list of URLs. Ripper Algorithm RIPPER algorithm builds a single rule in the following steps:

Results

Conclusion