Open AccessMachine Learning Based Malicious URL Detection
Author(s) -
Divya Kapil,
Atika Bansal,
. Anupriya,
Nidhi Mehra,
Aditya Joshi
Publication year - 2020
Publication title -
international journal of engineering and advanced technology
Language(s) - English
Resource type - Journals
ISSN - 2249-8958
DOI - 10.35940/ijeat.d1006.0484s19
Subject(s) - computer science , c4.5 algorithm , the internet , naive bayes classifier , computer security , precision and recall , machine learning , malware , world wide web , artificial intelligence , support vector machine
Today Internet technology has become an essentialpart of our life for education, entertainment, gaming, bankingand communication. In this modern digital era, it is very easy tohave any information by one click. But everything which haspros and cons, as we have any information at our tips butInternet is an attack platform also. When we use Internet to makeour work easy same time many attacker try to steal informationfrom our system. There are many means for attacking, maliciousURL one of them. When a user visits a website, which ismalicious then it triggers a malicious activity which ispredesigned. Hence, there are various approaches to finddangerous URL on the Internet. In this paper, we are usingmachine learning approach to detect malicious URLs. We usedISCXURL2016 dataset and used J48, Random forest, Lazyalgorithm and Bayes net classifiers. As performance metrics, wecalculate accuracy, TPR, FPR, precision and recall.