Malicious websites considered as critical threats to the users’ systems that access these websites as hackers use these websites to steal users’ personal information or account information or even harms the users’ systems. Many solutions have been developed to detect and prevent these malicious websites, but these solutions are not fully effective as these websites are changed continuously. This paper evaluates various classification algorithms to predict malicious and non- malicious web sites, based on various feature selection scenarios. Reasonable results are reached with 100% accuracy, recall, and precision when applying Logistic Regression and Decision Tree algorithms while 95% when applying Naïve Bayes algorithm with good timing.
Emad El-Din, A., Hemdan, E. E., & El-Sayed, A. (2019). Malicious Website Detection using Machine Learning on Apache Spark. Menoufia Journal of Electronic Engineering Research, 28(ICEEM2019-Special Issue), 337-342. doi: 10.21608/mjeer.2019.64449
MLA
Aml Emad El-Din; Ezz El-Din Hemdan; Ayman El-Sayed. "Malicious Website Detection using Machine Learning on Apache Spark". Menoufia Journal of Electronic Engineering Research, 28, ICEEM2019-Special Issue, 2019, 337-342. doi: 10.21608/mjeer.2019.64449
HARVARD
Emad El-Din, A., Hemdan, E. E., El-Sayed, A. (2019). 'Malicious Website Detection using Machine Learning on Apache Spark', Menoufia Journal of Electronic Engineering Research, 28(ICEEM2019-Special Issue), pp. 337-342. doi: 10.21608/mjeer.2019.64449
VANCOUVER
Emad El-Din, A., Hemdan, E. E., El-Sayed, A. Malicious Website Detection using Machine Learning on Apache Spark. Menoufia Journal of Electronic Engineering Research, 2019; 28(ICEEM2019-Special Issue): 337-342. doi: 10.21608/mjeer.2019.64449
)
View on SCiNiTO