Multi-Classification for Malicious URL Based on Improved Semi-Supervised Algorithm
- 1 July 2017
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 1, 143-150
Abstract
Web attacks are increasing and the scale of malicious URL continues to expand with the rapid development of the Internet, so that the network security situation is increasingly grim. In this case, this paper studies the URL multi-classification problem, which is a continuation of the reference [1] and follows the data sets and most of feature selection methods in it. Firstly, different types of URL structure is analyzed and features which have obvious directivity to the attack type are increased based on the original features. Secondly, an improved semi-supervised algorithm is proposed to train the URL multi-classification model. Finally, the effect of the multi-classification model is verified by using the data set with different labeling rate, which shows the improved algorithm has good classification performance compared to the previous algorithm.Keywords
This publication has 11 references indexed in Scilit:
- Online URL Classification for Large-Scale Streaming EnvironmentsIEEE Intelligent Systems, 2017
- Random forest in semi-supervised learning (Co-Forest)2013
- Transductive Relational Classification in the Co-training ParadigmLecture Notes in Computer Science, 2012
- PhishNet: Predictive Blacklisting to Detect Phishing Attacks2010
- Combined heuristics for determining order quantity under time-varying demandsJournal of Systems Engineering and Electronics, 2008
- Improve Computer-Aided Diagnosis With Machine Learning Techniques Using Undiagnosed SamplesIEEE Transactions on Systems, Man, and Cybernetics - Part A: Systems and Humans, 2007
- Tri-training: exploiting unlabeled data using three classifiersIEEE Transactions on Knowledge and Data Engineering, 2005
- Ensemble Methods in Machine Learning2000
- Combining labeled and unlabeled data with co-training1998
- Learning from noisy examplesMachine Learning, 1988