A Multi-Classifier Based Prediction Model for Phishing Emails Detection Using Topic Modelling, Named Entity Recognition and Image ProcessingReportar como inadecuado




A Multi-Classifier Based Prediction Model for Phishing Emails Detection Using Topic Modelling, Named Entity Recognition and Image Processing - Descarga este documento en PDF. Documentación en PDF para descargar gratis. Disponible también para leer online.

Phishing is the act ofattempting to steal a user’s financial and personal information, such as creditcard numbers and passwords by pretending to be a trustworthy participant,during online communication. Attackers may direct the users to a fake websitethat could seem legitimate, and then gather useful and confidential informationusing that site. In order to protect users from Social Engineering techniquessuch as phishing, various measures have been developed, including improvementof Technical Security. In this paper, we propose a new technique, namely -APrediction Model for the Detection of Phishing e-mails using Topic Modelling,Named Entity Recognition and Image Processing-. The features extracted areTopic Modelling features, Named Entity features and Structural features. Amulti-classifier prediction model is used to detect the phishing mails.Experimental results show that the multi-classification technique outperformsthe single-classifier-based prediction techniques. The resultant accuracy ofthe detection of phishing e-mail is 99% with the highest False Positive Ratebeing 2.1%.

KEYWORDS

Phishing, Conditional Random Field Classifier, Latent Dirichlet Allocation, Natural Language Processing, Machine Learning, Image Segmentation, Image Processing

Cite this paper

Shyni, C. , Sarju, S. and Swamynathan, S. 2016 A Multi-Classifier Based Prediction Model for Phishing Emails Detection Using Topic Modelling, Named Entity Recognition and Image Processing. Circuits and Systems, 7, 2507-2520. doi: 10.4236-cs.2016.79217.





Autor: C. Emilin Shyni1, S. Sarju2, S. Swamynathan3

Fuente: http://www.scirp.org/



DESCARGAR PDF




Documentos relacionados