A Spam Filtering Method Based on Multi-modal Features Fusion
Authors:
- Feng HuaminFHFeng Huamin
- Yang XinghuaYXYang Xinghua
- Liu BiaoLBLiu Biao
- Jiang ChaoJCJiang Chao
- 1 December 2011
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 421-426
Abstract
In recent years, to escape the spam detection of the text-based spam filtering system, spammers insert junk information into the email with images, and attach it to the message body. The traditional text-based filter cannot handle such spam image. In order to deal with the spam which contains text and images, a filtering method which fuses text, image and other multi-modal features is proposed in this paper. Firstly, extracting the text features and image features to build multiple classifiers, and then by employing the fusion method to choose the output of multiple classifier. Experimental results on TREC dataset show that the fusion method can have a better result than that of a single classifier and can achieve over 90% in accuracy rate.Keywords
This publication has 8 references indexed in Scilit:
- Statistical Machine Learning Used in Integrated Anti-Spam System2007
- Learning to Semantically Classify Email Messages2006
- An Approach to Spam Detection by Naive Bayes Ensemble Based on Decision Induction2006
- Using a probable weight based bayesian approach for spam filtering2005
- Image analysis for efficient categorization of image-based spam e-mail2005
- The Nature of Statistical Learning Theory1995
- Consensus theoretic classification methodsIEEE Transactions on Systems, Man, and Cybernetics, 1992
- The Consensus of Subjective Probability DistributionsManagement Science, 1968