Improved spam filtering by extraction of information from text embedded image e-mail

ABSTRACT

The increase of image spam, a kind of spam in which the text message is embedded into an attached image to defeat spam filtering techniques, is becoming an increasingly major problem. For nearly a decade, content based filtering using text classification or machine learning has been a major trend of antispam filtering systems. A Key technique being used by spammers is to embed text into image(s) in spam email. In [4], we proposed two levels of ontology spam filters: a first level global ontology filter and a second level user-customized ontology filter. However, that previous system handles only text e-mail and the percentage of attached images is increasing sharply. The contribution of the paper is that we add an image e-mail handling capability to the previous anti-spam filtering system, enhancing the effectiveness of spam filtering.

REFERENCES

• 1: Battista Biggio , Giorgio Fumera , Ignazio Pillai , Fabio Roli, Image Spam Filtering Using Visual Information, Proceedings of the 14th International Conference on Image Analysis and Processing, p.105-110, September 10-14, 2007 [doi>10.1109/ICIAP.2007.79]
• 2: Giorgio Fumera , Ignazio Pillai , Fabio Roli, Spam Filtering Based On The Analysis Of Text Information Embedded Into Images, The Journal of Machine Learning Research, 7, p.2699-2720, 12/1/2006
• 3: Youn, S. and McLeod, D. Spam E-mail Classification using an Adaptive Ontology, Journal of Software (JSW), 2, 3 (2007), 43--55

INDEX TERMS

Primary Classification:
  H. Information Systems
  H.4 INFORMATION SYSTEMS APPLICATIONS
      H.4.3 Communications Applications
          Subjects: Electronic mail

Additional Classification:
  H. Information Systems
  H.3 INFORMATION STORAGE AND RETRIEVAL
      H.3.3 Information Search and Retrieval
          Subjects: Information filtering

General Terms:
Algorithms, Experimentation, Management, Performance

Keywords:
OCR, e-mail classification, feature selection, ontology, spam filtering