Utilizing Innovative Techniques to Improve Email Security

This paper proposes a technique to protect against email bombing. The technique employs a statistical approach, Naïve Bayes (NB), and Neural Networks to show that it is possible to differentiate between good and bad traffic to protect against email bombing attacks. Neural networks and Naïve Bayes can be trained by utilizing many email messages that include both input and output data for legitimate and non-legitimate emails. The input to the model includes the contents of the body of the messages, the subject, and the headers. This information will be used to determine if the email is normal or an attack email. Preliminary tests suggest that Naïve Bayes can be trained to produce an accurate response to confirm which email represents an attack.

Authors:

• Amany M. Alshawi
• Khaled Alduhaiman

Keywords:

• Email bombing
• Legitimate email
• Naïve Bayes
• Neural networks
• Non-legitimate email.

References:

[1] Carnegie Mellon University. The Computer Emergency Response Team.
(2002, March) Internet Denial of Service Attacks and the Federal
Response. http://www.cert.org
[2] Langley, P. 1992. Systematic and nonsystematic search strategies. In
Proceedings of the First International Conference on Artificial
Intelligence Planning Systems, pp. 145-152 College Park, Maryland.
Morgan Kaufmann.
[3] Lindberg, G. "Anti-Spam Recommend-ations for SMTP MTAs" Internet
RFC 2505, February 1999.
[4] M. Aery and S. Chakravarthy. eMailSift: Adapting Graph Mining
Techniques for Email Classification: Technical Report. University of
Texas at Arlington. 2004.
[5] J. Catlett. Megainduction: A test ┬░ight. International Conference on
Machine Learning, 1991.
[6] W. W. Cohen. Learning rules that classify e-mail. Proceedings of AAAI-
1996 Spring Symposium on Machine Learning in Information Access,
pp. 145- 155.
[7] J. Herman and C. Isbell. Ishmail: Immediate identification of important
information, AT&T labs. 1995.
[8] J. D. M.Rennie. Application of machine learning to e-mail filtering.
Proceedings of KDD-2000 Text Mining Workshop, Boston Aug, 2000.
[9] T. Payne and P. Edwards. Interface agents that learn: An investigation of
learning issues in a mail agent interface. Applied Artificial Intelligence,
pp 132-144. 1997.
[10] J. Rissanen. Stochastic complexity in statistical enquiry. World
Publishing Company, 1989.
[11] M. Sahami, D. Heckerman, and E. Horovitz. A Bayesian approach to
filtering junk e-mail. AAAI-98 Workshop on Learning for Text
Categorization, 1998.
[12] Androutsopoulos, G. Paliouras, V. Karkaletsis, G. Sakkis, C.D.
Spyropoulos and P. Stamatopoulos, "Learning to Filter Spam E-Mail: A
Comparison of a Naive Bayesian and a Memory-Based Approach". In H.
Zaragoza, P. Gallinari, and M. Rajman (Eds.), Proceedings of the
Workshop on Machine Learning and Textual Information Access, 4th
European Conference on Principles and Practice of Knowledge
Discovery in Databases (PKDD 2000), Lyon, France, pp. 1-13, 2000.