Comparative Evaluation for High Intelligent Performance Adaptive Model for Spam Phishing Detection

A.A. Ojugo^1, and A.O. Eboka²

¹Department of Mathematics/Computer Science, Federal University of Petroleum Resources Effurun, Delta State, Nigeria

²Department of Computer Science Education, Federal College of Education Technical, Asaba, Delta State, Nigeria

Cite this paper:
A.A. Ojugo and A.O. Eboka. Comparative Evaluation for High Intelligent Performance Adaptive Model for Spam Phishing Detection. Digital Technologies. 2018; 3(1):9-15. doi: 10.12691/dt-3-1-2

Abstract

Modern day technology, daily seeks to better data processing activities through features such as improved speed, better functionality, higher mobility, portability and improved data access – all of which is extended via smart computing. The widespread use of smartphone has led to an exponential growth in the volumes of emails, alongside great success in phishing attacks carried out more effective via spam inbox mails to unsuspecting users – soliciting for funds. Many mail apps today, offers automatic filters as a set of rules to help better organize and dispose (as spam, if necessary) incoming mails based through the checking of certain keywords detected in a message’s header or body. Achieving such programming filter feature is quite mundane and also inefficient, as spams often evade such filters, slipping into inbox again and again. The study seeks to provide an intelligent adaptive mail support that learns user’s preference via an evolutionary unsupervised model(s) as a computational alternative that adapts the data locality feat as well as compares convergence results yielded by the unsupervised hybrid classifiers. It achieves such feats by building local decision heuristics into their classification processes so that such spam filter(s) are embedded with a design that allows for email genres.

Keywords:
evolutionary models spams filters SVM PHMM Neural network classifiers

This work is licensed under a Creative Commons Attribution 4.0 International License. To view a copy of this license, visit http://creativecommons.org/licenses/by/4.0/

References:

[1]	Androutsopoulos, I., Koutsias, J., Konstantinos V and Constantine, D., (2005). An experimental comparison of naïve bayesian and keyword-based anti-spam filtering with personal e-mail messages, Proc. of 23rd annual ACM SIGIR Conf. on research and development in information retrieval, SIGIR’00, pp. 160-167.
[2]	SPAMHAUS (2005). The definition of spam. Available online at http://www.spamhaus.org/definition.html.
[3]	Cormack, G., and Lynam, T. (2005). Spam corpus creation for TREC. In Proceedings of Second Conference on Email and Anti-Spam, CEAS’2005. http://ceas.cc/2005/.
[4]	Spam Defined. (2001). Spam defined, Online: www.monkeys.com/spamdefined.html.
[5]	Lorenzo, L., Mari, M. and Poggi, A. (2005). Cafe – collaborative agents for filtering e-mails. In Proceedings of 14th IEEE International Workshops on Enabling Technologies: Infrastructure for Collaborative Enterprise, WETICE’05, pages 356-361.
[6]	Delany, S., Padraig, C., Alexey, T and Lorcan, C., (2004). A case-based technique for tracking concept drift in spam filtering, Knowledge-based systems, pp 187-195.
[7]	MAAWG (2006). Messaging anti-abuse working group, Email metrics report for third & fourth quarter 2006, Online at: www.maawg.org/about/MAAWGMetric200634report.pdf.
[8]	Mikko, S and Carl, S., (2006). Effective anti-spam strategies in companies: An international study, Proc. of HICSS ’06, Vol. 6
[9]	Daniel, L and Christopher, M., (2005). Good word attacks on statistical spam filters, Proc. of Second Conference on Email and Anti-Spam, CEAS’2005.
[10]	Ferris Research (2015). The global economic impact of spam, report #409. http://www.ferris.com/get content file.php?id=364.
[11]	Christine, D., Oliver, J. and Koontz, E. (2004). Anatomy of a phishing email. In Proceedings of the First Conference on Email and Anti-Spam, CEAS’2004
[12]	Ojugo, A.A and Eboka, A.O., (2014). An intelligent hunting profile for evolvable metamorphic malware, African Journal of Computing and ICT, Vol. 8, No. 1, Issue 2, pp 181-190.
[13]	Longe, O.B., Robert, A.B.C., Chiemeke, S.C and Ojo. F.O., (2008). Feature Outliers And Their Effects On The Efficiencies Of Text Classifiers In The Domain Of Electronic Mail, The Journal of Computer Science and Its Applications, 15(2).
[14]	Wittel, G. and Wu, F. (2004). On attacking statistical spam filters. In Proceedings of First Conference on Email and Anti-Spam, CEAS’2004.
[15]	Agarwal, R., Aggarwal, C and Prasad, V., (2001). A tree projection algorithm for generation of frequent itemsets, Journal of Parallel and Distributed Computing, pp350-371.
[16]	Cukier W., Cody, S and Nesselroth, E. (2006). Genres of spam: Expectations and deceptions, Proc. of the 39th Annual Hawaii International Conference on System Sciences, Vol. 3. www.computer.org/csdl/proceedings/hicss/2006/2507/03/250730051a.pdf.
[17]	Ojugo, A.A., (2015). A comparative stochastic model solution on convergence problem of quadratic functions, Unpublished Thesis, Mathematics and Computer Science Department, Federal University of Petroleum Resources Effurun.
[18]	Ojugo, A.A., Allenotor, D and Eboka, A.O., (2016). Solving for convergence solution and properties of quadratic function: A case of selected intelligent supervised models, FUPRE Technical Report (TRON-119), pp 34-42.
[19]	Chaovalitwongse, W., (2007). On time series k-nearest neighbor classification of abnormal brain activity, IEEE Transactions on Systems, Man, and Cybernetics – Part A: Systems and Humans, Vol. 37.
[20]	Fix, E. and Hodges, J., “Discriminatory analysis -Nonparametric discrimination: Consistency properties”, Project No. 2-49-004, Report No. 4, Contract No. AF 41(128)-31, USAF School of Aviation, Randolph Field, Texas, 1951.
[21]	Viaene, S., Derrig, R., Baesens, B., and Dadene, G., (2002). A comparison of state‐of‐the art classification techniques for expert automobile insurance claim fraud detection, The Journal of Risk and Insurance, Vol. 69, pp. 373-421.
[22]	Yildiz, T., Yildirim, S., Altilar, D., (2008). Spam filtering with parallelized KNN algorithm, Akademik Bilisim.
[23]	Enas, G. and Choi, S., (1986). Choice of the smoothing parameter and efficiency of k-nearest neighbor, Computers and Mathematics with Applications, Vol. 12, pp. 235-244.
[24]	Berrueta, L., Alonso-Salces, R., Heberger, K., “Supervised pattern recognition in food analysis”, Journal of Chromatography A, 1158, pp. 196-214, 2007.
[25]	Okesola, J.O., Ojo., F.O., Adigun, A.A and Longe, O.B., (2015). Adaptive high probability algorithms for filtering advance fee fraud emails using the concept of data locality, Computing, Information Systems, Development Informatics and Allied Research Journal, Vol. 6, No. 1, pp 7-12.
[26]	Hulten, G., Penta, A., Gopalakrishnan, S. and Manav, M. (2004). Trends in spam products and method, Proceedings of the 1st Conf. on Email and Anti-Spam, CEAS’2004, 2004.
[27]	Lai, C. and Tsai, M. (2004). An empirical performance comparison of machine learning methods for spam e-mail categorization. Hybrid Intelligent Systems, pages 44-48, 2004.
[28]	Ojugo, A.A., Allenotor, D., Oyemade, D.A., Longe, O.B and Anujeonye, C.N., (2015). Comparative stochastic study for credit-card fraud detection models, African Journal of Computing & ICTs. Vol. 8, No. 1, Issue 1. Pp 15-24.
[29]	Ojugo, A.A., J. Emudianughe., R. Yoro., E. Okonta., A. Eboka., (2013). A hybrid neural network gravitational search algorithm for rainfall runoff modeling and simulation in hydrology, Progress in Intelligence Computing and Applications, 2(1): 22-33.
[30]	Dawson, C and Wilby, R., (2001). Comparison of neural networks in river flow forecasting, J. of Hydrology and Earth Science, SRef-ID: 1607-7938/hess/2001-3-529.
[31]	Ojugo, A.A., Ben-Iwhiwhu, E., Kekeje. O., Yerokun, M., Iyawah, I.J.B., (2014). Malware propagation on social time varying networks: a comparative study of machine learning frameworks, International Journal of Modern Education Computer Science, 6(8): pp25-33.
[32]	Barakat, N.H., Bradley, A.P and Barakat, M.N., (2010). Intelligible support vector machines for diagnosis of diabetes mellitus, IEEE Transactions on Information Technology in Biomedicine, 14(4), pp1114-1120.
[33]	Khan, J., Zahoor, R and Qureshi, I.R., (2009). Swarm intelligence for problem of non-linear ordinary differential equations and its application to Wessinger equation, European Journal of Science Research, 34(4), pp. 514-525.
[34]	Khashei, M., Eftekhari, S and Parvizian, J (2012). Diagnosing diabetes type-II using a soft intelligent binary classifier model, Review of Bioinformatics and Biometrics, 1(1), pp 9-23.
[35]	Ojugo, A.A., Eboka., A., E Okonta., R. Yoro., F. Aghware., (2012). Genetic algorithm rule-based intrusion detection system (GAIDS), Journal of Emerging Trends in Computing Information System, 3(8): pp1182-1194.
[36]	Andrew Farrugia (2004). Investigation of Support Vector Machines for Email Classification. Dissertation submitted to the School of Computer Science and Software Engineering Monash University.
[37]	Blanzieri, E and Bryl, A., (2007). Highest Probability SVM Nearest Neighbor Classifier For Spam Filtering, March 2007 Technical Report DIT-07-007, retrieved on January 2017.
[38]	Zhou, F., Zhuang, L., Zhao, B. Huang, L., Joseph, A. and Kubiatowicz, J. (2003). Approximate object location and spam filtering on peer-to-peer systems. In Proceedings of ACM/IFIP/USENIX International Middleware Conference, Middleware.