A Multi-Layer Perceptron Model for Classification of E-mail Fraud
##plugins.themes.bootstrap3.article.main##
This study was developed an e-mail classification model to preempt fraudulent activities. The e-mail has such a predominant nature that makes it suitable for adoption by cyber-fraudsters. This research used a combination of two databases: CLAIR fraudulent and Spambase datasets for creating the training and testing dataset. The CLAIR dataset consists of raw e-mails from users’ inbox which were pre-processed into structured form using Natural Language Processing (NLP) techniques. This dataset was then consolidated with the Spambase dataset as a single dataset. The study deployed the Multi-Layer Perceptron (MLP) architecture which used a back-propagation algorithm for training the fraud detection model. The model was simulated using 70% and 80% for training while 30% and 20% of datasets were used for testing respectively. The results of the performance of the models were compared using a number of evaluation metrics. The study concluded that using the MLP, an effective model for fraud detection among e-mail dataset was proposed.
References
-
Behdad M, Barone L, Bennamoun M, French T. Nature-inspired techniques in the context of fraud detection. IEEE Transactions on Systems, Man and Cybernetics – Part C, Applications and Reviews. 2012; 42(6): 1273-1290.
Google Scholar
1
-
Tive C. 419 Scam, Exploits of the Nigerian Con Man: Bloomington, iUniverse; 2006.
Google Scholar
2
-
Reich P. Advance Fee Schemes in Country and Across Borders. Proceeding of Crime in Australia International Connections Conference organized by Australian Institute of Criminology; Melbourne, Australia; 2004.
Google Scholar
3
-
Australian Competition and Consumer Commission (ACCC). Upfront Payment and Advance Fee Frauds [Internet]. 2017. [cited on 2017 November 30]. Available from: https//www.scamwatch.gov.au /types-of-scams/unexpected-money/up-front-payment-advanced-fee-frauds on.
Google Scholar
4
-
Nizamani S, Memon N, Glasdam M, Nguyen DD. Detection of fraudulent emails by employing advance feature abundance. Egyptian Informatics Journal. 2014; 15: 169-174.
Google Scholar
5
-
Fraud MR. Detection using supervised machine learning algorithms. International Journal of Advanced Research in Computer and Communication Engineering. 2017; 6(6): 6-10.
Google Scholar
6
-
Carcillo F, Dal Pozzolo A, Le Borgne Y.-A, Caelen O, Mazzer Y, Bontempi G. SCARFF: a Scalable Framework for Streaming Credit Card Fraud Detection with Spark. [Internet]. 2017. [cited on 2017 September 23]. Available from: https://doi.org/10.1016/j.inffus.2017.09.005.
Google Scholar
7
-
Zhang H, Li D. Naïve Bayes Text Classifier. Proceedings of the IEEE International Conference of Computing. 2007; 708-713.
Google Scholar
8
-
Abu-Nimeh S, Nappa D, Wang X, Nair S. A Comparison of Machine Learning Techniques for Phishing Detection. Proceedings of Anti-Phishing Working Groups 2nd Annual e-Crime Researchers Summit. 2007; 60-69.
Google Scholar
9
-
Amor NB, Benferhat S, Elouedi Z. Naïve Bayes vs decision trees in intrusion detection systems. Proceedings of the 2004 ACM Symposium - Applied Computing. 2004; 420-424.
Google Scholar
10
-
Sculley D, Cormack G. Filtering email spam in the presence of noisy user feedback. Proceedings of the 5th Email Anti-Spam Conference, 2008; 1-10.
Google Scholar
11
-
Chandrasekaran M, Narayanan K, Upadhyaya S. Phishing E-Mail detection based on structural properties. Proceedings of the 1st Annual Symposium on Information Assurance, Intrusion Detection Prevention, 2006; 2-8.
Google Scholar
12
-
Kim DS, Nguyen H.-N, Park JS. Genetic algorithm to improve SVM based network intrusion detection system. Proceedings of the 19th Conference of Advanced Information and Network Applications 2, 2005; 155-158.
Google Scholar
13
-
Degang Y, Guo C, Hui W, Xiaofeng L. Learning vector quantization neural network method for network intrusion detection. University of Wuhan University Journal of Natural Sciences. 2007; 12(1), 147-150.
Google Scholar
14
-
Su M.-Y, Yeh S.-C, Chang, K.-C, Wei H.-F. Using incremental mining to generate fuzzy rules for real-time network intrusion detection systems. Proceedings of the 22nd International Advanced Information and Network Application Conference. 2008; 50-55.
Google Scholar
15
-
Rehak M, Pechoucek P, Celeda P, Krmicek V, Grill M, Bartos K. Multi-agent approach to network intrusion detection. Proceedings of the 7th International Joint Autonomous Agents and Multi-agent Systems Conference. 2008; 1695-1696.
Google Scholar
16
-
Srivastava A, Kundu A, Sural S, Majumdar A. Credit card fraud detection using hidden Markov model. IEEE Transactions on Dependable Secure Computers. 2008; 5(1): 37-48.
Google Scholar
17
-
Sanchez D, Vila M, Cerda L, Serrano J. Association rules applied to credit card fraud detection. Expert Systems Application. 2009; 36(2): 3630-3640.
Google Scholar
18
-
Panigrahi S, Kundu A, Sural S, Majumdar A. Credit card fraud detection, a fusion approach using Dempster–Shafer theory and Bayesian learning. Information Fusion. 2009; 10(4): 354-363.
Google Scholar
19
-
Bolton RJ, Hand DJ. Statistical fraud detection, A review. Statistical Science Journal. 2002;17(3): 235-249.
Google Scholar
20
-
Zavvar M, Razaei M, Garavand S. E-Mail spam detection using a combination of particle swarm optimization and artificial neural network and support vector machine. International Journal of Modern Education and Computer Science. 2016; 7: 68-74.
Google Scholar
21
-
Choudhary M, Dhaka A. Automatic e-mail classification using genetic algorithm. International Journal of Computer Science and Information Technologies. 2015; 6(6): 5097-5103.
Google Scholar
22
-
Bahnsen AC, Stojanovic A, Aouada D, Ottersten, B. Cost sensitive credit card fraud detection using bayes minimum risk. Proceedings of the 12th International Conference on Machine Learning and Applications. 2013; 333-338.
Google Scholar
23
-
Chaudhary K, Yadav J, Mallick B. A review of fraud detection techniques, credit card. International Journal of Computer Applications. 2012; 45(1): 39-44.
Google Scholar
24