Machine Learning Based Prediction versus Human-as-a-Security-Sensor

(1) * Safwana Haque Mail (Department of Computing and Information Systems, Faculty of Architecture, Computing and Humanities, University of Greenwich, United Kingdom)
*corresponding author


Phishing is one of the most common cyber threats in the world today. It is a type of social engineering attack where the attacker lures unsuspecting victims into carrying out certain tasks mostly to steal personal and sensitive information. These stolen information are exploited to commit further crimes e.g. blackmails, data theft, financial theft, malware installation etc. This study was carried out to tackle this problem by designing an anti-phishing learning algorithm to detect phishing emails and also to study the accuracies of human phishing prediction to machine prediction. A graphical user interface was designed to emulate an email-client system that popped-up a warning on detecting a phishing mail successfully and collection of predictions made by expert and non-expert users on anti-phishing techniques. These predictions were compared to the predictions made by the machine learning algorithm to compare the efficiencies of all predictions considered in this research. The performance of the classifier used was measured with metrics such as confusion matrix, accuracy, receiver operating characteristic curve and area under graph


Phishing Feature extraction Machine learning Prediction Classifiers Logistic regression;



Article metrics

10.29099/ijair.v3i1.83 Abstract views : 1051 | PDF views : 159




Full Text



Rekouche, K. Early Phishing, arXiv: 1106.4692, 2011.

Kris, S. The Battle Against Identity Theft. Banker 2003, 153, 931.

Eisenstein, E.M. Identity theft: An exploratory study with implications for marketers. Journal of Business Research 2008, 61, 1160–1172.

Sullins, L.L. Phishing for a Solution: Domestic and International Approaches toDecreasing Online Identity Theft. Emory International Law Review 2006, 20, 397.

Group, A.P. Phishing activity trends report, Anti Phishing WorkGroup, 1st Quarter, [online] Available at, 2016.

Jung, J.S.; E.. An Empirical Study of Spam Traffic and the Use of DNSBlack Lists. (Accessed 2004, 18, 370–375.

Felegyhazi, M.; Kreibich, C.P.; V.. On the Potential of Proactive. Domain Blacklisting., LEET 2010, 10, 6–6.

Prakash, P.; Kumar, M.; Kompella, R.G.; M.. PhishNet: Predictive Blacklisting to. 2010, pp. 1–5.

Dong, X.; Clark, J.J.; L, J. Defending the weakest link: phishing websites detection by analysing user behaviours. Telecommunication Systems 2010, 45, 215–226.

Ramzan, Z. Phishing and Two-Factor Authentication Revisited, Symantec SecurityResponse, [online] Available, 2007.

Nilsson, M.; Adams, A.H.; S..Building Security and Trust in OnlineBanking, In CHI ’05 Extended Abstracts on; ACM: New York, NY, USA, 2005.1701–1704, [online] Available at: (Accessed 17.

Molloy, I.L.; N.. Attack on the GridCode One-time Password; ACM: New York, NY, USA, 2011; pp. 306–315. online] Available at: (Accessed 17.

Zviran, M.; Erlich.; Zippy. Identification and Authentication: Technology and Implementation Issues, Communications of the Association for Information Systems 2006, 17.

Van Oorschot Mannan, M.; P.C.. Using a personal device tostrengthen password authentication from an untrusted computer; 2007; pp. 88–103. SpringerBerlin Heidelberg.

Lu, H.P.; Lu, H.P.; Hsu, C.L.; Hsu, H.Y. An empirical study of the effect of perceived risk upon intention to use online applications. Information Management & Computer Security 2005, 13, 106–120.

Plössl, K.; Federrath, H.; Nowey, T. Protection Mechanisms Against Phishing Attacks. Trust, Privacy, andSecurity in Digital Business, Lecture Notes in Computer Science, Springer Berlin Heidelberg

DodgeJr., R.C.; Carver, C.F.; J, A. Phishing for user securityawareness. Computers & Security 2007, 26, 73–80.

Kumaraguru, P.; Rhee, Y.; Sheng, S.; Hasan, S.; Acquisti, A.; Cranor, L.H. J.(2007) Getting Users to Pay Attention to Anti-phishing Education: Evaluation ofRetention and Transfer; ACM: New York, NY, USA, 2016; pp. 70–81.

Robila, S.R.; W, J. Don’T Be a Phish: Steps in User Education; ACM: New York, NY, USA, 2006; pp. 237–241. Accessed 17 September 2016.

Vishwanath, A.; Herath, T.; Chen, R.; Wang, J.R.; R, H. Why do people getphished? Testing individual differences in phishing vulnerability within anintegrated, information processing model. Decision Support Systems 2011, 51, 576–586.

Del Castillo, M.D.; Iglesias, A.S.; I, J. Detecting Phishing E-mails by Heterogeneous Classification. Intelligent Data Engineering and Automated Learning IDEAL2007, Lecture Notes in Computer Science, Springer Berlin Heidelberg .

Chandrasekaran, M.; Narayanan, K.U.; Phishing email detection based onstructural properties; 2006; pp. 1–7.

Fette, I.; Sadeh, N.T.; A.. Learning to Detect Phishing Emails, InProceedings of the 16th International Conference on World Wide Web, WWW ’07,New. (Accessed 2007, 18, 649–656.

He, M.; Horng, S.J.; Fan, P.; Khan, M.K.; Run, R.S.; Lai, J.L.; andSutanto Chen, R.J.; A.. An efficient phishing webpage detector. Expert Systems withApplications 2011, 38, 12018–12027.

Bergholz, A.; Beer, J.D.; Glahn, S.; Moens, M.F.; Paaß, G.S.; S.. Newfiltering approaches for phishing email. Journal of Computer Security 2010, 18, 7–35.

Abu-Nimeh, S.; Nappa, D.; Wang, X.N.; S.. A Comparison of Machine LearningTechniques for Phishing Detection; Available: New York, NY, USA, ACM,pp. 60–69, [online, 2007].

Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.


The International Journal of Artificial Intelligence Research

Organized by: Departemen Teknik Informatika
Published by: STMIK Dharma Wacana
Jl. Kenanga No.03 Mulyojati 16C Metro Barat Kota Metro Lampung
phone. +62725-7850671
Fax. +62725-7850671


View IJAIR Statcounter

Creative Commons License
This work is licensed under  Creative Commons Attribution-ShareAlike 4.0 International License.