Dynamic Classification Mining Techniques for Predicting Phishing URL

The online community faces the security challenge due to Phishing attack because many numbers of transactions are performed online to save time of users. It is a continual threat, and the risk of this attack is mostly on social networking sites such as Facebook, Twitter, LinkedIn, and Google+. In this paper, a dynamic approach based on minimum time to detect Phishing URL by using classification technique is described. This approach is based on different parameters such as high accuracy, Recall, Precision, Specification, and many more. The analysis result of these algorithms shows that Random tree is a good classification technique with comparison to others; it takes very less training build data time.

[1]  Harry Wechsler,et al.  Phishing detection using traffic behavior, spectral clustering, and random forests , 2013, 2013 IEEE International Conference on Intelligence and Security Informatics.

[2]  Dong Hyun Kim,et al.  Heuristic-based Approach for Phishing Site Detection Using URL Features , 2015 .

[3]  Narendra Shekokar,et al.  An Ideal Approach for Detection and Prevention of Phishing Attacks , 2015 .

[4]  Elijah Blessing Rajsingh,et al.  Intelligent phishing url detection using association rule mining , 2016, Human-centric Computing and Information Sciences.

[5]  M. S. Vijaya,et al.  Efficient prediction of phishing websites using supervised learning algorithms , 2012 .

[6]  Yuancheng Li,et al.  A minimum enclosing ball-based support vector machine approach for detection of phishing websites , 2016 .

[7]  Fadi A. Thabtah,et al.  Phishing detection based Associative Classification data mining , 2014, Expert Syst. Appl..

[8]  Mohammad Abdur Razzaque,et al.  A comprehensive review on privacy preserving data mining , 2015, SpringerPlus.

[9]  Kang-Leng Chiew,et al.  Phishing email detection technique by using hybrid features , 2015, 2015 9th International Conference on IT in Asia (CITA).

[10]  A. Kannan,et al.  Performance study of classification techniques for phishing URL detection , 2014, 2014 Sixth International Conference on Advanced Computing (ICoAC).

[11]  Rahul Patil,et al.  A hybrid model to detect phishing-sites using clustering and Bayesian approach , 2014, International Conference for Convergence for Technology-2014.