This is the era of high end technologies which requires faster connectivity through internet and its variety of applications with prime concern of serving ease in transition, convey messages and data from one end of the world to another. These methods are consuming various sensitive information for their own record. Loose design formation and lower coupling with security approaches of web applications are waved of by attackers to get the system access from malicious activities which create the trouble in real life situations. The primary aim of this presented work is to study about various phishing techniques and their effects on our daily life additionally finding some acceptable and/ or adoptable detection and prevention techniques by which system automatically detects a phishing web URL uses data mining techniques. Along with the studying the work had also identified the problems associated with the current detection. As far as older systems are concerned detection are having larger ratio of false positive nature served with static patterns and rules. This work proposes a hybrid anti-phishing approach using some of the well-known phishing detection factors like MAC address of web pages. This works also elaborates the comparative study of most implemented recommendations algorithms to proposed Hybrid recommendations approach.

Blacklisting Recommendation System, Content Based, Collaborative Based, Knowledge Based System, Phishing, Pattern Analysis, MAC, Pattern Similarity Index (PSI)

[1] Artus Krohn-Grimberghe, Alexandros Nanopoulos, Lars Schmidt-Thieme, “A Novel Multidimensional Framework for Evaluating Recommender Systems” Barcelona, Spain, Sep 30, 2010. pp.34-51.
[2] Fabio Soldo, Anh Le, Athina Markopoulou “Blacklisting Recommendation System: Using Spatio-Temporal Patterns to Predict Future Attacks,” IEEE Journal on selected areas in communication vol.29,no.7 Aug 2011.pp.1423-1437.
[3] J. Zhang, P. Porras, and J. Ullrich, “Highly predictive blacklisting,” in USENIX Security, San Jose, CA, USA, Jul. 2008.pp.16-32.
[4] Yehuda Koren, “Collaborative Filtering with Temporal Dynamics,” in KDD’09, June 28–July 1, 2009, Paris, France.
[5] Andreas Töscher, Michael Jahrer, and Robert Legenstein “Improved Neighborhood-Based Algorithms for Large-Scale Recommender Systems,” in 2nd Netflix-KDD Workshop, August 24, 2008, Las Vegas, NV, USA.
[6] A. Ramachandran, N. Feamster, and S. Vempala, “Filtering spam with behavioral blacklisting,” in ACM CCS, Alexandria, VA, Oct 2007.
[7] Zan Huang , Daniel Zeng and Hsinchun Chen, “A Comparative Study of Recommendation Algorithms in Ecommerce Applications,” in Proc. of ACM KDD ’04, Seattle, WA, USA, Aug. 2004, pp. 79–88.
[8] F. Soldo, A. Le, and A. Markopoulou, “Predictive Blacklisting as an Implicit Recommendation System,” in IEEE INFOCOM, San Diego, CA, USA, Mar. 2010.pp.1-11.