Identification of Profile-Injection Attacks in Recommendation System

  • C. Santhiya
  • K. IndiraEmail author
Conference paper
Part of the Lecture Notes on Data Engineering and Communications Technologies book series (LNDECT, volume 26)


The suggestion framework makes utilization of different separating calculations. They’re Collaborative, substance and cross breed separating procedures. Cooperative separating procedures are utilized to create modernized expectation roughly the enthusiasm of client to social affair a similar rating data. So it’s miles easily assaulted by utilizing “Shilling Attackers”. The assailants may likewise make the phony client profiles to infuse the database of rating framework, because of which a couple of wrong contraptions are prescribed to the individual. In this paper, we recreate the three sorts of shilling assaults like unsystematic, standard, temporary fad. The proposed administered calculation to distinguish the aggressor’s profile. The proposed measurable strategy score departure from denote concurrence (SDDC), level of correspondence (LOC) to unearth the assailant profile from authentic profile and also choose the real profile are named an aggressor profile. Shilling assaults decrease the exactness of the synergistic recommendation of this nature, given in the addresses, will be erased by our typesetters.


Collaborative separating Recommended framework Profile-infusion assault Shilling attacks 


  1. 1.
    Yang, Z., Cai, Z.: Detecting abnormal profiles in collaborative filtering recommender systems. J. Intell. Inf. Syst. 48(3), 499–518 (2017)CrossRefGoogle Scholar
  2. 2.
    Kumar, A., Rana, P.S.: Clustering approach to detect profile injection attacks in recommender system. Int. J. Comput. Appl. 166(6), 7–11 (2017)Google Scholar
  3. 3.
    Patel, K., Thakkar, A., Shah, C., Makvana, K.: A novel supervised approach to detection of shilling attack in collaborative filtering based recommendation system. Int. J. Comput. Sci. Inf. Secur. 14(4), 208–211 (2016)Google Scholar
  4. 4.
    Zhou, W., Wen, J., Xiong, Q., Gao, M., Zeng, J.: SVM-TIA a shilling attack detection method based on SVM and target item analysis in recommender systems. Neurocomputing 210, 197–205 (2016)CrossRefGoogle Scholar
  5. 5.
    Yang, Z., Cai, Z., Guan, X.: Estimating user behavior toward detecting anomalous ratings in rating systems. Knowl. Based Syst. 111, 144–158 (2016)CrossRefGoogle Scholar
  6. 6.
    Zhang, F., Yi, H., Sun, S.: Robust collaborative recommendation algorithm based on kernel function and Welsch reweighted M-estimator. IET Inf. Secur. 9(5), 257–265 (2015)CrossRefGoogle Scholar
  7. 7.
    Zhang, F., Zhou, Q.: HHT-SVM: an online method for detecting profile injection attacks in collaborative recommender systems. Knowl. Based Syst. 65, 96–105 (2014)CrossRefGoogle Scholar
  8. 8.
    Cao, J., Wu, Z., Mao, B., Zhang, Y.: Shilling attack detection utilizing semi-supervised learning method for collaborative recommender system. World Wide Web 16(5–6), 729–748 (2013)CrossRefGoogle Scholar
  9. 9.
    Chung, C.Y., Hsu, P.Y., Huang, S.H.: βp: a novel approach to filter out malicious rating profiles from recommender systems. Decis. Support Syst. 55(1), 314–325 (2013)CrossRefGoogle Scholar
  10. 10.
    Zhang, F., Zhou, Q.: A meta-learning-based approach for detecting profile injection attacks in collaborative recommender systems. J. Comput. 7(1), 226–234 (2012)Google Scholar
  11. 11.
    Ekstrand, M., Riedl, J., Konstan, J.: Collaborative filtering recommender systems. Found. Trends Hum. Comput. Interact. 4(2), 44–54 (2012)Google Scholar
  12. 12.
  13. 13.

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.Department of ITTCEMaduraiIndia

Personalised recommendations