METHOD OF IDENTIFICATION BOT PROFILES BASED ON NEURAL NETWORKS IN RECOMMENDATION SYSTEMS

Article Sidebar

PDF
DOI: https://doi.org/10.20998/2522-9052.2020.2.05
Keywords:
recommendation systems, information attacks, information security, Internet bots, neural networks, data clustering

Main Article Content

Yelyzaveta Meleshko
Central Ukrainian National Technical University, Kropyvnytskyi
https://orcid.org/0000-0001-8791-0063
Oleksandr Drieiev
Central Ukrainian National Technical University, Kropyvnytskyi
https://orcid.org/0000-0001-6951-2002
Hanna Drieieva
Central Ukrainian National Technical University, Kropyvnytskyi
https://orcid.org/0000-0002-8557-3443

Abstract

The subject matter of the article is the process of increased the information security of recommendation systems. The goal of this work is to develop a method of identification bot profiles in recommendation systems. In this work, the basic models of information attacks by the profile-injection method on recommendation systems were researched, the method of identification bot profiles in recommendation systems using the multilayer feedforward neural network was developed and the experiments to test the quality of its work were conducted. The developed method is to identify bot profiles that attempt to change item ratings in a recommendation system in order to increase the occurrence frequency of target items in recommendation lists to all authentic users, or to certain segments of authentic users. When removing bot profiles' data from the database of the recommendation system before generating recommendation lists, the accuracy of the system and the correctness of recommendations are significantly increased, and authentic users get protection from information attacks. Random, Average and Popular attacks were used to model the attacks on a recommendation system. To identify bots, their ratings for system items were analyzed. The experiments have shown that the neural network that analyzes only the numbers of different ratings in a profile, detects bot profiles with high accuracy, that use Random attack regardless of the number of target items for each bot. At the same time, the developed neural network can detect bots that use Average or Popular attacks only when they have several target items. Also, the results of the experiments show that type I errors, when the system identifies authentic users as bots, is very rarely appear in the developed method. To improve the accuracy of the neural network, there can add to analysis also other data of user profiles, such as the timestamp of each rating and as segments of items, which was rated.

Article Details

How to Cite
Meleshko, Y., Drieiev, O., & Drieieva, H. (2020). METHOD OF IDENTIFICATION BOT PROFILES BASED ON NEURAL NETWORKS IN RECOMMENDATION SYSTEMS. Advanced Information Systems, 4(2), 24–28. https://doi.org/10.20998/2522-9052.2020.2.05
Issue
Vol. 4 No. 2 (2020): Advanced Information Systems
Section
Identification problems in information systems
Author Biographies

Yelyzaveta Meleshko, Central Ukrainian National Technical University, Kropyvnytskyi

Candidate of Technical Sciences, Associate Professor, Doctoral Student of Cybersecurity and Software Department

Oleksandr Drieiev, Central Ukrainian National Technical University, Kropyvnytskyi

Candidate of Technical Sciences, Associate Professor of Cybersecurity and Software Department

Hanna Drieieva, Central Ukrainian National Technical University, Kropyvnytskyi

Graduate student of Cybersecurity and Software Department

References

(2010), Recommender Systems Handbook, Editors Francesco Ricci, Lior Rokach, Bracha Shapira, Paul B. Kantor, 1st edition, Springer-Verlag New York Inc., New York, USA, 842 p.

Lam, S.K.,and Riedl, J. (2004), “Shilling recommender systems for fun and profit”, Proceedings of the 13th International World Wide Web Conference, pp. 393–402.

O’Mahony, M.P., Hurley, N.J. and Silvestre, G.C.M. (2002), “Promoting recommendations: An attack on collaborative filtering”, Database and Expert Systems Applications: 13th International Conference, DEXA Aix-en-Provence, France, pp. 494-503.

Williams, C., Mobasher, B. and Burke, R. (2007), “Defending recommender systems: detection of profile injection attacks”, Service Oriented Computing and Applications, pp. 157–170.

Chirita, P.A., Nejdl, W. and Zamfir C. (2005), “Preventing shilling attacks in online recommender systems”, Proceedings of the ACM Workshop on Web Information and Data Management, pp. 67–74.

Zhou W., Wen J., Qu Q., Zeng J. and Cheng T. (2018), “Shilling attack detection for recommender systems based on credibility of group users and rating time series”, PLoS ONE 13(5): e0196533, DOI: https://doi.org/10.1371/journal.pone.0196533

Kumari, T. and Punam, B.A (2017), “Comprehensive Study of Shilling Attacks in Recommender Systems”, IJCSI International Journal of Computer Science Issues, Volume 14, Issue 4, URL: https://www.ijcsi.org/papers/IJCSI-14-4-44-50.pdf

Mobasher, B., Burke, R., Bhaumik, R. and Williams C. (2007), “Toward trustworthy recommender systems: An analysis of attack models and algorithm robustness”, ACM Transactions on Internet Technology, Vol. 7(4), pp. 1–41.

Mobasher, B., Burke, R., Bhaumik R. and Williams C. (2005). “Effective attack models for shilling item-based collaborative filtering system”, Proceedings of the WebKDD Workshop, pp. 1–8.

Harper, F.M. and Konstan J.A. (2016), “The MovieLens Datasets: History and Context”, ACM Transactions on Interactive Intelligent Systems (TiiS), available at: https://doi.org/10.1145/2827872

(2020), TensorFlow tutorials, URL: https://www.tensorflow.org/tutorials/

(2017), “The gentle introduction to Adam optimization algorithm for deep learning”, Blog about Machine Learning, Neural Networks, Artificial Intelligence, URL: https://www.machinelearningmastery.ru/adam-optimization-algorithm-for-deep-learning (in Russian).