Mining Frequent pattern is a common technique of data mining and used as a preliminary step to mine association rules. Some frequent patterns are sensitive as they may disclose confidential information to adversaries and needs to be hidden in the data before sharing. Many of the existing techniques hide sensitive itemsets at a single sensitive support threshold. Also, these techniques generate various side effects and suffer from unexpected information loss. In this paper, a novel approach to hide sensitive itemsets at multiple sensitive support thresholds is proposed. The database is modeled as a set of closed itemsets which are selectively sanitized to hide sensitive itemsets. The proposed Recursive Pattern Sanitization algorithm for Personalized Itemsets Hiding (RPS-PIH) sanitizes the closed itemsets to hide sensitive itemsets at multiple sensitive support thresholds without generating any side effects. The sanitized model represents privacy preserved patterns of the database which may be shared to the third party for further data analysis without disclosing private information. Experimental results indicate that the proposed approach is efficient in hiding sensitive itemsets at multiple sensitive support thresholds. The effectiveness of the proposed approach is measured using popular metrics for side effects and information loss. The proposed approach is effective in reducing information loss and eliminating the generation of side effects compared with existing state-of-the-art techniques.

Itemset Hiding, Multiple Support Threshold, Privacy Preserved Data Publishing (PPDP), Personalized Privacy Preservation, Pattern Sharing, Pattern Sanitization, Sensitive Knowledge

[1] Clifton C, Marks D, “Security and privacy implications of data mining”. In Proceedings of the 1996 ACM SIGMOD International Conference on Management of Data, pp 15-19, 1996.
[2] Clifton C, Kantarcioglu M, Vaidya J, “Defining privacy for data mining”. National Science Foundation Workshop on Next Generation Data Mining (WNGDM), pp 126-133, 2002.
[3] Agrawal R and Srikant R, "Privacy-preserving data mining".In Proceedings of the ACM SIGMOD, ACM: 439-450, 2000.
[4] S. Sathyamoorthy, "Data Mining and Information Security in Big Data", International Journal of Scientific Research in Computer Science and Engineering, Vol.5, Issue.3, pp.86-91, 2017.
[5] G. Pannu, S. Verma, U. Arora, and A. K. Singh, "Comparison of various Anonymization Technique", International Journal of Scientific Research in Network Security and Communication, Vol.5, Issue.6, pp.16-20, 2017
[6] Agrawal R, Srikant R, "Fast algorithms for mining association rules in large databases". In Proceedings of the20th International Conference on Very Large Databases, pp. 487-499, 1994.
[7] Bodon F, “A fast APRIORI implementation”. Workshop Frequent Itemset Mining Implementations (FIMI03), vol.90, pp. 56-65, 2003.
[8] Brijs, T., Swinnen, G., Vanhoof, K., Wets, G., “Using association rules for product assortment decisions: a case study”. In Knowledge Discovery and Data Mining, pp.254-260, 1999.
[9] Zheng Z, Kohavi R, Mason L, “Real world performance of association rule algorithm”. In Proceedings of 7thACM-SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 401-406, 2001.
[10] Atallah M, Bertino E, Elmagarmid A, Ibrahim M, Verykios VS, “Disclosure limitation of sensitive rules”. In Workshop on Knowledge and Data Engineering Exchange, pp. 45-52, 1999.
[11] Pontikakis E D, Tsitsonis A A, Verykios V S, “An experimental study of distortion-based techniques for association rule hiding”. In Proceedings of the 18th Conference on Database Security (DBSEC 2004), pp. 325-339, 2004.
[12] Dasseni E, Verykios V, Elmagarmid A, Bertino E, “Hiding association rules by using confidence and support”. In Proceedings of the 4th International Workshop on Information Hiding, IHW, pp. 369-383, 2001.
[13] Oliveira S R M, Zaiane O R, "Privacy-preserving frequent itemset mining". In Proceedings of the IEEE International Conference on Privacy, Security and Data Mining, CRPIT, pp. 43-54, 2002.
[14] Oliveira S R M, Zaiane O R, “Protecting sensitive knowledge by data sanitization”. In Proceedings of the Third IEEE International Conference on Data Mining (ICDM2003), pp. 211-218, 2003.
[15] Verykios V S, Emagarmid A K, Bertino E, Saygin Y, Dasseni E, “Association rule hiding”. IEEE Transactions on Knowledge and Data Engineering, 16(4), pp. 434-447, 2004.
[16] Wu Y H, Chiang C M, Chen A L P, “Hiding sensitive association rules with limited side effects”. IEEE Transactions on Knowledge and Data Engineering, 19(1), pp.29-42, 2007.
[17] Aniket Patel, Patel Shreya, Kiran Amin, "A Survey on Heuristic Based Approach for Privacy Preserving in Data Mining", International Journal of Scientific Research in Computer Science and Engineering, Vol.5, Issue.5, pp.21-25, 2017.
[18] Mohnish Patel, Aasif Hasan and Sushil Kumar, "A Survey: Preventing Discovering Association Rules For Large Data Base", International Journal of Scientific Research in Computer Science and Engineering, Vol.1, Issue.3, pp.35-38, 2013
[19] Moustakides G V, Verykios V S, “A max-min approach for hiding frequent itemsets”. In Proceedings of the 6th IEEE International Conference on Data Mining (ICDM 2006), pp. 502-506, 2006.
[20] Leloglu E, Ayav T, Ergenc B, “Coefficient-based exact approach for frequent itemset hiding”. In eKNOW2014: The 6th international conference on information, process, and knowledge management, pp. 124-130, 2014.
[21] Sun X, Yu PS, “A border-based approach for hiding sensitive frequent itemsets”. In Proceedings of the Fifth IEEE International Conference on Data Mining (ICDM2005), pp. 426-433.
[22] Sun X, Yu PS, “Hiding sensitive frequent itemsets by a border-based approach”. Computing Science and Eng.,1(1), pp. 74-94, 2007.
[23] Gkoulalas-Divanis A and Verykios VS, “An integer programming approach for frequent itemset hiding”. In Proceedings of the 15th ACM International Conference on Information and Knowledge Management, CIKM, pp.748-757, 2006.
[24] Menon S, Sarkar S, Mukherjee S, “Maximizing accuracy of shared databases when concealing sensitive patterns”. Info. Sys. Research 16, 3, pp. 256-270, 2005.
[25] Kantarcioglu M, Jin J, Clifton C, “When do data mining results violate privacy?” In Proceedings of the 10th ACMSIGKDD international conference on knowledge discovery and data mining (KDD04), pp. 599-604, 2004.
[26] Elias C. Stavropoulos, Vassilios S. Verykios, and Vasileios Kagklis. “A transversal hyper-graph approach for the frequent itemset hiding problem.” Knowledge and Information Systems 47, 3, pp. 625-645, 2016.
[27] Akbar Telikani and Asadollah Shahbahrami. “Optimizing association rule hiding using combination of border and heuristic approaches”. Applied Intelligence 47, 2, pp. 544-557, 2017.
[28] Surendra H and Mohan H S, “Hiding sensitive itemsets without side effects”. Applied Intelligence.10.1007/s10489-018-1329-5, 2018.
[29] Gkoulalas-Divanis A, Verykios VS, “Hiding sensitive knowledge without side effects”. Knowledge and Information Systems20(3), pp. 263-299, 2009.
[30] Ahmet Cumhur ztrk and Belgin Ergen Bostanolu, “Itemset Hiding under Multiple Sensitive Support Thresholds”. In Proceedings of 9th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management (IC3K 2017) – vol 3: KMIS, pp, 222-231, 2017.
[31] Ztrk, Ahmet Cumhur, Belgin Ergen, “Dynamic Itemset Hiding Algorithm for Multiple Sensitive Support Thresholds”.IJDWM 14.2, pp 37-59, 2018.
[32] Mohammed J. Zaki and Ching-Jui Hsiao, “CHARM: An efficient algorithm for closed itemset mining”. In Proceedings of International Conference on Data Mining, pp. 457-473, 2002.
[33] Bayardo R, “Efficiently mining long patterns from databases”. In Proceedings of the 1998 ACM-SIGMOD International Conference on Management of Data (SIGMOD98), pp 85-93, 1998.
[34] Bertino E, Lin D, Jiang W, “A Survey of Quantification of Privacy Preserving Data Mining Algorithms”. In Aggarwal C.C., Yu P.S. (eds) Privacy-Preserving Data Mining. Advances in Database Systems, vol 34. Springer, Boston, MA, 2008.