ICTACT Journal on Soft Computing

Open Access Open Access  Restricted Access Subscription Access
Open Access Open Access Open Access  Restricted Access Restricted Access Subscription Access

Privacy Preserving Data Mining using Threshold Based Fuzzy C-Means Clustering


Affiliations
1 Department of Information Technology, Lebanese French University, Erbil, Iraq
     

   Subscribe/Renew Journal


Privacy preserving is critical in the field of where data mining is transformed into cooperative task among individuals. In data mining, clustering algorithms are most skilled and frequently used frameworks. In this paper, we propose a privacy-preserving threshold clustering that uses code based technique with threshold estimation for sharing of secret data in privacy-preserving mechanism. The process includes code based methodology which enables the information to be partitioned into numerous shares and handled independently at various servers. The proposed method takes less number of iterations in comparison with existing methods that does not require any trust among the clients or servers. The paper additionally provides experimental results on security and computational efficiency of proposed method.

Keywords

Privacy Preserving, Data Mining, Threshold Cryptography, Fuzzy C-Means Clustering, Vandermonde Matrix, Secure Multiparty Computation.
Subscription Login to verify subscription
User
Notifications
Font Size

  • R. Agrawal and R. Srikant, “Privacy Preserving Data Mining. ACM SIGMOD”, Proceedings of International Conference on Management of Data, pp. 439-450, 2000.

  • Y. Lindell and Pinkas, “Privacy Preserving Data Mining”, Journal of Cryptology, Vol. 15, No. 3, pp. 177-183, 2002.

  • A. Shamir, “How to Share a Secret”, Communications of the ACM, 1979.

  • M. Mignotte. “How to Share a Secret”, Proceedings of Workshop on Cryptography, pp. 371-375, 1983.

  • Josef Pieprzyk and Xian-Mo Zhang, “Ideal Threshold Schemes from MDS Codes”, Proceedings of International Conference on Information Security and Cryptology, pp. 253-263, 2003.

  • B. Pinkas, “Cryptographic Techniques for Privacy-Preserving Data Mining”, Available at: http://www.pinkas.net/PAPERS/sigkdd.pdf.

  • S. Verykios et al., “State of the-Art in Privacy Preserving Data Mining”, ACM SIGMOD Record, Vol. 33, No. 1, pp. 50-57, 2004.

  • V Baby and Subhash N Chandra, “Privacy-Preserving Distributed Data Mining Techniques: A Survey”, International Journal of Computer Applications, Vol. 143, No. 10, pp. 37-41, 2016.

  • J. Brickell and V. Shmatikov, “Privacy-Preserving Classifier Learning”, Proceedings of 13th International Conference on Financial Cryptography and Data Security, pp. 1-6, 2009.

  • G. Jagannathan and R.N. Wright, “Privacy-Preserving Distributed k-Means Clustering over Arbitrarily Partitioned Data”, Proceedings of 11th ACM SIGKDD International Conference on Knowledge Discovery in Data Mining, pp. 593-599, 2005.

  • P. Bunn and R. Ostrovsky, “Secure Two-Party K-Means Clustering”, Proceedings of ACM International Conference on Computer and Communications Security, pp. 486-497, 2007.

  • M. Upmanyu, A.M. Namboodiri, K. Srinathan and C.V. Jawahar, “Efficient Privacy Preserving K-Means Clustering”, Proceedings of Pacific-Asia Workshop on Intelligence and Security Informatics, pp. 154-166, 2010.

  • E. Bertino, I.N. Fovino and L.P. Provenza. “A Framework for Evaluating Privacy Preserving Data Mining Algorithms”, Data Mining and Knowledge Discovery, Vol. 11, No. 2, pp. 121-154, 2005.


Abstract Views: 567

PDF Views: 1




  • Privacy Preserving Data Mining using Threshold Based Fuzzy C-Means Clustering

Abstract Views: 567  |  PDF Views: 1

Authors

V. Manikandan
Department of Information Technology, Lebanese French University, Erbil, Iraq
V. Porkodi
Department of Information Technology, Lebanese French University, Erbil, Iraq
Amin Salih Mohammed
Department of Information Technology, Lebanese French University, Erbil, Iraq
M. Sivaram
Department of Information Technology, Lebanese French University, Erbil, Iraq

Abstract


Privacy preserving is critical in the field of where data mining is transformed into cooperative task among individuals. In data mining, clustering algorithms are most skilled and frequently used frameworks. In this paper, we propose a privacy-preserving threshold clustering that uses code based technique with threshold estimation for sharing of secret data in privacy-preserving mechanism. The process includes code based methodology which enables the information to be partitioned into numerous shares and handled independently at various servers. The proposed method takes less number of iterations in comparison with existing methods that does not require any trust among the clients or servers. The paper additionally provides experimental results on security and computational efficiency of proposed method.

Keywords


Privacy Preserving, Data Mining, Threshold Cryptography, Fuzzy C-Means Clustering, Vandermonde Matrix, Secure Multiparty Computation.

References