Secure extraction of association rules in horizontally distributed database using improved UNIFI
暂无分享,去创建一个
Data extraction is used to extract important data from large database which stored at the multiple sites. It may be keep in many computers covered in the some physical location or may be covered a network of computers. In this paper, we present protocol for secure extraction of association rules in horizontally distributed database. This protocol is based on the Fast Distributed Mining (FDM) algorithm, using concept of encryption and decryption for extraction of knowledge. Here, we present Improved UNIFI algorithm for secure extraction of association rules. The objective of the protocol is to overcome the problem of extraction of association rules that simulates the existing system i.e grants frequent itemset recognition without candidate itemset generation. This protocol uses support, confidence threshold value and for security and privacy purpose used AES encryption, decryption standard which is symmetric block cipher. It is simple and important in terms of communication rounds as well as communication and computational cost.
[1] Elisa Bertino,et al. State-of-the-art in privacy preserving data mining , 2004, SGMD.
[2] Chris Clifton,et al. Privacy-preserving distributed mining of association rules on horizontally partitioned data , 2004, IEEE Transactions on Knowledge and Data Engineering.
[3] Jaideep Vaidya,et al. Privacy preserving association rule mining in vertically partitioned data , 2002, KDD.
[4] Ramakrishnan Srikant,et al. Fast Algorithms for Mining Association Rules in Large Databases , 1994, VLDB.