A privacy preserving association rule mining algorithm was introducedThis algorithm preserved privacy of individual values by computing scalar productMeanwhile the algorithm of computing scalar product was given and the security was analyzed

Privacy preserving association rule mining in vertically partitioned data

Mining useful knowledge from corpus of data has become an important application in many fields Data mining algorithms like clustering, classification work on this data and provide crisp information for analysis As these data are available through various channels into public domain, privacy for the owners of the data is increasing need Though privacy can be provided by hiding sensitive data, it will affect the data mining algorithms in knowledge extraction, so an effective mechanism is required to provide privacy to the data and at the same time without affecting the data mining algorithms Privacy concern is a primary hindrance for quality data analysis Data mining algorithms on the contrary focus on the mathematical nature than on the private nature of the information Therefore instead of removing or encrypting sensitive data, we propose transformation strategies that retain the statistical, semantic and heuristic nature of the data while masking the sensitive information The proposed Correlation Based Transformation Strategy (CBTS) combines Correlation Analysis in tandem with data transformation techniques such as Singular Value Decomposition (SVD), Principal Component Analysis (PCA) and Non Negative Matrix Factorization (NNMF) provides the intended level of privacy preservation and enables data analysis The outcome of CBTS is evaluated on standard datasets against popular data mining techniques with significant success and Information Entropy is also accounted

CBTS: Correlation based transformation strategy for privacy preserving data mining

In this work, we propose an integrated itemset hiding algorithm that eliminates the need of pre-mining and post-mining and uses a simple heuristic in selecting the itemset and the item in itemset for distortion. Base algorithm (matrix-apriori) works without candidate generation so efficiency is increased. Performance evaluation demonstrates (1) the side effect (lost itemsets) and time while increasing the number of sensitive itemsets and support of itemset and (2) speed up by integrating the post mining.

Integrated Approach for Privacy Preserving Itemset Mining

This paper proposes a novel exact approach that relies on integer programming for association rule hiding. A large panorama of solutions exists for the complex problem of itemset hiding: from practical heuristic approaches to more accurate exact approaches. Exact approaches provide better solutions while suffering from the lack of performance and existing exact approaches still augment their methods with heuristics to make the problem solvable. In this case, the solution may not be optimum. This work presents a full-exact method, without any need for heuristics. Extensive tests are conducted on 10 real datasets to analyze distance and information loss performances of the algorithm in comparison to a former similar algorithm. Since the approach provides the optimum solution to the problem, it should be considered as a reference method.

/pdf/full-exact-approach-for-frequent-itemset-hiding-3h1cekrfq0.pdf

Full-Exact Approach for Frequent Itemset Hiding

Itemset mining is the challenging step of association rule mining that aims to extract patterns among items from transactional databases. In the case of applying itemset mining on the shared data of organizations, each party needs to hide its sensitive knowledge before extracting global knowledge for mutual benefit. Ensuring the privacy of the sensitive itemsets is not the only challenge in the itemset hiding process, also the distortion given to the non-sensitive knowledge and data should be kept at minimum. Most of the previous works related to itemset hiding allow database owner to assign unique sensitive threshold for each sensitive itemset however itemsets may have different count and utility. In this paper we propose a new heuristic based hiding algorithm which 1) allows database owner to assign multiple sensitive threshold values for sensitive itemsets, 2) hides all user defined sensitive itemsets, 3) uses heuristics that minimizes loss of information and distortion on the shared database. In order to speed up hiding steps we represent the database as Pseudo Graph and perform scan operations on this data structure rather than the actual database. Performance evaluation of our algorithm Pseudo Graph Based Sanitization (PGBS) is conducted on 4 real databases. Distortion given to the nonsensitive itemsets (information loss), distortion given to the shared data (distance) and execution time in comparison to three similar algorithms is measured. Experimental results show that PGBS is competitive in terms of execution time and distortion and achieves reasonable performance in terms of information loss amongst the other algorithms.

Itemset Hiding under Multiple Sensitive Support Thresholds.

Privacy preserving association rule mining has triggered the development of many privacy preserving data mining techniques. A large fraction of them use randomized data distortion techniques to mask the data for preserving. This paper proposes a new transaction randomization method which is a combination of the fake transaction randomization method and a new per transaction randomization method. This method distorts the items within each transaction and ensures a higher level of data privacy in comparison to the previous approaches. The pertransaction randomization method involves a randomization function to replace the item by a random number guarantying privacy within the transaction also. A tool has also been developed to implement the proposed approach to mine frequent itemsets and association rules from the data guaranteeing the antimonotonic property.

Rajesh Kumar Boora

Papers

An Improved Approach to High Level Privacy Preserving Itemset Mining