Privacy-preserving Mining Research Articles

Recent Developments in Privacy-Preserving Mining of Clinical Data.

With the dramatic increases in both the capability to collect personal data and the capability to analyze large amounts of data, increasingly sophisticated and personal insights are being drawn. These insights are valuable for clinical applications but also open up possibilities for identification and abuse of personal information. In this paper, we survey recent research on classical methods of privacy-preserving data mining. Looking at dominant techniques and recent innovations to them, we examine the applicability of these methods to the privacy-preserving analysis of clinical data. We also discuss promising directions for future research in this area.

Efficient privacy-preserving frequent itemset query over semantically secure encrypted cloud database

In recent years, more users tend to use data mining as a service (DMaaS) provided by cloud service providers. However, while enjoying the convenient pay-per-use mode and powerful capacity of cloud computing, users are also threatened by the potential risk of privacy leakage. In this paper, we aim to efficiently perform privacy-preserving DMaaS, and focus on frequent itemset mining over encrypted database in outsourced cloud environment. Existing work apply different encryption methods to design various privacy-preserving mining solutions. Nevertheless, these approaches either cannot provide sufficient security requirements, or introduce heavy computation costs. Some of them also need users staying on-line to execute computations, which are not practical in real-world applications. In this paper, we propose a novel efficient privacy-preserving frequent itemset query (PPFIQ) scheme using two homomorphic encryptions and ciphertext packing technique. The proposed scheme protects transaction database with semantic security, preserves mining privacy and resists frequency analysis attacks. Meanwhile, efficiency is guaranteed by inherent parallel computations for packed plaintexts and users could stay off-line during the mining process. We provide formal security analysis and evaluate the performance of our scheme with extensive experiments. The experiment results demonstrate that the proposed scheme can be efficiently implemented on large databases.

A Survey of Data Anonymization Techniques for Privacy-Preserving Mining in Bigdata

Bigdata era is seeing the data burst occurring in a multitude of angles that are better expressed in terms of the 4Vs (Volume, Velocity, Velocity, Veracity). While trying to infer information from data, care should be exercised as not to reveal the identity of the data owner, which breaches the privacy rights. Leakage of information can happen right from the data collection point, at the data storage area, followed by the distribution of data to data users/miners and finally with published results. A cross-matching of all these points with the 4Vs (growing still) of big data, puts a huge challenge on how to extract the maximum possible information, without compromising on the privacy of the data owner. Anonymization of the original data should be done at one or more of the above-mentioned stages before the data are given for the mining process. This work makes a survey of the various anonymization techniques followed to transform the data in such a way that the privacy of the data owner is not compromised. Also, the sample data drawn should resemble and represent the original dataset in the maximum possible number of dimensions. The results of the various methodologies have been analyzed and the observations have been presented.

Privacy-preserving Process Mining: Differential

Privacy-preserving Process Mining: Differential

Privacy Preserving Mining in Code Profiling Data

Privacy preserving data mining is an important issue nowadays for data mining. Since various organizations and people are generating sensitive data or information these days. They don’t want to share their sensitive data however that data can be useful for data mining purpose. So, due to privacy preserving mining that data can be mined usefully without harming the privacy of that data. Privacy can be preserved by applying encryption on database which is to be mined because now the data is secure due to encryption. Code profiling is a field in software engineering where we can apply data mining to discover some knowledge so that it will be useful in future development of software. In this work we have applied privacy preserving mining in code profiling data such as software metrics of various codes. Results of data mining on actual and encrypted data are compared for accuracy. We have also analyzed the results of privacy preserving mining in code profiling data and found interesting results.

Physical implementation of oblivious transfer using optical correlated randomness

We demonstrate physical implementation of information-theoretic secure oblivious transfer based on bounded observability using optical correlated randomness in semiconductor lasers driven by common random light broadcast over optical fibers. We demonstrate that the scheme can achieve one-out-of-two oblivious transfer with effective key generation rate of 110 kb/s. The results show that this scheme is a promising approach to achieve information-theoretic secure oblivious transfer over long distances for future applications of secure computation such as privacy-preserving database mining, auctions and electronic-voting.

Sensitivity Association Rule Mining using Weight based Fuzzy Logic

Mining of sensitive rules is the most important task in data mining. Most of the existing techniques worked on finding sensitive rules based upon the crisp thresh hold value of support and confidence which cause serious side effects to the original database. To avoid these crisp boundaries this paper aims to use WFPPM (Weighted Fuzzy Privacy Preserving Mining) to extract sensitive association rules. WFPPM completely find the sensitive rules by calculating the weights of the rules. At first, we apply FP-Growth to mine association rules from the database. Next, we implement fuzzy to find the sensitive rules among the extracted rules. Experimental results show that the proposed scheme find actual sensitive rules without any modification along with maintaining the quality of the released data as compared to the previous techniques.

Secure and flexible cloud-assisted association rule mining over horizontally partitioned databases

With recent trends in big data and cloud computing, data mining has also attracted considerable interest due to its potential to deal with distributed data in the cloud. However, existing data mining technologies may not be directly deployed as we need to avoid accidental privacy disclosure when data from different sources are mined. In this paper, we propose a secure and flexible cloud-assisted association rule mining over horizontally partitioned databases. Using the proposed scheme, data owners can provide their data and mine the association rules in the cloud flexibly, while being assured of minimal risks of privacy leakage. We then show that our proposed scheme achieves privacy-preserving mining of association rules, and provides resilience against collusion attacks. A comparative summary demonstrates that the proposed scheme is more efficient, in terms of computational costs, relative to several existing homomorphic-encryption-based schemes.

Privacy-Preserving-Outsourced Association Rule Mining on Vertically Partitioned Databases

Association rule mining and frequent itemset mining are two popular and widely studied data analysis techniques for a range of applications. In this paper, we focus on privacy-preserving mining on vertically partitioned databases. In such a scenario, data owners wish to learn the association rules or frequent itemsets from a collective data set and disclose as little information about their (sensitive) raw data as possible to other data owners and third parties. To ensure data privacy, we design an efficient homomorphic encryption scheme and a secure comparison scheme. We then propose a cloud-aided frequent itemset mining solution, which is used to build an association rule mining solution. Our solutions are designed for outsourced databases that allow multiple data owners to efficiently share their data securely without compromising on data privacy. Our solutions leak less information about the raw data than most existing solutions. In comparison to the only known solution achieving a similar privacy level as our proposed solutions, the performance of our proposed solutions is three to five orders of magnitude higher. Based on our experiment findings using different parameters and data sets, we demonstrate that the run time in each of our solutions is only one order higher than that in the best non-privacy-preserving data mining algorithms. Since both data and computing work are outsourced to the cloud servers, the resource consumption at the data owner end is very low.

Effective Incentive Compatible Model for Privacy Preservation of Information in Secure Data Sharing and Publishing

Privacy preserving is one of the most important research topics in the data security field and it has become a serious concern in the secure transformation of personal data in recent years. For example, different credit card companies and disease control centers may try to build better data sharing or publishing models for privacy protection through privacy preserving data mining techniques (PPDM). A model has been proposed to design the effective Privacy Preserving Mining Framework for secure private information transformation and Publishing. Building this framework depends on Incentive Compatible Model based secure code computation process and PPDM techniques like Association rule mining, Randomization method and Cryptographic technique. An Encryption algorithm is used to identify which data sets need to be encrypted for preserving privacy in data storage publishing. The Incentive Compatible model is very efficient in protecting the sensitive data in privacy preserving data sharing, because it provides the secrecy against not only semi-honest adversary model and also the malicious model.

Privacy-Preserving Mining of Association Rules for Smart Grid

The widespread deployment of smart meters for the modernization of the electricity distribution network has been associated with privacy concerns due to the potentially large number of measurements that reflect the consumers’ behavior. At the same time, how to extract important knowledge from the potentially large of measurements — these measurements are spilt among various parties, has already became a hot topic in the field of data mining. In this paper, we present protocols that can be used to compute meter measurements over defined sets of meters without revealing any additional about the individual meter readings, and address secure mining of association rules. Thus, most of the benefits of the smart grid can be achieved without revealing individual data.

Privacy-Preserving Mining of Association Rules From Outsourced Transaction Databases

Spurred by developments such as cloud computing, there has been considerable recent interest in the paradigm of data mining-as-a-service. A company (data owner) lacking in expertise or computational resources can outsource its mining needs to a third party service provider (server). However, both the items and the association rules of the outsourced database are considered private property of the corporation (data owner). To protect corporate privacy, the data owner transforms its data and ships it to the server, sends mining queries to the server, and recovers the true patterns from the extracted patterns received from the server. In this paper, we study the problem of outsourcing the association rule mining task within a corporate privacy-preserving framework. We propose an attack model based on background knowledge and devise a scheme for privacy preserving outsourced mining. Our scheme ensures that each transformed item is indistinguishable with respect to the attacker's background knowledge, from at least k-1 other transformed items. Our comprehensive experiments on a very large and real transaction database demonstrate that our techniques are effective, scalable, and protect privacy.

Privacy-preserving range set union for rare cases in healthcare data

Hospitals have to use a large amount of medical data from individuals while protecting their privacy to execute medical data mining. It is important to find ‘rare’ cases among medical data of individuals in many healthcare applications. Therefore hospitals need privacy-preserving mining techniques to find rare cases among medical data of individuals. However, previous privacy-preserving data-mining techniques cannot be used to find rare cases. In this study, they suggest a privacy-preserving ‘range set union’ protocol that can be used to find rare cases in the private medical datasets of individuals.

An Appraisal on Privacy Preserving Mining of Association Rules

An interesting new direction for data mining research is the development of techniques that incorporate privacy concerns for association rules. In this work, we present a framework for mining association rules from various transactions. These transactions mainly consisting of categorical items, where the data has to preserve privacy of individual transactions. By using uniform randomization, it is feasible to recover association rules, but these rules are in turn be exploited to find privacy breaches. Hence, in this work we clearly analyze the nature of privacy breaches and propose a new class of randomization operators that are much more effective than uniform randomization which was proposed previously. Here we also derive formulae for an unbiased support estimator, which allows us to recover item set supports from randomization data sets. Here we also show how the above derived formulae will be incorporated into mining algorithms. Finally; we provide experimental results that validate the proposed algorithm by applying it to real data sets.

Privacy-Preserving Hierarchical-k-Means Clustering on Horizontally Partitioned Data

Privacy preserving mining of distributed data is an important direction for data mining, and privacy preserving clustering is one of the main researches. Privacy-preserving data mining techniques enable knowledge discovery without requiring disclosure of private data. The existing privacy preserving algorithms mainly concentrated on association rules and classification, only few algorithms on privacy preserving clustering, and these algorithms mainly concentrated on centralized and vertically partitioned data. So we proposed privacy preserving hierarchical k-means clustering algorithm on horizontally partitioned data, denoted as HPPHKC. The complexity on k-means clustering algorithm is only O(n), so most existing privacy preserving clustering algorithms are concentrated on k-means and based on two parties and the trusted third party, these algorithms have the drawbacks of inaccurate results because of choosing initial clustering centers randomly and applying to multi-party difficult and revealing privacy because of depending on the third party excessively. By introduction of three protocols for secure multi-party computation: distance computation, cluster center computation, and standardization and combination of the merits of hierarchical and k-means clustering, we presented a privacy-preserving hierarchical-k-means clustering algorithm on horizontally partitioned data for semi-honest parties using some secure multi-party computation protocols. The algorithm uses the security protocol mentioned above to achieve the protection of the privacy data, and uses the hierarchical clustering algorithm to obtain k cluster centers, then uses the k-means clustering algorithm to obtain the final k clusters. We introduce the clustering feature and the clustering feature tree, which are used to summarize the cluster representations. A clustering feature (CF) is a three-dimensional vector summarizing information about clusters of objects. The ith clustering feature is CFi = (cni,cci,cpi), where cni is the number of th clusters, denoted as the size of th cluster, cci is the center of the cni objects, and cpi is the pointer of the list of cni objects. The algorithm has two phases: the first phase, every object can be as a cluster, a secure computation protocol is used to compute the dissimilarity matrix and the most similar clusters will be merged. This process is repeated until we get the assigned clusters number k and get k clustering centers. In the second phase, the semi-honest third party and all data involved parties use the k-means algorithm refine the results of the first phase and get the final clustering results. Finally, we give the proof of security of the algorithm and analysis of communication costs, and we show that our scheme is secure and complete with good efficiency.

FRAPP: a framework for high-accuracy privacy-preserving mining

To preserve client privacy in the data mining process, a variety of techniques based on random perturbation of individual data records have been proposed recently. In this paper, we present FRAPP, a generalized matrix-theoretic framework of random perturbation, which facilitates a systematic approach to the design of perturbation mechanisms for privacy-preserving mining. Specifically, FRAPP is used to demonstrate that (a) the prior techniques differ only in their choices for the perturbation matrix elements, and (b) a symmetric positive-definite perturbation matrix with minimal condition number can be identified, substantially enhancing the accuracy even under strict privacy requirements. We also propose a novel perturbation mechanism wherein the matrix elements are themselves characterized as random variables, and demonstrate that this feature provides significant improvements in privacy at only a marginal reduction in accuracy. The quantitative utility of FRAPP, which is a general-purpose random-perturbation-based privacy-preserving mining technique, is evaluated specifically with regard to association and classification rule mining on a variety of real datasets. Our experimental results indicate that, for a given privacy requirement, either substantially lower modeling errors are incurred as compared to the prior techniques, or the errors are comparable to those of direct mining on the true database.

Privacy preserving itemset mining through noisy items

This work investigates the problem of privacy-preserving mining of frequent itemsets. We propose a procedure to protect the privacy of data by adding noisy items to each transaction. Then, an algorithm is proposed to reconstruct frequent itemsets from these noise-added transactions. The experimental results indicate that this method can achieve a rather high level of accuracy. Our method utilizes existing algorithms for frequent itemset mining, and thereby takes full advantage of their progress to mine frequent itemset efficiently.