Privacy Preserving Data Publishing Research Articles

Enhancing data publishing privacy: split-and-mould, an algorithm for equivalent specification

<div align="center"><span>Data sharing and publication have been popular in recent years due to the abundance of options. Evaluating and extracting data from sizable valuable databases i.e., data mining has various challenges which include issues with security, privacy, and data integrity. Anonymized data is used in the majority of privacy preserving data publication approaches, depending on a few utilitarian measures. However, applications that have particular needs for the data they utilize might not be able to use the anonymized data. Practical data anonymization must work to accomplish two opposing objectives: to maintain the data’s usefulness and to satisfy a specific privacy need. <br /> The utility loss when data is anonymized is frequently measured using generic utility metrics, such as the specific values generalized in a specific ontology. As a need for an application, we suggest equivalent specification, a technique that enables a data user to characterize some properties of the anonymized data. We also introduce the “split-and-mould” algorithm, a heuristic anonymization algorithm that applies a generalization method to the user-provided parameters. Our preliminary results indicate that the specification format and procedure can improve significantly the utility of the anonymized data for data mining that develop predictive models, like decision trees (DTs) and Naïve Bayes.</span></div>

Privacy-preserving data publishing: an information-driven distributed genetic algorithm

The privacy-preserving data publishing (PPDP) problem has gained substantial attention from research communities, industries, and governments due to the increasing requirements for data publishing and concerns about data privacy. However, achieving a balance between preserving privacy and maintaining data quality remains a challenging task in PPDP. This paper presents an information-driven distributed genetic algorithm (ID-DGA) that aims to achieve optimal anonymization through attribute generalization and record suppression. The proposed algorithm incorporates various components, including an information-driven crossover operator, an information-driven mutation operator, an information-driven improvement operator, and a two-dimensional selection operator. Furthermore, a distributed population model is utilized to improve population diversity while reducing the running time. Experimental results confirm the superiority of ID-DGA in terms of solution accuracy, convergence speed, and the effectiveness of all the proposed components.

DP2-Pub: Differentially Private High-Dimensional Data Publication With Invariant Post Randomization

A large amount of high-dimensional and heterogeneous data appear in practical applications, which are often published to third parties for data analysis, recommendations, targeted advertising, and reliable predictions. However, publishing these data may disclose personal sensitive information, resulting in an increasing concern on privacy violations. Privacy-preserving data publishing has received considerable attention in recent years. Unfortunately, the differentially private publication of high dimensional data remains a challenging problem. In this paper, we propose a differentially private high-dimensional data publication mechanism (DP2-Pub) that runs in two phases: a Markov-blanket-based attribute clustering phase and an invariant post randomization (PRAM) phase. Specifically, splitting attributes into several low-dimensional clusters with high intra-cluster cohesion and low inter-cluster coupling helps obtain a reasonable allocation of privacy budget, while a double-perturbation mechanism satisfying local differential privacy facilitates an invariant PRAM to ensure no loss of statistical information and thus significantly preserves data utility. We also extend our DP2-Pub mechanism to the scenario with a semi-honest server which satisfies local differential privacy. We conduct extensive experiments on four real-world datasets and the experimental results demonstrate that our mechanism can significantly improve the data utility of the published data while satisfying differential privacy.

An Improved Partitioning Method via Disassociation towards Environmental Sustainability

The amount of data created by individuals increases daily. These data may be gathered from various sources, such as social networks, e-commerce websites and healthcare systems, and they are frequently made available to third-party research and commercial organisations to facilitate a wide range of data studies. The protection of sensitive and confidential information included within the datasets to be published must be addressed, even though publishing data can assist organisations in improving their service offerings and developing new solutions that would not otherwise be available. The research community has invested great effort over the past two decades to comprehend how individuals’ privacy may be preserved when their data need to be published. Disassociation is a common approach for anonymising transactional data against re-identification attacks in privacy-preserving data publishing. To address this issue, we proposed three new strategies for horizontal partitioning: suppression, adding and remaining list. Each strategy identifies a different approach for handling small clusters with fewer than k transactions. We used three real datasets for transactional data in our experiments, and our findings showed that our proposed strategies could decrease the percentage of information loss of disassociated transactional data by almost 35%, comparing it with the previous original disassociation algorithm. As a result, the utility of published data will be improved.

Data Anonymization With Diversity Constraints

Recent privacy legislation has aimed to restrict and control the amount of personal data published by companies and shared with third parties. Much of this real data is not only sensitive requiring anonymization but also contains characteristic details from a variety of individuals. This diversity is desirable in many applications ranging from Web search to drug and product development. Unfortunately, data anonymization techniques have largely ignored diversity in its published result. This inadvertently propagates underlying bias in subsequent data analysis. We study the problem of finding a diverse anonymized data instance where diversity is measured via a set of diversity constraints. We formalize diversity constraints, and study their fundamental problems of satisfiability, implication, and validation. We show that determining the existence of a diverse, anonymized instance can be done in PTIME, and we present a clustering-based algorithm, along with optimizations to improve performance. We conduct extensive experiments using real and synthetic data showing the effectiveness of our techniques, and improvement over existing baselines. Our work aligns with recent trends towards responsible data science by coupling diversity with privacy-preserving data publishing.

AN An Enhanced Differential Homomorphic Model using N-Prime Scheme for Privacy Preservation

In preserving individual privacy in data publishing, several efforts have been made by scholars globally to develop an individual privacy preserving model and hybridized models which harness the strength of the individual model to increase privacy preservation in data Publishing (PPDP). The Differential homomorphic model (DHM) was among the hybridized models developed that combine differential and homomorphic models. Though is one of the state of the art hybridization methods for privacy preservation because of the Differential model and Homomorphic model strengths of the two hybridized models which are the ability to prevent composition problems and database attacks respectively. However, applying this model is challenging because of the high computational complexities due to the modular exponentiation problem available in pailler encryption scheme used in DHM. In this research, an N-PRIME homomorphic encryption scheme was proposed to replace the Pailler encryption scheme in the differential homomorphic model (DHM). The designed model was 51% faster than the existing model (Differential Homomorphic Model) in terms of computation time and 48.5% faster when generating the graphical data set, though the designed model consumed 4% more storage space than the existing model.

Uncovering the structures of privacy research using bibliometric network analysis and topic modelling

PurposeThis paper aims that privacy research is divided in distinct communities and rarely considered as a singular field, harming its disciplinary identity. The authors collected 119.810 publications and over 3 million references to perform a bibliometric domain analysis as a quantitative approach to uncover the structures within the privacy research field.Design/methodology/approachThe bibliometric domain analysis consists of a combined directed network and topic model of published privacy research. The network contains 83,159 publications and 462,633 internal references. A Latent Dirichlet allocation (LDA) topic model from the same dataset offers an additional lens on structure by classifying each publication on 36 topics with the network data. The combined outcomes of these methods are used to investigate the structural position and topical make-up of the privacy research communities.FindingsThe authors identified the research communities as well as categorised their structural positioning. Four communities form the core of privacy research: individual privacy and law, cloud computing, location data and privacy-preserving data publishing. The latter is a macro-community of data mining, anonymity metrics and differential privacy. Surrounding the core are applied communities. Further removed are communities with little influence, most notably the medical communities that make up 14.4% of the network. The topic model shows system design as a potentially latent community. Noteworthy is the absence of a centralised body of knowledge on organisational privacy management.Originality/valueThis is the first in-depth, quantitative mapping study of all privacy research.

Incremental Diversity: An Efficient Anonymization Technique for PPDP of Multiple Sensitive Attributes

Data collected at the organizations such as schools, offices, healthcare centers and e-commerce websites contain multiple sensitive attributes. The sensitive information from these organisations such as marks obtained, salary, disease, treatment and traveling history are personal information that an individual dislikes to disclose to the public as it may lead to privacy threats. Therefore, it is necessary to preserve privacy of the data before publishing. Privacy Preserving Data Publishing(PPDP) algorithms aim to publish the data without compromising the privacy of individuals. In the recent years several algorithms have been designed for PPDP multiple sensitive attributes. The major limitations are, firstly among several sensitive attributes these algorithms consider one of them as primary sensitive attribute and anonymize the data, however there may be other dominant sensitive attributes that need to be preserved. Secondly, there is no consistent way to categorize multiple sensitive attributes. Lastly, increased proportion of records are generated due to usage of generalization and suppression techniques. Hence, to overcome these limitations the current work proposes an efficient approach to categorize the sensitive attributes based their semantics and anonymize the data using an anatomy technique. This reduces the residual records as well as categorizes the attributes. The results are compared with popular techniques like Simple Distribution of Sensitive Values (SDSV) and (l, e) diversity. Experiments prove that our method outperforms the existing methods in terms of categorization of multiple sensitive attributes, reducing the percentage of residual records and preventing the existing privacy threats.

Local generalization and bucketization technique for personalized privacy preservation

Anonymization technique has been extensively studied and widely applied for privacy-preserving data publishing. In most previous approaches, a microdata table consists of three categories of attributes, namely explicit-identifier, quasi-identifier (QI), and sensitive attribute. In general, individuals may have different views on the sensitivity of different attributes. Therefore, there is another type of attribute that contains both QI values and sensitive values, termed semi-sensitive attribute. In this paper, we propose a new anonymization technique, called Local Generalization and Bucketization, to prevent identity disclosure and protect the sensitive values on each semi-sensitive attribute and sensitive attribute. The rationale is to use local generalization and local bucketization to divide the tuples into local equivalence groups and partition the sensitive values into local buckets, respectively. The protections of local generalization and local bucketization are independent, so that they can be implemented by appropriate algorithms without weakening other protection. Besides, the protection of local bucketization for each semi-sensitive attribute and sensitive attribute is also independent. Consequently, local bucketization can comply with various principles in different attributes according to the actual requirements of anonymization. We conducted extensive experiments to illustrate the effectiveness of the proposed approach.

Preserving the Privacy of Sensitive Data Using Bit-Coded-Sensitive Algorithm (BCSA)

Organizations now deal with massive amounts of data. Data is collected from various points such as hospitals, credit card companies, and search engines. After collecting this voluminous data, it is published and shared for research. Data that is collected may have sensitive information that might be used to identify an individual and consequently lead to privacy violations when published. To address this challenge, privacy-preserving data publishing (PPDP) seeks to remove threats to privacy while ensuring that the necessary information is released for data mining. Various techniques have been proposed to solve the problems associated with sensitive information. One such technique is k- anonymity. This technique is the best and very efficient. However, it also leads to loss of information, reduces data utility, and works well only with static tables. In this paper, we proposed a technique that addresses the challenges of K-anonymity known as the Bit-Coded-Sensitive Algorithm (BCSA). This algorithm is more efficient and effective and ensures that the privacy of the individual is preserved by avoiding disclosure, and linkages and at the same time ensuring high quality and utility of data. BCSA first identifies the source of data and based on that, uses bits to code sensitive data with a key.

Optimized key generation-based privacy preserving data mining model for secure data publishing

The data from the mobile devices and internet services plays a significant role now a day. The information shared needs to be original to get the best solution. Without the utilization of privacy preservation techniques, the individual's sensitive information cannot be exposed. The Privacy preserving data publishing (PPDP) is one of the privacy preserving techniques to preserve privacy. However, the reduction of the loss of data and the security enhancement are the major challenges. To solve the issues in secure data publishing, the efficient Cat Swarm Henry Gas Solubility Optimization (CSHGSO) is introduced for achieving effective privacy preservation for secure data publishing. In addition, the proposed CSHGSO is devised by the incorporation of Cat Swarm Optimization (CSO), and Henry Gas Solubility Optimization (HGSO). Here, the procedure of generating secret key is carried out based on the proposed CSHGSO with respect to the objective measures. The experimentation of the developed CSHGSO is performed in JAVA tool using Heart Disease Dataset. Furthermore, the CSHGSO achieved the higher conditional privacy of 1.338 using database-1, maximum accuracy of 0.965 using database-4, and the NMI value of 0.927 using database-4.

Differential Privacy via Haar Wavelet Transform and Gaussian Mechanism for Range Query.

Range query is the hot topic of the privacy-preserving data publishing. To preserve privacy, the large range query means more accumulate noise will be injected into the input data. This study presents a research on differential privacy for range query via Haar wavelet transform and Gaussian mechanism. First, the noise injected into the input data via Laplace mechanism is analyzed, and we conclude that it is difficult to judge the level of privacy protection based on the Haar wavelet transform and Laplace mechanism for range query because the sum of independent random Laplace variables is not a variable of a Laplace distribution. Second, the method of injecting noise into Haar wavelet coefficients via Gaussian mechanism is proposed in this study. Finally, the maximum variance for any range query under the framework of Haar wavelet transform and Gaussian mechanism is given. The analysis shows that using Haar wavelet transform and Gaussian mechanism, we can preserve the differential privacy for each input data and any range query, and the variance of noise is far less than that just using the Gaussian mechanism. In an experimental study on the dataset age extracted from IPUM's census data of the United States, we confirm that the proposed mechanism has much smaller maximum variance of noises than the Gaussian mechanism for range-count queries.

Background knowledge attacks in privacy-preserving data publishing models

Massive volumes of data are being generated at every moment through various sources in the cyber-physical world. While storing as well as facilitating these data for business or individual requirements, data disclosure, sensitive data leakage, and privacy breaches are important concerns to both service providers and service consumers. Many privacy-preserving data publishing models came into existence to protect data security and privacy from disclosure. Background knowledge has been an important data source to the adversary and has become a potential threat to many privacy-preserving data publishing models. Background knowledge allows the adversary to reveal sensitive information of an individual from the published data. In this paper, we formalize background knowledge by defining different knowledge sets. We present a privacy model against the given background knowledge. We analyze the conventional privacy-preserving data publishing models such as k-anonymity, l-diversity, and t-closeness against the background knowledge attacks and show that all these privacy models fail to preserve privacy against the comprehensive background knowledge adversarial model, which we formalized in this work. Comprehensive background knowledge attacks in privacy-preserving data publishing models are practical in many real-world applications, and we believe that the privacy model presented in this work advances the research findings in the area.

A New Anonymization Model for Privacy Preserving Data Publishing: CANON

Data privacy is a challenging trade-off problem between privacy preserving and data utility. Anonymization is a fundamental approach for privacy preserving and also a hard trade-off problem. It enables to hide the identities of data subjects or record owners and requires to be developed near-optimal solutions. In this paper, a new multidimensional anonymization model (CANON) that employs vantage-point tree (VPtree) and multidimensional generalization for greedy partitioning and anonymization, respectively, is proposed and introduced successfully for the first time. The main concept of CANON is inspired from Mondrian, which is an anonymization model for privacy preserving data publishing. Experimental results have shown that CANON takes data distribution into consideration and creates equivalence classes including closer data points than Mondrian. As a result, CANON provides better data utility than Mondrian in terms of GCP metric and it is a promising anonymization model for future works.

Bridging unlinkability and data utility: Privacy preserving data publication schemes for healthcare informatics

Publishing patient data without revealing their sensitive information is one of the challenging research issues in the healthcare sector. Patient records contain useful information that is often released to healthcare industries and government institutions to support medical and census research. There are several existing privacy models in protecting healthcare data privacy, which are mainly built upon the anonymity of patients. In this paper, we incorporate unlinkability in the context of healthcare data publication, where two new privacy notions namely identity unlinkability and attribute unlinkability are introduced. We design two schemes using the proposed models to address identity disclosure and attribute disclosure problems in publishing healthcare data. Experimental results on real and synthetic datasets show that our schemes efficiently achieve data utility preservation and privacy protection simultaneously.

Preserving Privacy of High-Dimensional Data by l-Diverse Constrained Slicing

In the modern world of digitalization, data growth, aggregation and sharing have escalated drastically. Users share huge amounts of data due to the widespread adoption of Internet-of-things (IoT) and cloud-based smart devices. Such data could have confidential attributes about various individuals. Therefore, privacy preservation has become an important concern. Many privacy-preserving data publication models have been proposed to ensure data sharing without privacy disclosures. However, publishing high-dimensional data with sufficient privacy is still a challenging task and very little focus has been given to propound optimal privacy solutions for high-dimensional data. In this paper, we propose a novel privacy-preserving model to anonymize high-dimensional data (prone to various privacy attacks including probabilistic, skewness, and gender-specific). Our proposed model is a combination of l-diversity along with constrained slicing and vertical division. The proposed model can protect the above-stated attacks with minimal information loss. The extensive experiments on real-world datasets advocate the outperformance of our proposed model among its counterparts.

Transactional Data Anonymization for Privacy and Information Preservation via Disassociation and Local Suppression

Ubiquitous devices in IoT-based environments create a large amount of transactional data on daily personal behaviors. Releasing these data across various platforms and applications for data mining can create tremendous opportunities for knowledge-based decision making. However, solid guarantees on the risk of re-identification are required to make these data broadly available. Disassociation is a popular method for transactional data anonymization against re-identification attacks in privacy-preserving data publishing. The anonymization algorithm of disassociation is performed in parallel, suitable for the asymmetric paralleled data process in IoT where the nodes have limited computation power and storage space. However, the anonymization algorithm of disassociation is based on the global recoding mode to achieve transactional data km -anonymization, which leads to a loss of combinations of items in transactional datasets, thus decreasing the data quality of the published transactions. To address the issue, we propose a novel vertical partition strategy in this paper. By employing local suppression and global partition, we first eliminate the itemsets which violate km-anonymity to construct the first km-anonymous record chunk. Then, by the processes of itemset creating and reducing, we recombine the globally partitioned items from the first record chunk to construct remaining km-anonymous record chunks. The experiments illustrate that our scheme can retain more association between items in the dataset, which improves the utility of published data.

Privacy preserving dynamic data release against synonymous linkage based on microaggregation

The rapid development of the mobile Internet coupled with the widespread use of intelligent terminals have intensified the digitization of personal information and accelerated the evolution of the era of big data. The sharing and publishing of various big data brings convenience and also increases the risk of personal privacy leakage. In order to reduce users’ privacy leakage that may be caused by data release, many privacy preserving data publishing methods have been proposed by scientists in both academia and industry in the recent years. However, non-numerical sensitive information has natural semantic relevance, and therefore, synonymous linkages may still exist and cause serious privacy disclosures in privacy protection methods based on an anonymous model. To address this issue, this paper proposes a privacy preserving dynamic data publishing method based on microaggregation. A series of indicators are accordingly designed to evaluate the synonymous linkages between the non-numerical sensitive values which in turn facilitate in improving the clustering effect of the microaggregation anonymous method. The dynamic update program is introduced into the proposed microaggregation method to realize the dynamic release and update of data. Experimental analysis suggests that the proposed method provides better privacy protection effect and availability of published data in contrast to the state-of-the-art methods.

MRMondrian: Scalable Multidimensional Anonymisation for Big Data Privacy Preservation

Scalable data processing platforms built on cloud computing becomes increasingly attractive as infrastructure for supporting big data applications. But privacy concerns are one of the major obstacles to making use of public cloud platforms. Multidimensional anonymisation, a global-recoding generalisation scheme for privacy-preserving data publishing, has been a recent focus due to its capability of balancing data obfuscation and usability. Existing multidimensional anonymisation methods suffer from scalability problems when handling big data due to the impractical serial I/O cost. Given the recursive feature of multidimensional anonymisation, parallelisation is an ideal solution to scalability issues. However, it is still a challenge to use existing distributed and parallel paradigms directly for recursive computation. In this paper, we propose a scalable approach for big data multidimensional anonymisation based on MapReduce, a state-of-the-art data processing paradigm. Our basic idea is to partition a data set recursively into smaller partitions using MapReduce until all partitions can fit in the memory of a computing node. A tree indexing structure is proposed to achieve recursive computation. Moreover, we show the applicability of our approach to differential privacy. Experimental results on real-life data demonstrate that our approach can significantly improve the scalability of multidimensional anonymisation over existing methods.

A new utility‐aware anonymization model for privacy preserving data publishing

AbstractMost of data in various forms contain sensitive information about individuals and so publishing such data might violate privacy. Privacy preserving data publishing (PPDP) is an essential for publishing useful data while preserving privacy. Anonymization, which is a utility based privacy preserving approach, helps hiding the identities of data subjects and also provides data utility. Since data utility is effective on the accuracy of analysis model, new anonymization algorithms to improve data utility are always required. Mondrian is one of the near‐optimal anonymization models that presents high data utility and is frequently used for PPDP. However, the upper bound problem of Mondrian causes a decrease in potential data utility. This article focuses on this problem and proposes a new utility‐aware anonymization model (u‐Mondrian). Experimental results have shown that u‐Mondrian presents an acceptable solution to the upper bound problem, increases total data utility and presents higher data utility than Mondrian for different partitioning strategies and datasets.