Data Swapping Research Articles

A Computational Framework for Preserving Privacy and Maintaining Utility of Geographically Aggregated Data: A Stochastic Spatial Optimization Approach

Geographically aggregated data are often considered to be safe because information can be published by group as population counts rather than by individual. Identifiable information about individuals can still be disclosed when using such data, however. Conventional methods for protecting privacy, such as data swapping, often lack transparency because they do not quantify the reduction in disclosure risk. Recent methods, such as those based on differential privacy, could significantly compromise data utility by introducing excessive error. We develop a methodological framework to address the issues of privacy protection for geographically aggregated data while preserving data utility. In this framework, individuals at high risk of disclosure are moved to other locations to protect their privacy. Two spatial optimization models are developed to optimize these moves by maximizing privacy protection while maintaining data utility. The first model relocates all at-risk individuals while minimizing the error (hence maximizing the utility). The second model assumes a budget that specifies the maximum error to be introduced and maximizes the number of at-risk individuals being relocated within the error budget. Computational experiments performed on a synthetic population data set of two counties of Ohio indicate that the proposed models are effective and efficient in balancing data utility and privacy protection for real-world applications.

Order selection with confidence for finite mixture models

The determination of the number of mixture components (the order) of a finite mixture model has been an enduring problem in statistical inference. We prove that the closed testing principle leads to a sequential testing procedure (STP) that allows for confidence statements to be made regarding the order of a finite mixture model. We construct finite sample tests, via data splitting and data swapping, for use in the STP, and we prove that such tests are consistent against fixed alternatives. Simulation studies and real data examples are used to demonstrate the performance of the finite sample tests-based STP, yielding practical recommendations of their use as confidence estimators in combination with point estimates such as the Akaike information or Bayesian information criteria. In addition, we demonstrate that a modification of the STP yields a method that consistently selects the order of a finite mixture model, in the asymptotic sense. Our STP is not only applicable for order selection of finite mixture models, but is also useful for making confidence statements regarding any sequence of nested models.

Compilation of Parallel Data Access for Vector Processor in Radio Base Stations

The data size and data feature under the cur-rent mainstream compilation schemes can be diversified, formal methods are thus mandatory. However, in a micro base station, as an embedded system, the typical feature or opportunity of baseband algorithms is its predictable small code and data sizes. The research is thus needed and there is so far no dedicated research on the related register alloca-tion algorithms. In this letter, we focus on compilation re-search for baseband kernel subroutines of 5G micro base stations. We proposed a parallel data access compilation scheme for applications with fixed and known data size, while operation data can be mostly stored and allocated in register file. The goal of the compilation scheme is to opti-mize algorithms based on 4x4 or smaller matrices, to reach the maximum register file utility, and eliminate the extra register data swapping. At the same time, we hide the data access time when allocating data into register file, and minimize the data access cost by using VLIW machine, so that the overall running time is minimum. Based on a small register group (48x32b) and the proposed compilation method, this letter implemented frequently used baseband subroutines (kernels) of 4x4 matrix with complex variables of 16b+16b and reached minimized run time. Results show that the extra addressing and data accessing cost is mini-mized for algorithms with small data size.

An Energy-Efficient and Fast Scheme for Hybrid Storage Class Memory in an AIoT Terminal System

Conventional main memory can no longer meet the requirements of low energy consumption and massive data storage in an artificial intelligence Internet of Things (AIoT) system. Moreover, the efficiency is decreased due to the swapping of data between the main memory and storage. This paper presents a hybrid storage class memory system to reduce the energy consumption and optimize IO performance. Phase change memory (PCM) brings the advantages of low static power and a large capacity to a hybrid memory system. In order to avoid the impact of poor write performance in PCM, a migration scheme implemented in the memory controller is proposed. By counting the write times and row buffer miss times in PCM simultaneously, the write-intensive data can be selected and migrated from PCM to dynamic random-access memory (DRAM) efficiently, which improves the performance of hybrid storage class memory. In addition, a fast mode with a tmpfs-based, in-memory file system is applied to hybrid storage class memory to reduce the number of data movements between memory and external storage. Experimental results show that the proposed system can reduce energy consumption by 46.2% on average compared with the traditional DRAM-only system. The fast mode increases the IO performance of the system by more than 30 times compared with the common ext3 file system.

Data Anonymization for Hiding Personal Tendency in Set-Valued Database Publication

Set-valued database publication has been increasing its importance recently due to its benefit for various applications such as marketing analysis and advertising. However, publishing a raw set-valued database may cause individual privacy breach such as the leakage of sensitive information like personal tendencies when data recipients perform data analysis. Even though imposing data anonymization methods such as suppression-based methods and random data swapping methods to such a database can successfully hide personal tendency, it induces item loss from records and causes significant distortion in record structure that degrades database utility. To avoid the problems, we proposed a method based on swapping technique where an individual’s items in a record are swapped to items of the other record. Our swapping technique is distinct from existing one called random data swapping which yields much structure distortion. Even though the technique results in inaccuracy at a record level, it can preserve every single item in a database from loss. Thus, data recipients may obtain all the item information in an anonymized database. In addition, by carefully selecting a pair of records for item swapping, we can avoid excessive record structure distortion that leads to alter database content immensely. More importantly, such a strategy allows one to successfully hide personal tendency without sacrificing a lot of database utility.

Conditional Masking to Numerical Data

Protecting the privacy of datasets has become hugely important these days. Many real-life datasets like income data and medical data need to be secured before making it public. However, security comes at the cost of losing some useful statistical information about the dataset. Data obfuscation deals with this problem of masking a dataset in such a way that the utility of the data is maximized while minimizing the risk of the disclosure of sensitive information. Two popular approaches to data obfuscation for numerical data involve (i) data swapping and (ii) adding noise to data. While the former masks well sacrificing the whole of correlation information, the latter gives estimates for most of the popular statistics like mean, variance, quantiles and correlation but fails to give an unbiased estimate of the distribution curve of the original data. In this paper, we propose a mixed method of obfuscation combining the above two approaches and discuss how the proposed method succeeds in giving an unbiased estimation of the distribution curve while giving reliable estimates of the other well-known statistics like moments and correlation.

An integrated method for calculating DEM-based RUSLE LS

The improvement of resolution of digital elevation models (DEMs) and the increasing application of the Revised Universal Soil Loss Equation (RUSLE) over large areas have created problems for the efficiency of calculating the LS factor for large data sets. The pretreatment for flat areas, flow accumulation, and slope-length calculation have traditionally been the most time-consuming steps. However, obtaining these features are generally usually considered as separate steps, and calculations still tend to be time-consuming. We developed an integrated method to improve the efficiency of calculating the LS factor. The calculation model contains algorithms for calculating flow direction, flow accumulation, slope length, and the LS factor. We used the Deterministic 8 method to develop flow-direction octrees (FDOTs), flat matrices (FMs) and first-in-first-out queues (FIFOQs) tracing the flow path. These data structures were much more time-efficient for calculating the slope length inside the flats, the flow accumulation, and the slope length linearly by traversing the FDOTs from their leaves to their roots, which can reduce the search scope and data swapping. We evaluated the accuracy and effectiveness of this integrated algorithm by calculating the LS factor for three areas of the Loess Plateau in China and SRTM DEM of China. The results indicated that this tool could substantially improve the efficiency of LS-factor calculations over large areas without reducing accuracy.

Comparative Study on Perturbation Techniques in Privacy Preserving Data Mining on Two Numeric Datasets

Data Mining is a computational process that able to identify patterns, trends and behaviour from large datasets. With this advantages, data mining has been applied in many fields such as finance, healthcare, retail and so on. However, information disclosure become one of an issue during data mining process. Therefore, privacy protection is needed during data mining process which known as Privacy Preserving Data Mining (PPDM). There are several techniques available in PPDM and each of the techniques has its’ own benefits and drawbacks. In this research, perturbation technique is selected as privacy preserving technique. Perturbation technique is a method that alters the original data value before the application of data mining. In PPDM applications, perturbation technique able to provide a protection of data privacy but the accuracy of data should not be ignored too. In this research, three perturbation techniques are selected which are additive noise, data swapping and resample. For data mining techniques, two methods of classification are selected which are Naïve Bayes and Support Vector Machines (SVM). With the selection of these techniques, the experimental results are evaluated based on the hiding failure, accuracy and precision. For overall result, resample is selected as the best perturbation technique in naïve bayes and SVM classification for both glass and ionosphere datasets.

Data Swapping for Private Information Sharing of Web Search Logs

With the increasing number of sophisticated cyber attacks on both government and private infrastructure, cybersecurity data sharing is critical for the advancement of collaborative research among various entities, both in government, private sector, and academia. Of recent, the US Congress passed the Cyber Intelligence Sharing and Protection Act, as a framework for data sharing between various entities. Nevertheless this development raises the issue of trust between the collaborating parties, since shared data could be revealing. Conversely, due to the sensitive and confidential nature of the data involved, entities would have to employ various anonymization techniques to meet legal requirements in compliance with confidentiality policies of both their own organizations and federal government requirements. Secondly, a basic sharing of the data without the privatization process could make entities involved vulnerable to insider and inference attacks. For instance, an entity sharing data on cyber attacks might accidently reveal a sensitive network topology to an untrusted collaborator. As a contribution, we propose a modest but effective data privacy enhancement heuristic; a targeted 2k basic data swapping of individual web search log records. In this heuristic, if individual has a set of x records in their web search log set A, those records are swapped in that individual set A, then swapped again with another individual y records in set B. Our preliminary results show that data swapping is effective for big data and it would be demanding to trace the original issuer of the queries in a given large dataset of web search logs, thus providing some level of confidentiality.

Propensity score based conditional group swapping for disclosure limitation of strata-defining variables.

In this paper we propose a method for statistical disclosure limitation of categorical variables that we call Conditional Group Swapping. This approach is suitable for design and strata-defining variables, the cross-classification of which leads to the formation of important groups or subpopulations. These groups are considered important because from the point of view of data analysis it is desirable to preserve analytical characteristics within them. In general data swapping can be quite distorting ([12, 18, 15]), especially for the relationships between the variables not only within the subpopulations but for the overall data. To reduce the damage incurred by swapping, we propose to choose the records for swapping using conditional probabilities which depend on the characteristics of the exchanged records. In particular, our approach exploits the results of propensity scores methodology for the computation of swapping probabilities. The experimental results presented in the paper show good utility properties of the method.

Secure attribute sharing of linked microdata

Two organizations that have records on the same collection of individuals can benefit from sharing attributes on these individuals. The combined data, with records linked on certain common identifying information, is termed linked microdata. Linked microdata attributes can add considerable value to organizations by enabling them to perform analysis that can provide important information on individual (or record-level) data items. We illustrate practical examples of the need and benefits of sharing linked microdata and identify important privacy issues relating to this context. Based on a conditional distribution approach, we develop a procedure (SASH) for sharing masked attributes in linked microdata that addresses these privacy issues. Our experimental results show that SASH achieves a priori expectations of analytical usefulness, without either party having to provide true values of attribute data. Our results also show that an ad hoc approach such as data swapping, cannot achieve privacy without sacrificing usefulness or vice versa. Our study should provide immediate practical benefits to organizations interested in secure attribute sharing of linked microdata.

On the Accelerating of Two-dimensional Smart Laplacian Smoothing on the GPU

This paper presents a GPU-accelerated implementation of two-dimensional Smart Laplacian smoothing. This implementation is developed under the guideline of our paradigm for accelerating Laplacianbased mesh smoothing [13]. Two types of commonly used data layouts, Array-of-Structures (AoS) and Structure-of-Arrays (SoA) are used to represent triangular meshes in our implementation. Two iteration forms that have different choices of the swapping of intermediate data are also adopted. Furthermore, the feature CUDA Dynamic Parallelism (CDP) is employed to realize the nested parallelization in Smart Laplacian smoothing. Experimental results demonstrate that: (1) our implementation can achieve the speedups of up to 44x on the GPU GT640; (2) the data layout AoS can always obtain better efficiency than the SoA layout; (3) the form that needs to swap intermediate nodal coordinates is always slower than the one that does not swap data; (4) the version of our implementation with the use of the feature CDP is slightly faster than the version where the CDP is not adopted.

An Efficient Algorithm for Calculating Drainage Accumulation in Digital Elevation Models Based on the Basin Tree Index

Calculating drainage accumulation in a digital elevation model (DEM) is a common requirement for hydrology and terrain analysis. This letter presents a basin tree index (BTI) algorithm to improve the efficiency of this calculation, achieving the time complexity of <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="TeX">$O(N)$</tex-math></inline-formula> and the input–output efficiency of <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="TeX">$O(\hbox{Scan}(N))$</tex-math></inline-formula> . We have developed a BTI to guide the calculation sequence, allowing us to avoid invalid and repeat manipulation and to reduce random scattered data access. The BTI provides a one-to-one correspondence between a basin and an outlet, and it maintains cells orderly in terms of both the elevation and the spatial distribution, as it is built by tracing the drainage path from the outlet to the source directly. This is achieved according to the drainage direction for each basin extracted from the DEM, where basins are divided based on watersheds. Therefore, the drainage accumulation can be calculated by traversing the BTIs from their leaves to roots linearly and simultaneously. These BTIs divide the entire study area into several basins that can be processed in isolation, reducing the search scope for basins and allowing the algorithm to efficiently utilize the main memory and decrease the data swapping between the main memory and the disk. A DEM for the Zhejiang Province in China was used to validate the results and compare the processing speeds. The results show that the algorithm provides the same calculation result as alternative algorithms but becomes more efficient as the volume of the DEM data increases. Furthermore, the BTI algorithm in this letter is easy to implement.

English

This paper reviews methods developed for anonymizing data from 2009 to 2010. Publishing microdata such as census or patient data for extensive research and other purposes is an important problem area being focused by government agencies and other social associations. The traditional approach identified through literature survey reveals that the approach of eliminating uniquely identifying fields such as social security number from microdata, still results in disclosure of sensitive data, k-anonymization optimization algorithm ,seems to be promising and powerful in certain cases ,still carrying the restrictions that optimized k-anonymity are NP-hard, thereby leading to severe computational challenges. k-anonimity faces the problem of homogeneity attack and background knowledge attack . The notion of ldiversity proposed in the literature to address this issue also poses a number of constraints , as it proved to be inefficient to prevent attribute disclosure (skewness attack and similarity attack), l-diversity is difficult to achieve and may not provide sufficient privacy protection against sensitive attribute across equivalence class can substantially improve the privacy as against information disclosure limitation techniques such as sampling cell suppression rounding and data swapping and pertubertation. This paper aims to discuss efficient anonymization approach that requires partitioning of microdata equivalence classes and by minimizing closeness by kernel smoothing and determining ether move distances by controlling the distribution pattern of sensitive attribute in a microdata and also maintaining diversity.

English

4 ABSTRACT: This paper reviews methods developed for anonymizing data from 2001 to 2003 . Publishing microdata such as census or patient data for extensive research and other purposes is an important problem area being focused by government agencies and other social associations. The traditional approach identified through literature survey reveals that the approach of eliminating uniquely identifying fields such as social security number from microdata, still results in disclosure of sensitive data, k-anonymization optimization algorithm ,seems to be promising and powerful in certain cases ,still carrying the restrictions that optimized k-anonymity are NP-hard, thereby leading to severe computational challenges. k-anonimity faces the problem of homogeneity attack and background knowledge attack . The notion of l- diversity proposed in the literature to address this issue also poses a number of constraints , as it proved to be inefficient to prevent attribute disclosure (skewness attack and similarity attack), l-diversity is difficult to achieve and may not provide sufficient privacy protection against sensitive attribute across equivalence class can substantially improve the privacy as against information disclosure limitation techniques such as sampling cell suppression rounding and data swapping and pertubertation. This paper aims to discuss efficient anonymization approach that requires partitioning of microdata equivalence classes and by minimizing closeness by kernel smoothing and determining ether move distances by controlling the distribution pattern of sensitive attribute in a microdata and also maintaining diversity.

English

This paper reviews methods developed for anonymizing data from 2007 to 2012 . Publishing microdata such as census or patient data for extensive research and other purposes is an important problem area being focused by government agencies and other social associations. The traditional approach identified through literature survey reveals that the approach of eliminating uniquely identifying fields such as social security number from microdata, still results in disclosure of sensitive data, k-anonymization optimization algorithm ,seems to be promising and powerful in certain cases ,still carrying the restrictions that optimized k-anonymity are NP-hard, thereby leading to severe computational challenges. k-anonimity faces the problem of homogeneity attack and background knowledge attack . The notion of ldiversity proposed in the literature to address this issue also poses a number of constraints , as it proved to be inefficient to prevent attribute disclosure (skewness attack and similarity attack), l-diversity is difficult to achieve and may not provide sufficient privacy protection against sensitive attribute across equivalence class can substantially improve the privacy as against information disclosure limitation techniques such as sampling cell suppression rounding and data swapping and pertubertation. This paper aims to discuss efficient anonymization approach that requires partitioning of microdata equivalence classes and by minimizing closeness by kernel smoothing and determining ether move distances by controlling the distribution pattern of sensitive attribute in a microdata and also maintaining diversity.

English

This paper reviews methods developed for anonymizing data from 2008 to 2009. Publishing microdata such as census or patient data for extensive research and other purposes is an important problem area being focused by government agencies and other social associations. The traditional approach identified through literature survey reveals that the approach of eliminating uniquely identifying fields such as social security number from microdata, still results in disclosure of sensitive data, k-anonymization optimization algorithm ,seems to be promising and powerful in certain cases ,still carrying the restrictions that optimized k-anonymity are NP-hard, thereby leading to severe computational challenges. k-anonimity faces the problem of homogeneity attack and background knowledge attack . The notion of ldiversity proposed in the literature to address this issue also poses a number of constraints , as it proved to be inefficient to prevent attribute disclosure (skewness attack and similarity attack), l-diversity is difficult to achieve and may not provide sufficient privacy protection against sensitive attribute across equivalence class can substantially improve the privacy as against information disclosure limitation techniques such as sampling cell suppression rounding and data swapping and pertubertation. This paper aims to discuss efficient anonymization approach that requires partitioning of microdata equivalence classes and by minimizing closeness by kernel smoothing and determining ether move distances by controlling the distribution pattern of sensitive attribute in a microdata and also maintaining diversity.

English

This paper reviews methods developed for anonymizing data from 1989 to 1993 . Publishing microdata such as census or patient data for extensive research and other purposes is an important problem area being focused by government agencies and other social associations. The traditional approach identified through literature survey reveals that the approach of eliminating uniquely identifying fields such as social security number from microdata, still results in disclosure of sensitive data, k-anonymization optimization algorithm ,seems to be promising and powerful in certain cases ,still carrying the restrictions that optimized k-anonymity are NP-hard, thereby leading to severe computational challenges. k-anonimity faces the problem of homogeneity attack and background knowledge attack . The notion of l- diversity proposed in the literature to address this issue also poses a number of constraints , as it proved to be inefficient to prevent attribute disclosure (skewness attack and similarity attack), l-diversity is difficult to achieve and may not provide sufficient privacy protection against sensitive attribute across equivalence class can substantially improve the privacy as against information disclosure limitation techniques such as sampling cell suppression rounding and data swapping and pertubertation. This paper aims to discuss efficient anonymization approach that requires partitioning of microdata equivalence classes and by minimizing closeness by kernel smoothing and determining ether move distances by controlling the distribution pattern of sensitive attribute in a microdata and also maintaining diversity.

English

This paper reviews methods developed for anonymizing data from 1984 to 1988 . Publishing microdata such as census or patient data for extensive research and other purposes is an important problem area being focused by government agencies and other social associations. The traditional approach identified through literature survey reveals that the approach of eliminating uniquely identifying fields such as social security number from microdata, still results in disclosure of sensitive data, k-anonymization optimization algorithm ,seems to be promising and powerful in certain cases ,still carrying the restrictions that optimized k-anonymity are NP-hard, thereby leading to severe computational challenges. k-anonimity faces the problem of homogeneity attack and background knowledge attack . The notion of ldiversity proposed in the literature to address this issue also poses a number of constraints , as it proved to be inefficient to prevent attribute disclosure (skewness attack and similarity attack), l-diversity is difficult to achieve and may not provide sufficient privacy protection against sensitive attribute across equivalence class can substantially improve the privacy as against information disclosure limitation techniques such as sampling cell suppression rounding and data swapping and pertubertation. This paper aims to discuss efficient anonymization approach that requires partitioning of microdata equivalence classes and by minimizing closeness by kernel smoothing and determining ether move distances by controlling the distribution pattern of sensitive attribute in a microdata and also maintaining diversity.

Data sharing and reuse: What are the issues?

Data sharing and reuse: What are the issues?