DPLK-Means: A Novel Differential Privacy K-Means Mechanism

Ren, Jian; Xiong, Jinbo; Yao, Zhiqiang; Ma, Rong; Lin, Mingwei

doi:10.1109/dsc.2017.64

Cited by 25 publications

(9 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, we expect differential identifiability can be applied to more complex privacy preservation issues to evaluate performance, such as data mining in big data. Table 2 [13,[33][34][35][36][37] compares some privacy-preserving k-means algorithms. Currently, differential identifiability can provide an easy parameterization approach.…”

Section: K-means Clustering Algorithmsmentioning

confidence: 99%

Differential identifiability clustering algorithms for big data analysis

Shang

Zhao

Ren

et al. 2021

Sci. China Inf. Sci.

View full text Add to dashboard Cite

Individual privacy preservation has become an important issue with the development of big data technology. The definition of ρ-differential identifiability (DI) precisely matches the legal definitions of privacy, which can provide an easy parameterization approach for practitioners so that they can set privacy parameters based on the privacy concept of individual identifiability. However, differential identifiability is currently only applied to some simple queries and achieved by Laplace mechanism, which cannot satisfy complex privacy preservation issues in big data analysis. In this paper, we propose a new exponential mechanism and composition properties of differential identifiability, and then apply differential identifiability to k-means and k-prototypes algorithms on MapReduce framework. DI k-means algorithm uses the usual Laplace mechanism and composition properties for numerical databases, while DI k-prototypes algorithm uses the new exponential mechanism and composition properties for mixed databases. The experimental results show that both DI k-means and DI k-prototypes algorithms satisfy differential identifiability.

show abstract

Section: K-means Clustering Algorithmsmentioning

confidence: 99%

Differential identifiability clustering algorithms for big data analysis

Shang

Zhao

Ren

et al. 2021

Sci. China Inf. Sci.

View full text Add to dashboard Cite

show abstract

“…The privacy loss parameter defines how much noise is added and how much information about a sample could be revealed from the output, and the application of these mechanisms requires finding a balance between privacy loss and accuracy of the federated analysis model [ 31 ]. Different versions of differentially private algorithms for data classification [ 31 , 32 , 33 ] and clustering [ 34 , 35 ] are suggested. The trusted execution environment (TEE), e.g.…”

Section: Federated Learning Challengesmentioning

confidence: 99%

Open-Source Federated Learning Frameworks for IoT: A Comparative Review and Analysis

Kholod

Yanaki

Fomichev

et al. 2020

Sensors

View full text Add to dashboard Cite

The rapid development of Internet of Things (IoT) systems has led to the problem of managing and analyzing the large volumes of data that they generate. Traditional approaches that involve collection of data from IoT devices into one centralized repository for further analysis are not always applicable due to the large amount of collected data, the use of communication channels with limited bandwidth, security and privacy requirements, etc. Federated learning (FL) is an emerging approach that allows one to analyze data directly on data sources and to federate the results of each analysis to yield a result as traditional centralized data processing. FL is being actively developed, and currently, there are several open-source frameworks that implement it. This article presents a comparative review and analysis of the existing open-source FL frameworks, including their applicability in IoT systems. The authors evaluated the following features of the frameworks: ease of use and deployment, development, analysis capabilities, accuracy, and performance. Three different data sets were used in the experiments—two signal data sets of different volumes and one image data set. To model low-power IoT devices, computing nodes with small resources were defined in the testbed. The research results revealed FL frameworks that could be applied in the IoT systems now, but with certain restrictions on their use.

show abstract

“…And they developed a method for selecting the initial centroid for a specified number of clusters k to solve the problem that the number of points outputs by the canopy algorithm is uncertain. Reference [36] proposed a DPLK-means algorithm based on differential privacy, which improved the selection of the initial center points through performing the differential privacy K-means algorithm to each subset divided by the original dataset.…”

Section: Related Workmentioning

confidence: 99%

An Optimizing and Differentially Private Clustering Algorithm for Mixed Data in SDN-Based Smart Grid

Wang

Guan

et al. 2019

IEEE Access

View full text Add to dashboard Cite

Software-defined network (SDN) is widely used in smart grid for monitoring and managing the communication network. Big data analytics for SDN-based smart grid has got increasing attention. It is a promising approach to use machine learning technologies to analyze a large amount of data generated in SDN-based smart grid. However, the disclosure of personal privacy information must receive considerable attention. For instance, data clustering in user electricity behavior analysis may lead to the disclosure of personal privacy information. In this paper, an optimizing and differentially private clustering algorithm named ODPCA is proposed. In the ODPCA, the differentially private K-means algorithm and K-modes algorithm are combined to cluster mixed data in a privacy-preserving manner. The allocation of privacy budgets is optimized to improve the accuracy of clustering results. Specifically, the loss function that considers both the numerical and categorical attributes between true centroids and noisy centroids is analyzed to optimize the allocation the privacy budget; the number of iterations of clustering is set to a fixed value based on the total privacy budget and the minimal privacy budget allocated to each iteration. It is proved that the ODPCA can meet the differential privacy requirements and has better performance by comparing with other popular algorithms.INDEX TERMS Differential privacy, clustering, machine learning, SDN-based smart grid, big data.

show abstract

DPLK-Means: A Novel Differential Privacy K-Means Mechanism

Cited by 25 publications

References 18 publications

Differential identifiability clustering algorithms for big data analysis

Differential identifiability clustering algorithms for big data analysis

Open-Source Federated Learning Frameworks for IoT: A Comparative Review and Analysis

An Optimizing and Differentially Private Clustering Algorithm for Mixed Data in SDN-Based Smart Grid

Contact Info

Product

Resources

About