Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
Filters








312 Hits in 4.4 sec

Partition Based Perturbation for Privacy Preserving Distributed Data Mining

M. Antony Sheela, K. Vijayalakshmi
2017 Cybernetics and Information Technologies  
The perturbation maintains the statistical relationship among attributes.  ...  Data mining on vertically or horizontally partitioned dataset has the overhead of protecting the private data. Perturbation is a technique that protects the revealing of data.  ...  The proposed kd-anonymous perturbation method gives a smaller disclosure risk than the kd-tree method. This is shown in Fig. 2 .  ... 
doi:10.1515/cait-2017-0015 fatcat:7ggmcyvv6zespm2kypb4e3hy44

A Quantitative Approach for Evaluating the Utility of a Differentially Private Behavioral Science Dataset

Raquel Hill, Michael Hansen, Erick Janssen, Stephanie A. Sanders, Julia R. Heiman, Li Xiong
2014 2014 IEEE International Conference on Healthcare Informatics  
Our results align with the theory of differential privacy and show when the number of records in the database is sufficiently larger than the number of cells covered by a database query, the number of  ...  Objective: Social scientists who collect large amounts of medical data value the privacy of their survey participants.  ...  The researcher needs to consider all of the potential risks including whether "any disclosure of the subjects' responses could reasonably place the subjects at risk of criminal or civil liability or be  ... 
doi:10.1109/ichi.2014.45 dblp:conf/ichi/HillHJSHX14 fatcat:dkkk7cpfjfdtrow2h6qlddghju

Non-Interactive Differential Privacy: a Survey [article]

David Leoni
2012 arXiv   pre-print
Differential privacy stands out as a model that provides strong formal guarantees about the anonymity of the participants in a sanitized database.  ...  Theory, utility and a data-aware comparison are discussed on a variety of principles and concrete applications.  ...  Since we are addressing the problem of statistical disclosure at large, we use R to denote a wide range of output possibilities for the mechanism designers, whose goal is to devise a mechanism function  ... 
arXiv:1205.2726v1 fatcat:shps24vi2jg3fibknsmltsziky

Non-interactive differential privacy

David Leoni
2012 Proceedings of the First International Workshop on Open Data - WOD '12  
Differential privacy stands out as a model that provides strong formal guarantees about the anonymity of the participants in a sanitized database.  ...  Theory, utility and a data-aware comparison are discussed on a variety of principles and concrete applications.  ...  Since we are addressing the problem of statistical disclosure at large, we use R to denote a wide range of output possibilities for the mechanism designers, whose goal is to devise a mechanism function  ... 
doi:10.1145/2422604.2422611 dblp:conf/wod/Leoni12 fatcat:tdfnvwiqybe7pos2z4sc4unk7q

HTF: Homogeneous Tree Framework for Differentially-Private Release of Location Data [article]

Sina Shaham, Gabriel Ghinita, Ritesh Ahuja, John Krumm, Cyrus Shahabi
2021 arXiv   pre-print
We show through extensive experiments on large-scale real-world data that the proposed approach achieves superior accuracy compared to existing approaches.  ...  We identify density homogeneity as a main factor driving the accuracy of DP-compliant histograms, and we build a data structure that splits the space such that data density is homogeneous within each resulting  ...  Note that since the grid is fixed, enumerating split candidates as cell coordinates is data-independent, hence does not incur disclosure risk.  ... 
arXiv:2107.13749v1 fatcat:fpgfyky3ibgd3jcpjq6oqmk6ke

Developing privacy solutions for sharing and analysing healthcare data

Luvai Motiwalla, Xiao Bai Li
2013 International Journal of Business Information Systems  
A pilot evaluation study on large real-world healthcare data shows the effectiveness of our solution in privacy protection.  ...  Dataset-level properties and statistics remain approximately the same after data masking; however, individual record-level values are altered to prevent privacy disclosure.  ...  The content is solely the responsibility of the authors and does not necessarily represent the official views of NSF, NLM or NIH. Dr. Xiaobai Li  ... 
doi:10.1504/ijbis.2013.054335 pmid:24285983 pmcid:PMC3839961 fatcat:5nuv37m77ff4ndjxgedsixybie

Secure multidimensional range queries over outsourced data

Bijit Hore, Sharad Mehrotra, Mustafa Canim, Murat Kantarcioglu
2011 The VLDB journal  
We also study the trade-off characteristics through an extensive set of experiments on real and synthetic data.  ...  For a given bucketization scheme, we derive cost and disclosure-risk metrics that estimate client's computational overhead and disclosure risk respectively.  ...  Acknowledgments This work was made possible by grant from NSF (award number 1045296) and gift from NEC laboratories USA.  ... 
doi:10.1007/s00778-011-0245-7 fatcat:4ma6bbcxafg3jpitwtfu47ho6e

A retrospective study on the relationship between annual airborne pollen levels during four decades of 1975–2014 and annual occurrence of ulcerative colitis, Crohn's disease, primary biliary cirrhosis, fulminant hepatitis, severe acute pancreatitis, interstitial pneumonia, amyloidosis, based on the national registry database of specific intractable diseases in Japan

Akira Awaya, Yoshiyuki Kuroiwa
2019 Archives of Epidemiology and Public Health  
Koichi Iwata for his elaborate and diligent graphing work and correlation analysis. Conflict of interest The authors declare no conflict of interest in the preparation of this article.  ...  The authors have never had an opportunity of receiving any research fund in relation to this research.  ...  Japanese cedar trees were rapidly cut on a large scale in the 1940s-50s, because of military and industrial needs during and after the World War II.  ... 
doi:10.15761/aeph.1000112 fatcat:c7n4iv55gvcc7hgx4noewbrkqy

Efficiency Analysis of Machine Learning Intelligent Investment Based on K-means Algorithm

Liang Li, Jia Wang
2020 IEEE Access  
The results show that Capricorn has a certain randomness in the selection process of the fund, and chooses to reduce the rate of return in order to control the risk.  ...  the advent of the era of large asset management in the domestic wealth management industry, in order to improve the efficiency of financial services, traditional finance is needed.  ...  The kd tree is a binary tree that represents a division of the k-dimensional space.  ... 
doi:10.1109/access.2020.3011366 fatcat:asn3zm6egrfs3fsb3n7xwmwj5u

Class-Restricted Clustering and Microperturbation for Data Privacy

Xiao-Bai Li, Sumit Sarkar
2013 Management science  
To accomplish this, the clustering method, which is based on a minimum spanning tree (MST) technique, uses two risk-utility tradeoff measures in the growing and pruning stages of the MST technique respectively  ...  their inability to preserve important statistical properties such as the variance of attributes and the covariance across attributes.  ...  The content is solely the responsibility of the authors and does not necessarily represent the official views of NLM or NIH.  ... 
doi:10.1287/mnsc.1120.1584 pmid:24307745 pmcid:PMC3846357 fatcat:tlehfdvraje3ng3iiglxkxqfnm

Data Clustering and Micro-perturbation for Privacy-Preserving Data Sharing and Analysis

Xiao-Bai Li, Sumit Sarkar
2010 International Conference on Information Systems  
Our approach is novel in that it (i) incorporates an entropy-based measure, which represents the disclosure risk of the categorical confidential attribute, into the traditional distance measure used for  ...  For numeric data, these approaches are also unable to preserve important statistical properties such as variance and covariance of the data.  ...  The proposed approach adopts a minimum spanning tree (MST) technique for clustering data and takes into account the disclosure risk of the categorical confidential attribute when forming data groups.  ... 
dblp:conf/icis/LiS10 fatcat:wfyeketugzdghkt4frow43n2ry

Protecting Privacy When Sharing and Releasing Data with Multiple Records per Person

Hasan Kartal, University of Illinois at Springfield, USA, Xiao-Bai Li, University of Massachusetts Lowell, USA
2020 Journal of the AIS  
This study concerns the risks of privacy disclosure when sharing and releasing a dataset in which each individual may be associated with multiple records.  ...  We propose two novel measures of privacy disclosure to arrive at a more appropriate assessment of disclosure risks.  ...  The content is solely the responsibility of the authors and does not necessarily represent the official views of the National Library of Medicine or the National Institutes of Health.  ... 
doi:10.17705/1jais.00643 fatcat:ayyymlnjejfsroqrfohxvbx3xa

Differential Privacy in Practice

Hiep H. Nguyen, Jong Kim, Yoonho Kim
2013 Journal of Computing Science and Engineering  
We briefly review the problem of statistical disclosure control under differential privacy model, which entails a formal and ad omnia privacy guarantee separating the utility of the database and the risk  ...  It has born fruitful results over the past ten years, both in theoretical connections to other fields and in practical applications to real-life datasets.  ...  ACKNOWLEDGMENTS This research was supported by World Class University program funded by the Ministry of Education, Science and Technology through the National Research Foundation of Korea (R31-10100).  ... 
doi:10.5626/jcse.2013.7.3.177 fatcat:xrcbyxpzfvh2tfdrr5572rdnku

Differentially Private Location Recommendations in Geosocial Networks

Jia Dong Zhang, Gabriel Ghinita, Chi Yin Chow
2014 2014 IEEE 15th International Conference on Mobile Data Management  
Extensive experimental results on real-world datasets show that a careful choice of differential privacy technique leads to satisfactory location recommendation results.  ...  With the help of location recommendations, users are able to learn about events, products or places of interest that are relevant to their preferences.  ...  ): Consider a statistical database that produces the transcript U on the set of queries Q = {Q 1 , . . . , Q q }, and let ϵ > 0 be an arbitrarily-small real constant.  ... 
doi:10.1109/mdm.2014.13 dblp:conf/mdm/ZhangGC14 fatcat:6jdwjw6sizdtzd6ilqqwao32dq

Review on a Privacy-Preserving and Efficient kNearest Neighbor Model Based on k- Dimension Tree for Outsource Data

Pratiksha Bhimte, Neha Mogre
2021 International journal of innovations in engineering and science  
tree encryption (defined by kd-tree enhancement). traditional KNN algorithm.  ...  However, because of the major security risks arising from computer computing, many organizations now encrypt data before extracting data.  ...  As mentioned earlier, a reliable cloudbut-curious cloud server cannot detect any information about its use in the kd tree process and distance comparisons.  ... 
doi:10.46335/ijies.2021.6.8.3 fatcat:iudir6vyqbcybg3coedqej5jde
« Previous Showing results 1 — 15 out of 312 results