Filters








73,713 Hits in 5.8 sec

Using Feature Selection to Improve the Utility of Differentially Private Data Publishing

Yasser Jafer, Stan Matwin, Marina Sokolova
2014 Procedia Computer Science  
Protection of patient's privacy is an obligation enforced by laws and regulations in the US, Canada, and other jurisdictions.  ...  We propose the TOP_Diff algorithm which offers a trade-off between anonymization level K and the privacy budget ε, and enables us to publish privacy preserving datasets with high utility.  ...  We do not use data independent generalization and random sampling and do not use microaggregation to achieve K-anonymity,etc.  ... 
doi:10.1016/j.procs.2014.08.076 fatcat:wsut4jmtrjg2lhdoprwzuls524

Using Safety Constraint for Transactional Dataset Anonymization [chapter]

Bechara Al Bouna, Chris Clifton, Qutaibah Malluhi
2013 Lecture Notes in Computer Science  
We conduct a set of experiments to evaluate privacy breach and the anonymization cost of safe grouping.  ...  In this paper, we address privacy breaches in transactional data where individuals have multiple tuples in a dataset.  ...  After the l-diversity enforcement process, the algorithms verifies whether the group contains k buckets, and if not anonymizes (which could mean generalizing, suppressing, or encrypting the values, depending  ... 
doi:10.1007/978-3-642-39256-6_11 fatcat:zglhd4smgzeqvli467z7zgiunu

Measuring Discrepancies in Airbnb Guest Acceptance Rates Using Anonymized Demographic Data [article]

Siddhartha Basu, Ruthie Berman, Adam Bloomston, John Campbell, Anne Diaz, Nanako Era, Benjamin Evans, Sukhada Palkar, Skyler Wharton
2022 arXiv   pre-print
In this paper, we present a system that measures discrepancies in platform user experience that are attributable to perceived race (experience gaps) using anonymized data.  ...  Our work establishes that measurement of experience gaps with anonymized data is feasible and can be used to guide the development of policies to promote equitable outcomes for users of Airbnb as well  ...  This could lead us to take a different approach to enforcing k-anonymity.  ... 
arXiv:2204.12001v1 fatcat:fm2cy5m3qvdzlnvtglxdby7dla

Privug: Using Probabilistic Programming for Quantifying Leakage in Privacy Risk Analysis [article]

Raúl Pardo, Willard Rafnsson, Christian Probst, Andrzej Wąsowski
2021 arXiv   pre-print
Privug is a tool-supported method to explore information leakage properties of data analytics and anonymization programs.  ...  In Privug, we reinterpret a program probabilistically, using off-the-shelf tools for Bayesian inference to perform information-theoretic analysis of the information flow.  ...  In those instances, k_ano masked Sex, replacing everyone's Sex with * to enforce 2-anonymity.  ... 
arXiv:2011.08742v5 fatcat:mechsiah25fxjdc6hsmbkf25au

ACHIEVING k-ANONYMITY PRIVACY PROTECTION USING GENERALIZATION AND SUPPRESSION

LATANYA SWEENEY
2002 International Journal of Uncertainty Fuzziness and Knowledge-Based Systems  
Both Datafly and µ-Argus use heuristics to make approximations, and so, they do not always yield optimal results.  ...  that appear in external data.  ...  Finally, I thank the corporate and government members of the Laboratory for International Data Privacy at Carnegie Mellon University for the opportunity to work on real-world data anonymity problems.  ... 
doi:10.1142/s021848850200165x fatcat:kgxoghfebfdznpbldnglpppksu

Prevalence of Problem Drug Use and Injecting Drug Use in Luxembourg: A Longitudinal and Methodological Perspective

Alain Origer
2012 European Addiction Research  
upon standardized and sustained data collection routines.  ...  data from different sources and different settings, control multiple counts and build  ...  Addiction) for their statistical support, to Sofia Lopes da Costa, Pascale Straus and Celine Diederich (EMCDDA Focal Point Luxembourg/CRP-Santé) for their relentless efforts to ensure and maintain quality of data  ... 
doi:10.1159/000337211 pmid:22854631 fatcat:ojf5ywolyrb5pfcvmfe2icvdfe

User-centric identity management using trusted modules

J. Vossaert, J. Lapon, B. De Decker, V. Naessens
2013 Mathematical and computer modelling  
This paper presents a new flexible approach for user-centric identity management, using trusted modules.  ...  However, the strategy described above limits the impact and hence, decreases the incentive for malicious users. Using the anonymous credentials will deteriorate the performance.  ...  Our current implementation uses customized protocols and message formats although SAML tokens could be used. However, this will decrease the performance significantly.  ... 
doi:10.1016/j.mcm.2012.06.010 fatcat:angbjoejd5b67eieos5qyhllsm

Protecting location privacy using location semantics

Byoungyoung Lee, Jinoh Oh, Hwanjo Yu, Jong Kim
2011 Proceedings of the 17th ACM SIGKDD international conference on Knowledge discovery and data mining - KDD '11  
Location privacy protection methods based on k-anonymity and ℓdiversity have been proposed to provide anonymized use of LBS.  ...  In our scheme, location semantics are first learned from location data.  ...  As θt decreases the average size of a cloaking area increases because a small θt implies more strict anonymization degree and causes a larger cloaking area.  ... 
doi:10.1145/2020408.2020602 dblp:conf/kdd/LeeOYK11 fatcat:lt2szwgr6zg3faqhznwochh5nu

Evaluating Seat Belt Use in Lebanon (1997-2017)

Ziad Akl, Mona Akl, Charli Eriksson, Mervyn Gifford, Dalal Koustuv
2019 The Open Public Health Journal  
Results: The results show a significant variation in the use of the seat belt. When enforcement efforts are in progress, seat belt use increases.  ...  Our observations of seat belt use among drivers and front seat passengers showed a significant correlation between seat belt use and the enforcement of seat belt law.  ...  All information will continue to be anonymous, and all collected data will be used for this study only.  ... 
doi:10.2174/1874944501912010127 fatcat:wpuqwzuolnhxlhxpy7bdjki3vq

Flexible data anonymization using ARX-Current status and challenges ahead

Fabian Prasser, Johanna Eicher, Helmut Spengler, Raffael Bild, Klaus A. Kuhn
2020 Software, Practice & Experience  
For instance, the effectiveness of different anonymization techniques depends on context, and thus tools need to support a large set of methods to ensure that the usefulness of data is not overly affected  ...  Data anonymization is an important building block of data protection concepts, as it allows to reduce privacy risks by altering data.  ...  Moreover, we would like to thank the anonymous  ... 
doi:10.1002/spe.2812 fatcat:5mzoacmnjjdwrn2xsoincydjyy

A Framework to Balance Privacy and Data Usability Using Data Degradation

Harold van Heerde, Maarten Fokkinga, Nicolas Anciaux
2009 2009 International Conference on Computational Science and Engineering  
Although the services are free in terms of money, the user does not know how much he or she actually pays for a given service when allowing his or her data to be collected, unaware of taking a significant  ...  data as long as possible.  ...  This technique is often used in k-anonymity research, where it is used to generalize identities in order to make the data k-anonymous [24] , and applied in data mining and warehousing [17] .  ... 
doi:10.1109/cse.2009.174 dblp:conf/cse/HeerdeFA09 fatcat:xezygbtixrhyzf2pzvaun3cg5a

Logit Estimation Using Warner's Randomized Response Model

Zawar Hussain, Javid Shabbir
2008 Journal of Modern Applied Statistical Methods  
As a means of guaranteeing anonymity to the respondent, consider Warner's (1965) randomized response model.  ...  Survey respondents may not be willing to reveal their true answers to sensitive questions without foolproof guarantees of anonymity -not only from outside observers such as law enforcement or friends and  ... 
doi:10.22237/jmasm/1209615000 fatcat:zwhrzzdyzjg3jg5kwcscrkf23y

Using the small-world model to improve Freenet performance

Hui Zhang, Ashish Goel, Ramesh Govindan
2004 Computer Networks  
I. specific function such as distributed data storage, cache replication, multicasting etc. and uses normal I nternet functionality for all other purposes.  ...  These systems can be modeled as distributed hash-tables; they essentially distribute 〈 key, data 〉 tuples  ...  The arrow from a key to a node means this node contains this key in its data store and therefore claims itself as the source of this key.  ... 
doi:10.1016/j.comnet.2004.05.004 fatcat:iq5jkllhv5ftfd7nunapck2j54

Using the small-world model to improve freenet performance

Hui Zhang, Ashish Goel, Ramesh Govindan
2002 Computer communication review  
I. specific function such as distributed data storage, cache replication, multicasting etc. and uses normal I nternet functionality for all other purposes.  ...  These systems can be modeled as distributed hash-tables; they essentially distribute 〈 key, data 〉 tuples  ...  The arrow from a key to a node means this node contains this key in its data store and therefore claims itself as the source of this key.  ... 
doi:10.1145/510726.510753 fatcat:ej26al36unhyxks2qwjdifl7km

Using the theory of planned behavior to understand student intent to use tobacco in California universities

Harit K. Agroia, Anna Nelson
2022 International Journal of Community Medicine and Public Health  
Most tobacco use, including addiction, starts between 18-26 years of age.  ...  Administrators are encouraged to tailor enforcement messages to increase compliance.  ...  and PBC with levels of policy enforcement using Kruskal-Wallis. 4 Constructs enforcement levels N Mean rank Df X 2 P Communication only 40 72.18 Attitude Communication and signage 80 90.86 2 5.355 0.07  ... 
doi:10.18203/2394-6040.ijcmph20220674 fatcat:thr7fwohfbbgre5olcbx2mftqe
« Previous Showing results 1 — 15 out of 73,713 results