Data Level Privacy Preserving: A Stochastic Perturbation Approach Based on Differential Privacy

With the great amount of available data, especially collecting from the ubiquitous Internet of Things (IoT), the issue of privacy leakage arises increasingly concerns recently. To preserve the privacy of IoT datasets, traditional methods usually calibrate random noises on the data values to achieve...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on knowledge and data engineering Jg. 35; H. 4; S. 3619 - 3631
Hauptverfasser: Ma, Chuan, Yuan, Long, Han, Li, Ding, Ming, Bhaskar, Raghav, Li, Jun
Format: Journal Article
Sprache:Englisch
Veröffentlicht: New York IEEE 01.04.2023
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Schlagworte:
Algorithms
Availability
Cognitive tasks
Datasets
Differential privacy
Internet of Things
Machine learning
Machine learning algorithms
Perturbation methods
Privacy
Probability density function
Publishing
stochastic perturbation
Stochastic processes
tabular dataset
ISSN:1041-4347, 1558-2191
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:With the great amount of available data, especially collecting from the ubiquitous Internet of Things (IoT), the issue of privacy leakage arises increasingly concerns recently. To preserve the privacy of IoT datasets, traditional methods usually calibrate random noises on the data values to achieve differential privacy (DP). However, the amount of the calibrating noises should be carefully designed and a heedless value will definitely degrade the availability of datasets. Thus, in this work, we propose a stochastic perturbation method to sanitize the dataset, where the perturbation is obtained from the rest samples in the same dataset. In addition, we derive the expression of the utility level based on its unique framework and prove that the proposed algorithm can achieve the <inline-formula><tex-math notation="LaTeX">\epsilon</tex-math> <mml:math><mml:mi>ε</mml:mi></mml:math><inline-graphic xlink:href="yuan-ieq1-3137047.gif"/> </inline-formula>-DP. To show the effectiveness of the proposed algorithm, we conduct extensive experiments on real-life datasets by various functions, such as query answers and machine learning tasks. By comparing with the state-of-the-art methods, our proposed algorithm can achieve a better performance under the same privacy level.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1041-4347
1558-2191
DOI:10.1109/TKDE.2021.3137047