首页|Data anonymization evaluation for big data and IoT environment
Data anonymization evaluation for big data and IoT environment
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NSTL
Elsevier
The growth of big data can increase risks of re-identification in complex IoT environment. Data anonymization is widely used to prevent shared data from being re-identified private or sensitive information from anonymized data with other available data. It is very important to understand the risks of re-identification of results and process of commonly used anonymization techniques before properly mitigating. This work proposes a data anonymisation evaluation framework that can evaluate commonly used data anonymization algorithms in terms of privacy preserving level, data utility, and performance. Specifically, data utility, privacy metrics, and information loss were used to evaluate data anonymization schemes that can further optimise the data anonymization process to keep risks of re identification low. Experiment results demonstrate that the proposed solution can effectively evaluate the performance and de-identification features that can help to prevent inappropriate usage of anonymized data. CO 2022 Published by Elsevier Inc.
Data anonymizationPrivacy modelRe-identificationPrivacy evaluationData utilityData SecurityDIFFERENTIAL PRIVACYEFFICIENTINTERNET
Ni, Chunchun、Cang, Li Shan、Gope, Prosanta、Min, Geyong
NSTL
Elsevier
