Privacy Preserving Data Publishing with Multiple Sensitive Attributes based on Overlapped Slicing

Abstract

Investigation into privacy preserving data publishing with multiple sensitive attributes is performed to reduce probability of adversaries to guess the sensitive values. Masking the sensitive values is usually performed by anonymizing data by using generalization and suppression techniques. A successful anonymization technique should reduce information loss due to the generalization and suppression. This research attempts to solve both problems in microdata with multiple sensitive attributes. We propose a novel overlapped slicing method for privacy preserving data publishing with multiple sensitive attributes. We used discernibility metrics to measure information loss. The experiment result shows that our method obtained a lower discernibility value than other methods.Information 2019, 10, 362 2 of 18 data publishing based on single sensitive attribute, while in the real world, it should be a multiple sensitive attributes problem. Some researches concerned with multiple sensitive attributes, but almost all of them only solved partial problems. When, k-anonymity, l-diversity, and p-sensitive are performed by anonymizing data, it tends to produce information loss. While we use anatomy [8], a model, which dissociates quasi identifier attributes and sensitive attributes, it produces minimum information loss.The major problem of previous works is when a privacy model is applied to a microdata using any methods, it always produces information loss values. This work tried to minimize the information loss when anonymizing is conducted. This investigation started by distributing sensitive values. The sensitive values are distributed evenly in each bucket, which represents equivalence class. We also employed overlapped slicing not only for keeping the relationship between quasi identifier attributes and sensitive attributes, but also for scrambling the records to hold its privacy. It means that this work also aims to maintain its privacy but obtains better data utility. This paper has some following contributions:

Heap Bucketization Anonymity—An Efficient Privacy-Preserving Data Publishing Model for Multiple Sensitive Attributes

“…Tp-tree needs high storage requirement to store the indexing structure of the original dataset. Overlapped slicing method [63] 1 There is no much difference in execution time when compared with existing. Lsl-diversity mode [65].…”

f-Slip: an efficient privacy-preserving data publishing framework for 1:M microdata with multiple sensitive attributes

“…The Discernibility value metric was used to measure the utility and a comparison was made with two different existing methods and tested on an adult dataset. The overlapped slicing model lagged in dissociating the relationship between quasi-identifier and sensitive attributes (Widodo et al 2019). The privacy and security level of each sensitive attribute differs according to the different requirements of sensitivity.…”

f-Slip: An Efficient Privacy-Preserving Data Publishing Framework for 1: M Microdata with Multiple Sensitive Attributes.

“…The Discernibility value metric was used to measure the utility and a comparison was made with two different existing methods and tested on an adult dataset. The overlapped slicing model lagged in dissociating the relationship between quasi-identifier and sensitive attributes (Widodo et al 2019). The privacy and security Later, few researchers have paid concentration towards 1: M datasets.…”