Achieving differential privacy of trajectory data publishing in participatory sensing

Li, Meng; Zhu, Liehuang; Zhang, Zijian; Xu, Rixin

doi:10.1016/j.ins.2017.03.015

Cited by 82 publications

(45 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The first category is using the exponential mechanism [60], [61], in which the utility function is defined to assign higher scores with the exponentially greater probability of being selected to an output so that the final output is close to the optimum utility. Li et al [62] proposed a differential privacy trajectory publishing methodology using the utility function to merge locations generating closer trajectory partitions that effectively reduces the trajectory information loss after generalization. The second category is choosing the optimal privacy parameter to maximize the utility.…”

Section: Utility Optimizationmentioning

confidence: 99%

Risk-Aware Individual Trajectory Data Publishing With Differential Privacy

et al. 2021

View full text Add to dashboard Cite

Section: Utility Optimizationmentioning

confidence: 99%

Risk-Aware Individual Trajectory Data Publishing With Differential Privacy

et al. 2021

View full text Add to dashboard Cite

“…Hua et al proposed a generalization algorithm for differential privacy to merge nodes based on their distances [26]. To solve the problem of random and unbounded noises [26], Li et al proposed a novel differentially private algorithm with a bounded noise generation [10]. To solve the privacy of continuous publication in population statistics, a monitoring framework with w-event privacy guarantee was designed [27] including adaptive budget allocation, dynamic grouping and perturbation.…”

Section: Perturbationmentioning

confidence: 99%

Sensitive attribute privacy preservation of trajectory data publishing based on l-diversity

Yao

Chen

et al. 2020

Distrib Parallel Databases

View full text Add to dashboard Cite

The widely application of positioning technology has made collecting the movement of people feasible for knowledge-based decision. Data in its original form often contain sensitive attributes and publishing such data will leak individuals’ privacy. Especially, a privacy threat occurs when an attacker can link a record to a specific individual based on some known partial information. Therefore, maintaining privacy in the published data is a critical problem. To prevent record linkage, attribute linkage, and similarity attacks based on the background knowledge of trajectory data, we propose a data privacy preservation with enhanced l -diversity. First, we determine those critical spatial-temporal sequences which are more likely to cause privacy leakage. Then, we perturb these sequences by adding or deleting some spatial-temporal points while ensuring the published data satisfy our ( )-privacy, an enhanced privacy model from l -diversity. Our experiments on both synthetic and real-life datasets suggest that our proposed scheme can achieve better privacy while still ensuring high utility, compared with existing privacy preservation schemes on trajectory.

show abstract

“…Zheng et al [29, 30] found that the attributes information in published data can be used to correlate the user, and they provided their scheme with attributes generalization. Li et al [31] assumed the adversary can obtain the maximum degree of background knowledge to initial the differential attack, and they had utilized the principle of differential privacy to provide a dummy scheme to protect the privacy. There is no doubt that, the series of current algorithms had improved the capacity of location data privacy protection in data publishing.…”

Section: Related Workmentioning

confidence: 99%

A novel ε-sensitive correlation indistinguishable scheme for publishing location data

Wang

Zhang

2019

PLoS ONE

View full text Add to dashboard Cite

Nowadays, location based service (LBS) is one of the most popular mobile apps and following with humongous of location data been produced. The publishing of location data can provide benefit for promoting the quality of service, optimizing the commercial environment as well as harmonizing the infrastructure construction. However, as location data may contain some sensitive or confidential information, the publishing may reveal privacy and bring hazards. So the published data had to be disposed to protect the privacy. In order to cope with this problem, a number of algorithms based on the strategy of k-anonymity were proposed, but this is not enough for the privacy protection, as the correlation between the sensitive region and the background knowledge can be used to infer the real location. Thus, consider about this condition, in this paper a ε-sensitive correlation privacy protection scheme is proposed, and provides correlation indistinguishable to the location data. In this scheme, entropy is first used to determine the location centroid of each cell to build up the voronoi diagram. Then the coordinate of the untreated location data that is located in the cell is transferred into the centroid vicinity. Accordingly, the sensitive correlation is destroyed by the coordinate of each published data. The process of transferring the location data is determined by metrics of ε-sensitive correlation privacy, and is rigorous in mathematical justification. At last, security analysis is proposed in this paper to verify the privacy ability of our proposed algorithm based on voronoi diagram and entropy, and then we utilize the comparative experiment to further affirm the advantage of this algorithm in the location data privacy protection as well as the availability of published data.

show abstract

Achieving differential privacy of trajectory data publishing in participatory sensing

Cited by 82 publications

References 7 publications

Risk-Aware Individual Trajectory Data Publishing With Differential Privacy

Risk-Aware Individual Trajectory Data Publishing With Differential Privacy

Sensitive attribute privacy preservation of trajectory data publishing based on l-diversity

A novel ε-sensitive correlation indistinguishable scheme for publishing location data

Contact Info

Product

Resources

About