Visible to the public A Semantic k-Anonymity Privacy Protection Method for Publishing Sparse Location Data

TitleA Semantic k-Anonymity Privacy Protection Method for Publishing Sparse Location Data
Publication TypeConference Paper
Year of Publication2019
AuthorsYang, Xudong, Gao, Ling, Wang, Hai, Zheng, Jie, Guo, Hongbo
Conference Name2019 Seventh International Conference on Advanced Cloud and Big Data (CBD)
Date PublishedSept. 2019
ISBN Number978-1-7281-5141-0
Keywordsanonymity, anonymous set, attacker, composability, compressed sensing, data privacy, diversity reception, Human Behavior, information science, k-anonymity, location based services, location information, location technology, location-based services, Metrics, missing location data, multiuser compressing sensing method, nonsensitive data, privacy disclosure, privacy leaks, privacy protection, pubcrawl, Publishing, resilience, Resiliency, semantic attacks, semantic k-anonymity privacy protection method, semantic privacy protection, semantic translation, Semantics, Sensors, sparse location data, Trajectory, user sensitive information

With the development of location technology, location-based services greatly facilitate people's life . However, due to the location information contains a large amount of user sensitive informations, the servicer in location-based services published location data also be subject to the risk of privacy disclosure. In particular, it is more easy to lead to privacy leaks without considering the attacker's semantic background knowledge while the publish sparse location data. So, we proposed semantic k-anonymity privacy protection method to against above problem in this paper. In this method, we first proposed multi-user compressing sensing method to reconstruct the missing location data . To balance the availability and privacy requirment of anonymity set, We use semantic translation and multi-view fusion to selected non-sensitive data to join anonymous set. Experiment results on two real world datasets demonstrate that our solution improve the quality of privacy protection to against semantic attacks.

Citation Keyyang_semantic_2019