Author(s)

ShanLin Yu, Hui Wang^*

Affiliation(s)

School of Computerscience and Technology, Henan Polytechnic University, Jiaozuo 454003, Henan, China.

Corresponding Author

Hui Wang

ABSTRACT

Aiming at the problems of being vulnerable to semantic attacks and having low data availability in the current trajectory data privacy protection schemes, a trajectory differential privacy protection scheme based on semantic location clustering is proposed. Firstly, the semantic distances between various positioning points in the trajectory are estimated by sorting out the logical relationships of different semantic concepts. Then, the clustering algorithm is used to generate clustering results with members having high semantic similarity for the trajectory data set as anonymous sets. Secondly, the differential privacy exponential mechanism is utilized to select representative positions with a lower possibility of privacy leakage from the clustering results to anonymize the sensitive points in the original trajectory, which achieves good privacy protection effects while avoiding large information losses.

KEYWORDS

Semantic distance; Location clustering; Differential privacy; Privacy protection

CITE THIS PAPER

ShanLin Yu, Hui Wang. Trajectory differential privacy protection mechanism based on semantic location clustering. World Journal of Information Technology. 2024, 2(3): 49-53. DOI: https://doi.org/10.61784/wjit3013.

REFERENCES

[1] Zhang Qingyun, Zhang Xing, Li Wanjie, et al. Overview of location trajectory privacy protection technology based on LBS system. Application Research of Computers, 2020, 37(12): 3534-3544.

[2] Cunningham T, Cormode G, Ferhatosmanoglu H, et al. Real-world trajectory sharing with local differential privacy[J]. Proceedings of the VLDB Endowment, 2021, 14(11): 2283-2295.

[3] Zheng Zhirun, Li Zhetao, Jiang Hongbo, et al. Semantic-Aware Privacy-Preserving Online Location Trajectory Data Sharing. IEEE Trans on information forensics and security, 2022, 17: 2256-2271.

[4] Liu Peiqian, Jia Qinglin, Wang Hui, et al. Differential privacy trajectory privacy protection scheme based on user correlation. Application Research of Computers, 2024, 41(7): 2189-2194.

[5] Kim J W, Jang B. Deep learning-based privacy-preserving framework for synthetic trajectory generation. Journal of network and computer applications, 2022, 206: 103459.

[6] Wen Ruxue, Cheng Wenqing, Huang Haojun, et al. Privacy Preserving Trajectory Data Publishing with Personalized Differential Privacy\\ Proc of IEEE Intl Conf on ISPA/BDCloud/SocialCom/SustainCom. Exeter, United Kingdom: IEEE Press, 2020: 313-320. DOI: 10.1109/ISPA-BDCloud-SocialCom-SustainCom51426.2020.00065.

[7] Zhang Jing, Li Yanzi, Ding Qian, et al. Successive Trajectory Privacy Protection with Semantics Prediction Differential Privacy. Entropy, 2022, 24(9): 1172.

[8] Hua Jingyu, Gao Yue, Zhong Sheng. Differentially private publication of general time-serial trajectory data// Proc of IEEE INFOCOM. Hong Kong, China: IEEE Press, 2015: 549-557. DOI: 10.1109/INFOCOM.2015.7218422.

[9] Zhao Xiaodong, Pi Dechang, Chen Junfu. Novel trajectory privacy-preserving method based on clustering using differential privacy. Expert Systems with Applications, 2020, 149: 113241.

[10] Ma Tinghuai, Song Fagen. A Trajectory Privacy Protection Method Based on Random Sampling Differential Privacy. ISPRS International Journal of Geo-Information, 2021, 10(7): 454.

[11] Gu Zhen, Zhang Guoyin. Trajectory Data Publication Based on Differential Privacy. International Journal of Information Security and Privacy, 2023,17(1): 1-15.

[12] Guo Kun, Wang Dongbin, Zhi Hui, et al. Privacy-preserving Trajectory Generation Algorithm Considering Utility based on Semantic Similarity Awareness// Proc of IEEE International Conference on Communications. Seoul, Korea: IEEE Press, 2022: 992-997. DOI: 10.1109/ICC45855.2022.9838628.

[13] Cheng Wenqing, Wen Ruxue, Huang Haojun, et al. OPTDP: Towards optimal personalized trajectory differential privacy for trajectory data publishing. Neurocomputing, 2022, 472: 201-211.

[14] Li Meng, Zhu Liehuang, Zhang Zijian, et al. Achieving differential privacy of trajectory data publishing in participatory sensing. Information sciences, 2017, 400-401: 1-13.

[15] Gao Zhigang, Huang Yucai, Zheng Leilei, et al. Protecting Location Privacy of Users Based on Trajectory Obfuscation in Mobile Crowdsensing. IEEE Trans on industrial informatics, 2022, 18(9): 1.