With the widespread application of location-based services, how to effectively publish trajectories while preserving users' privacy has become a critical challenge. Existing privacy-preserving trajectory publishing methods often face issues such as missing in synthetic trajectories, low data utility, and privacy leakage of users' social relationships due to trajectory correlation. To address these issues, a differentially private trajectory publishing method based on feature extraction and trajectory correlation (DP-FETC) is proposed in this paper. The method is composed of two synergistic core algorithms. First, a trajectory synthesis algorithm (SynFE) employs adaptive grid discretization to extract key statistical features—including weighted location, origin-destination (OD), and length distributions—to generate high-fidelity synthetic trajectories that maintain high data utility. Second, to mitigate the risk of social relationship disclosure, an innovative correlated trajectory protection algorithm (PreOD) identifies highly correlated trajectories using a novel metric based on stay duration at points of interest. It then applies a targeted perturbation exclusively to the OD points of these high-risk trajectories. This strategy effectively obscures social links while minimizing the impact on overall data quality. Experimental results on two real-world datasets validate that the proposed method has good data utility while providing robust privacy guarantees.
Citation: Bin Yue, Shuyu Li, Anyu Liu, Xiongfei Li. DP-FETC: a differentially private trajectory publishing method based on feature extraction and trajectory correlation[J]. Electronic Research Archive, 2025, 33(11): 6631-6651. doi: 10.3934/era.2025293
With the widespread application of location-based services, how to effectively publish trajectories while preserving users' privacy has become a critical challenge. Existing privacy-preserving trajectory publishing methods often face issues such as missing in synthetic trajectories, low data utility, and privacy leakage of users' social relationships due to trajectory correlation. To address these issues, a differentially private trajectory publishing method based on feature extraction and trajectory correlation (DP-FETC) is proposed in this paper. The method is composed of two synergistic core algorithms. First, a trajectory synthesis algorithm (SynFE) employs adaptive grid discretization to extract key statistical features—including weighted location, origin-destination (OD), and length distributions—to generate high-fidelity synthetic trajectories that maintain high data utility. Second, to mitigate the risk of social relationship disclosure, an innovative correlated trajectory protection algorithm (PreOD) identifies highly correlated trajectories using a novel metric based on stay duration at points of interest. It then applies a targeted perturbation exclusively to the OD points of these high-risk trajectories. This strategy effectively obscures social links while minimizing the impact on overall data quality. Experimental results on two real-world datasets validate that the proposed method has good data utility while providing robust privacy guarantees.
| [1] | D. Wang, T. Miwa, T. Morikawa, Big trajectory data mining: A survey of methods, applications, and services, Sensors, 20 (2020), 4571. https://doi.org/10.3390/s20164571 |
| [2] |
X. F. Xiao, C. H. Li, X. J. Wang, A. P. Zeng, Personalized tourism recommendation model based on temporal multilayer sequential neural network, Sci. Rep., 15 (2025), 382. https://doi.org/10.1038/s41598-024-84581-z doi: 10.1038/s41598-024-84581-z
|
| [3] |
X. Wang, Z. Jerome, Z. Wang, C. Zhang, S. Shen, V. V. Kumar, et al., Traffic light optimization with low penetration rate vehicle trajectory data, Nat. Commun., 15 (2024), 1306. https://doi.org/10.1038/s41467-024-45427-4 doi: 10.1038/s41467-024-45427-4
|
| [4] |
B. Benreguia, H. Moumen, M. A. Merzoug, Tracking COVID-19 by tracking infectious trajectories, IEEE Access, 8 (2020), 145242–145255. https://doi.org/10.1109/ACCESS.2020.3015002 doi: 10.1109/ACCESS.2020.3015002
|
| [5] |
S. Wang, Z. Bao, J. S. Culpepper, G. Cong, A survey on trajectory data management, analytics, and learning, ACM Comput. Surv., 54 (2021), 1–36. https://doi.org/10.1145/3440207 doi: 10.1145/3440207
|
| [6] |
F. Jin, W. Hua, M. Francia, P. Chao, M. E. Orlowska, X. Zhou, A survey and experimental study on privacy-preserving trajectory data publishing, IEEE Trans. Knowl. Data Eng., 35 (2023), 5577–5596. https://doi.org/10.1109/TKDE.2022.3174204 doi: 10.1109/TKDE.2022.3174204
|
| [7] | Y. Zhan, H. Haddadi, A. Kyllo, A. Mashhadi, Privacy-aware human mobility prediction via adversarial networks, in 2022 2nd International Workshop on Cyber-Physical-Human System Design and Implementation (CPHS), (2022), 7–12. https://doi.org/10.1109/CPHS56133.2022.9804533 |
| [8] |
À. Miranda-Pascual, P. Guerra-Balboa, J. Parra-Arnau, J. Forné, T. Strufe, SoK: Differentially private publication of trajectory data, Proc. Priv. Enhancing Technol., 2023 (2023), 438–457. https://doi.org/10.56553/popets-2023-0065 doi: 10.56553/popets-2023-0065
|
| [9] | R. Bhadani, A survey on differential privacy for spatiotemporal data in transportation research, preprint, arXiv: 2407.15868. https://doi.org/10.48550/arXiv.2407.15868 |
| [10] | M. E. Andrés, N. E. Bordenabe, K. Chatzikokolakis, C. Palamidessi, Geo-indistinguishability: Differential privacy for location-based systems, in Proceedings of the 2013 ACM SIGSAC Conference on Computer & Communications Security, (2013), 901–914. https://doi.org/10.1145/2508859.2516735 |
| [11] | N. Wang, M. Kankanhalli, Dptraj-pm: Differentially private trajectory synthesis using prefix tree and markov process, preprint, arXiv: 2404.14106. https://doi.org/10.48550/arXiv.2404.14106 |
| [12] | Y. Jiang, Y. Wu, S. Zhang, J. J. Q. Yu, Fedvae: Trajectory privacy preserving based on federated variational autoencoder, in 2023 IEEE 98th Vehicular Technology Conference (VTC2023-Fall), (2023), 1–7. https://doi.org/10.1109/VTC2023-Fall60731.2023.10333794 |
| [13] | E. Buchholz, A. Abuadbba, S. Wang, S. Nepal, S. S. Kanhere, Reconstruction attack on differential private trajectory protection mechanisms, in Proceedings of the 38th Annual Computer Security Applications Conference, (2022), 279–292. https://doi.org/10.1145/3564625.3564628 |
| [14] |
R. Shokri, G. Theodorakopoulos, C. Troncoso, Privacy games along location traces: A game-theoretic framework for optimizing location privacy, ACM Trans. Priv. Secur., 19 (2016), 1–31. https://doi.org/10.1145/3009908 doi: 10.1145/3009908
|
| [15] | J. Long, T. Chen, G. Ye, K. Zheng, Q. V. H. Nguyen, H. Yin, Physical trajectory inference attack and defense in decentralized poi recommendation, in Proceedings of the ACM Web Conference 2024, (2024), 3379–3387. https://doi.org/10.1145/3589334.3645410 |
| [16] | Y. Yu, H. Zhu, M. Xie, CTP: Correlated trajectory publication with differential privacy, in 2021 IEEE 6th International Conference on Computer and Communication Systems (ICCCS), (2021), 128–133. https://doi.org/10.1109/ICCCS52626.2021.9449263 |
| [17] |
L. Wu, C. Qin, Z. Xu, Y. Guan, R. Lu, TCPP: Achieving privacy-preserving trajectory correlation with differential privacy, IEEE Trans. Inf. Forensics Secur., 18 (2023), 4006–4020. https://doi.org/10.1109/TIFS.2023.3290486 doi: 10.1109/TIFS.2023.3290486
|
| [18] |
Z. Zheng, Z. Li, J. Li, H. Jiang, T. Li, B. Guo, Utility-aware and privacy-preserving trajectory synthesis model that resists social relationship privacy attacks, ACM Trans. Intell. Syst. Technol., 13 (2022), 1–28. https://doi.org/10.1145/3495160 doi: 10.1145/3495160
|
| [19] |
H. Yuan, L. Wu, L. Xu, L. Ban, H. Wang, Y. Su, L. Ban, H. Wang, Y. Su, et al., SCTP: Achieving semantic correlation trajectory privacy-preserving with differential privacy, IEEE Trans. Veh. Technol., 74 (2025), 5856–5870. https://doi.org/10.1109/TVT.2024.3505200 doi: 10.1109/TVT.2024.3505200
|
| [20] |
L. Kuang, W. Shi, X. Chen, J. Zhang, H. Liao, A location semantic privacy protection model based on spatial influence, Sci. Rep., 15 (2025), 15227. https://doi.org/10.1038/s41598-025-88553-9 doi: 10.1038/s41598-025-88553-9
|
| [21] |
D. Liu, G. Yu, Y. Ding, Z. Zhong, C. Wang, Privacy preserving multi-party computation with secret sharing for trajectory prediction in vanets, IEEE Trans. Veh. Technol., 2024 (2024). https://doi.org/10.1109/TVT.2024.3432614 doi: 10.1109/TVT.2024.3432614
|
| [22] | C. Dwork, Differential privacy: A survey of results, in International Conference on Theory and Applications of Models of Computation, (2008), 1–19. https://doi.org/10.1007/978-3-540-79228-4_1 |
| [23] |
S. Li, Y. Geng, Y. Li, A Differentially private hybrid decomposition algorithm based on quad-tree, Comput. Secur., 109 (2021), 102384. https://doi.org/10.1016/j.cose.2021.102384 doi: 10.1016/j.cose.2021.102384
|
| [24] |
X. Du, H. Zhu, Y. Zheng, R. Lu, F. Wang, H. Li, A semantic-preserving scheme to trajectory synthesis using differential privacy, IEEE Internet Things J., 10 (2023), 13784–13797. https://doi.org/10.1109/JIOT.2023.3262964 doi: 10.1109/JIOT.2023.3262964
|
| [25] | Y. Zhu, Y. Hong, Q. Xue, X. Lan, Y. Zhang, Y. Xiang, LDGI: Location-discriminative geo-indistinguishability for location privacy, IEEE Trans. Knowl. Data Eng., 37 (2024). https://doi.org/10.1109/TKDE.2024.3522320 |
| [26] |
S. Ghane, L. Kulik, K. Ramamohanarao, TGM: A generative mechanism for publishing trajectories with differential privacy, IEEE Internet Things J., 7 (2020), 2611–2621. https://doi.org/10.1109/JIOT.2019.2943719 doi: 10.1109/JIOT.2019.2943719
|
| [27] |
X. Sun, Q. Ye, H. Hu, J. Duan, Q. Xue, T. Wo, et al., Puts: Privacy-preserving and utility-enhancing framework for trajectory synthesization, IEEE Trans. Knowl. Data Eng., 36 (2024), 296–310. https://doi.org/10.1109/TKDE.2023.3288154 doi: 10.1109/TKDE.2023.3288154
|
| [28] |
X. Sun, Q. Ye, H. Hu, Y. Wang, K. Huang, T. Wo, Synthesising realistic trajectory data with differential privacy, IEEE Trans. Intell. Transp. Syst., 24 (2023), 5502–5515. https://doi.org/10.1109/TITS.2023.3241290 doi: 10.1109/TITS.2023.3241290
|
| [29] | Y. Du, Y. Hu, Z. Zhang, Z. Fang, L. Chen, B. Zheng, et al., Ldptrace: Locally differentially private trajectory synthesis, preprint, arXiv: 2302.06180. https://doi.org/10.48550/arXiv.2302.06180 |
| [30] | G. S. Watson, Fiducial inference, J. R. Stat. Soc. Ser. B, 39 (1977), 319–321. |
| [31] | R. A. Davis, K. S. Lii, D. N. Politis, Remarks on some nonparametric estimates of a density function, in Selected Works of Murray Rosenblatt, Springer, (2011), 95–100. https://doi.org/10.1007/978-1-4419-8339-8_13 |
| [32] | Y. Zheng, X. Xie, W. Y. Ma, GeoLife: A collaborative social networking service among user, location and trajectory, IEEE Data Eng. Bull., 33 (2010), 32–39. |
| [33] |
L. Moreira-Matias, J. Gama, M. Ferreira, J. Mendes-Moreira, L. Damas, Predicting taxi-passenger demand using streaming data, IEEE Trans. Intell. Transp. Syst., 14 (2013), 1393–1402. https://doi.org/10.1109/TITS.2013.2262376 doi: 10.1109/TITS.2013.2262376
|
| [34] |
J. Li, W. Chen, A. Liu, Z. Li, L. Zhao, FTS: A feature-preserving trajectory synthesis model, Geoinformatica, 22 (2018), 49–70. https://doi.org/10.1007/s10707-017-0301-6 doi: 10.1007/s10707-017-0301-6
|
| [35] |
X. Wang, X. Liu, Z. Lu, H. Yang, Large scale GPS trajectory generation using map based on two stage GAN, J. Data Sci., 19 (2021), 126–141. https://doi.org/10.6339/21-JDS1004 doi: 10.6339/21-JDS1004
|
| [36] |
J. Zhang, Q. Huang, Y. Huang, Q. Ding, P. W. Tsai, Dp-trajgan: A privacy-aware trajectory generation model with differential privacy, Future Gener. Comput. Syst., 142 (2023), 25–40. https://doi.org/10.1016/j.future.2022.12.027 doi: 10.1016/j.future.2022.12.027
|
| [37] | V. Kulkarni, B. Garbinato, Generating synthetic mobility traffic using RNNs, in Proceedings of the 1st Workshop on Artificial Intelligence and Deep Learning for Geographic Knowledge Discovery, (2017), 1–4. https://doi.org/10.1145/3149808.3149809 |
Figures(6) / Tables(1)
Bin Yue, Shuyu Li, Anyu Liu, Xiongfei Li. DP-FETC: a differentially private trajectory publishing method based on feature extraction and trajectory correlation[J]. Electronic Research Archive, 2025, 33(11): 6631-6651. doi: 10.3934/era.2025293
DownLoad: