[1]阎红灿,赵雨婷,李思佳,等.基于 BiLSTM-GAN 的轨迹隐私保护模型[J].郑州大学学报(工学版),2027,48(XX):1-8.[doi:10.13705/j.issn.1671-6833.2026.04.015]
　YAN Hongcan,ZHAO Yuting,LI Sijia,et al.Trajectory Privacy Protection Model Based on BiLSTM-GAN[J].Journal of Zhengzhou University (Engineering Science),2027,48(XX):1-8.[doi:10.13705/j.issn.1671-6833.2026.04.015]
点击复制

基于 BiLSTM-GAN 的轨迹隐私保护模型()
分享到：

《郑州大学学报(工学版)》[ISSN:1671-6833/CN:41-1339/T]

卷:
48
期数:
2027年XX
页码:
1-8
栏目:
出版日期:
2027-12-10

文章信息/Info

Title:
Trajectory Privacy Protection Model Based on BiLSTM-GAN
作者:
阎红灿 1,2 , 赵雨婷 1 , 李思佳 3 , 辛禹池1
1. 华北理工大学 理学院,河北 唐山 063210;2. 河北省数据科学与应用重点实验室,河北 唐山 063210;3. 中国人民警察大学 网络舆情研究中心,河北 廊坊 065000
Author(s):
YAN Hongcan1,2, ZHAO Yuting1, LI Sijia3, XIN Yuchi1
1. College of Science, North China University of Science and Technology, Tangshan 063210, China; 2. Hebei Province Key Laboratory of Data Science and Application, Tangshan 063210, China; 3. Research Center for Network Public Opinion Governance, China People′s Police University, Langfang 065000
关键词:
轨迹保护;  基于层次密度的含噪声应用空间聚类;  双向长短期记忆网络;  生成对抗网络;  隐马尔可夫模型;  轨迹相似度
Keywords:
trajectory protection;  hierarchical density-based spatial clustering of applications with noise (HDBSCAN);  bidirectional long short-term memory network (BiLSTM);  generative adversarial network (GAN);  hidden Markov model (HMM);  trajectory similarity
分类号:
TP309.2U495
DOI:
10.13705/j.issn.1671-6833.2026.04.015
文献标志码:
A
摘要:
基于位置的服务中，移动轨迹数据的指数级增长使得用户隐私泄露风险问题日益突出，亟需有效的隐私保护机制。为了在保障隐私的同时提升轨迹数据的可用性，构建基于BiLSTM-GAN的轨迹隐私保护模型TCI-BiGAN。利用贝叶斯优化方法实现基于层次密度的含噪声应用空间聚类（HDBSCAN）的自适应调参，提高数据处理效率，降低轨迹冗余度；将BiLSTM嵌入生成对抗网络的生成器和鉴别器，利用其上下文特征提取能力高效提取轨迹数据的时空特征，捕捉其依赖关系，使GAN生成轨迹与真实轨迹更为相似；通过多元离散型隐马尔可夫模型进行轨迹插值，提高数据的完整性和可用性。在Foursquare NYC和T-Drive两个真实数据集上，用户轨迹关联准确率分别降低至0.243、0.198，生成轨迹与真实轨迹的平均豪斯多夫距离分别降低至0.013、0.019。
Abstract:
The exponential growth of mobile trajectory data in location-based services has significantly increased the risk of user privacy leakage, making effective privacy protection mechanisms urgently necessary. To enhance the utility of trajectory data while ensuring privacy protection, a trajectory privacy protection model named TCI-BiGAN was constructed based on BiLSTM-GAN. The Bayesian optimization method was used to perform adaptive parameter tuning for hierarchical density-based spatial clustering of applications with noise(HDBSCAN), improving data processing efficiency and reducing trajectory redundancy. BiLSTM was embedded into both the generator and discriminator of the generative adversarial network to efficiently extract spatiotemporal features and capture dependencies of trajectory data through its contextual feature extraction capability, thereby enhancing the similarity between generated and real trajectories. A multivariate discrete hidden Markov model was applied for trajectory interpolation, increasing data completeness and utility. On the Foursquare NYC and T-Drive real-world datasets, the user trajectory linkage accuracy was reduced to 0.243 and 0.198, respectively, and the average Hausdorff distance between generated and real trajectories was decreased to 0.013 and 0.019, respectively.

参考文献/References:

[1] Liu Kai, Wang Jiaqin, Li Hantao. A review of vehicle trajectory prediction based on deep learning[J]. Journal of Zhengzhou University (Engineering Science), 2025, 46(5): 77-89. [刘凯, 汪佳琴, 李汉涛. 基于深度学习的车辆轨迹预测研究综述[J]. 郑州大学学报(工学版), 2025, 46(5): 77-89.]
[2] Li Wenxuan, Wu Hao, Li Changsong. Survey of semantics-based location privacy protection[J]. Journal of Computer Applications, 2023, 43(11): 3472-3483. [李雯萱, 吴昊, 李昌松. 基于语义的位置隐私保护综述[J]. 计算机应用, 2023, 43(11): 3472-3483.]
[3] Ashbrook D, Starner T. Using GPS to learn significant locations and predict movement across multiple users[J]. Personal and Ubiquitous Computing, 2003, 7(5): 275-286.
[4] Ester M, Kriegel H P, Sander J, et al. A density-based algorithm for discovering clusters in large spatial databases with noise[C]//Proceedings of the Second International Conference on Knowledge Discovery and Data Mining. New York: ACM, 1996: 226-231.
[5] Campello R J G B, Moulavi D, Sander J. Density-based clustering based on hierarchical density estimates[C]//Advances in Knowledge Discovery and Data Mining. Cham: Springer, 2013: 160-172.
[6] Yang Peiyu, Zhu Tongyu, Wan Xuejin, et al. Identifying significant places using multi-day call detail records[C]//Proceedings of the 2014 IEEE 26th International Conference on Tools with Artificial Intelligence. Piscataway: IEEE, 2014: 360-366.
[7] Shen Zihao, Tang Yuyu, Wang Hui, et al. Clustering and deep learning based trajectory privacy protection mechanism for Internet of Vehicles[J]. Journal of Zhejiang University (Engineering Science), 2024, 58(1): 20-28. [申自浩, 唐雨雨, 王辉, 等. 基于聚类和深度学习的车联网轨迹隐私保护机制[J]. 浙江大学学报(工学版), 2024, 58(1): 20-28.]
[8] Xu Zhenqiang, Wang Jiayao, Yang Weidong. Research progress in privacy-preserving techniques for trajectory publication[J]. Journal of Geomatics Science and Technology, 2018, 35(1): 87-93. [徐振强, 王家耀, 杨卫东. 面向轨迹数据发布的隐私保护技术研究进展[J]. 测绘科学技术学报, 2018, 35(1): 87-93.]
[9] Kim J W, Jang B. Deep learning-based privacy-preserving framework for synthetic trajectory generation[J]. Journal of Network and Computer Applications, 2022, 206: 103459.
[10] Pan Jiaji, Yang Jingkang, Liu Yining. Dummy trajectory generation scheme based on deep learning[C]//Cyberspace Safety and Security. Cham: Springer, 2019: 511-523.
[11] Liu Xi, Chen Hanzhou, Andris C. trajGANs: using generative adversarial networks for geo-privacy protection of trajectory data (vision paper)[EB/OL]. [2025-12-01]. https://ptal.io. github. io/lopas2018/papers/LoPaS2018_Liu.pdf.
[12] Rao Jinmeng, Gao Song, Kang Yuhao, et al. LSTM-TrajGAN: a deep learning approach to trajectory privacy protection[PP/OL]. V1. arXiv (2020-06-14)[2025-12-01]. https://doi.org/10.48550/arXiv.2006.10521.
[13] Choi S, Kim J, Yeo H. TrajGAIL: generating urban vehicle trajectories using generative adversarial imitation learning[J]. Transportation Research Part C: Emerging Technologies, 2021, 128: 103091.
[14] Wang Xingrui, Liu Xinyu, Lu Ziteng, et al. Large scale GPS trajectory generation using map based on two stage GAN[J]. Journal of Data Science, 2021: 126-141.
[15] Yang Jingkang, Yu Xiaobo, Meng Weizhi, et al. Dummy trajectory generation scheme based on generative adversarial networks[J]. Neural Computing and Applications, 2023, 35(11): 8453-8469.
[16] Shin J, Song Yeji, Ahn J, et al. TCAC-GAN: synthetic trajectory generation model using auxiliary classifier generative adversarial networks for improved protection of trajectory data[C]//Proceedings of the 2023 IEEE International Conference on Big Data and Smart Computing (BigComp). Piscataway: IEEE, 2023: 314-315.
[17] Shin J, Song Yeji, Cheong Y Y, et al. Advanced trajectory privacy protection with attention mechanism and auxiliary classifier generative adversarial networks[C]//Proceedings of the 2024 International Conference on Information Networking (ICOIN). Piscataway: IEEE, 2024: 257-261.
[18] Douglas D H, Peucker T K. Algorithms for the reduction of the number of points required to represent a digitized line or its caricature[J]. Cartographica, 1973, 10(2): 112-122.
[19] Ma Shengjie, Wang Pei, Lee H. An enhanced hidden Markov model for map-matching in pedestrian navigation[J]. Electronics, 2024, 13(9): 1685.
[20] Huang Zhiheng, Xu Wei, Yu Kai. Bidirectional LSTM-CRF models for sequence tagging[PP/OL]. V1. arXiv (2015-08-09)[2025-12-01]. https://arxiv. org/abs/1508.01991.
[21] Goodfellow I J, Pouget-Abadie J, Mirza M, et al. Generative adversarial nets[C]//Proceedings of the 28th International Conference on Neural Information Processing Systems. New York: ACM, 2014: 2672-2680.
[22] Goodfellow I, Bengio Y, Courville A. Deep learning[M]. Cambridge, Mass.: MIT Press, 2016.
[23] Bishop C M. Pattern recognition and machine learning[M]. New York: Springer New York, 2006.
[24] Yang Dingqi, Zhang Daqing, Zheng V W, et al. Modeling user activity preference by leveraging user spatial temporal characteristics in LBSNs[J]. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 2015, 45(1): 129-142.
[25] Yuan Jing, Zheng Yu, Xie Xing, et al. Driving with knowledge from the physical world[C]//Proceedings of the 17th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York: ACM, 2011: 316-324.
[26] May Petry L, Leite Da Silva C, Esuli A, et al. MARC: a robust method for multiple-aspect trajectory classification via space, time, and semantic embeddings[J]. International Journal of Geographical Information Science, 2020, 34(7): 1428-1450.
[27] Huttenlocher D P, Klanderman G A, Rucklidge W J. Comparing images using the Hausdorff distance[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1993, 15(9): 850-863.
[28] Snoek J, Larochelle H, Adams R P. Practical Bayesian optimization of machine learning algorithms[J]. Advances in neural information processing systems. 2012, 4: 2960-2968.
[29] Bergstra J, Bengio Y. Random search for hyper-parameter optimization[J]. Journal of Machine Learning Research, 2012, 13: 281-305.
[30] Gao Song, Rao Jinmeng, Liu Xinyi, et al. Exploring the effectiveness of geomasking techniques for protecting the geoprivacy of Twitter users[J]. Journal of Spatial Information Science, 2019(19): 105-129.

备注/Memo

备注/Memo:
收稿日期:2026-03-05;修订日期:206-03-27
基金项目:河北省自然科学基金资助项目( G2024507002)
作者简介:阎红灿(1968— ) ,女,河北保定人,华北理工大学教授,博士,主要从事网络安全、大数据分析与安全研究,E-mail:yanhongcan@ncst.edu.cn。
更新日期/Last Update: 2026-04-08