摘要With the development of networked vehicles, location information-based transportation systems have proven to provide significant benefits. However, the exposure of vehicle location information also raises important privacy issues. Current typical methods for protecting vehicle location privacy protection methods such as anonymity and pseudonymity, still carry the risk of the vehicle being tracked, leading to data security issues. This paper proposes a kind of vehicle trajectory generation algorithm based on Generative Adversarial Networks (GAN). The algorithm utilizes vehicle movement trajectory data to train both the discriminator and generator models to generate virtual trajectory data that matches the distribution of real trajectory data. Therefore, virtual trajectory data can obscure vehicle information, addressing the privacy concerns associated with moving trajectory data and enhancing the security of applications. In this paper, the vehicle travel time of sample trajectory data and virtual trajectory data is used as indicators for statistical analysis. The experiment demonstrated that the cumulative probability distribution of travel time for the sample data and virtual data passed the Kolmogorov-Smirnov (K-S) test at permeabilities ranging from 10% to 100% and at significance levels of 0.01 and 0.05. Both datasets accepted the hypothesis that they originate from the same distribution. The reliability of the proposed method for generating virtual trajectories has been demonstrated.
Abstract：With the development of networked vehicles, location information-based transportation systems have proven to provide significant benefits. However, the exposure of vehicle location information also raises important privacy issues. Current typical methods for protecting vehicle location privacy protection methods such as anonymity and pseudonymity, still carry the risk of the vehicle being tracked, leading to data security issues. This paper proposes a kind of vehicle trajectory generation algorithm based on Generative Adversarial Networks (GAN). The algorithm utilizes vehicle movement trajectory data to train both the discriminator and generator models to generate virtual trajectory data that matches the distribution of real trajectory data. Therefore, virtual trajectory data can obscure vehicle information, addressing the privacy concerns associated with moving trajectory data and enhancing the security of applications. In this paper, the vehicle travel time of sample trajectory data and virtual trajectory data is used as indicators for statistical analysis. The experiment demonstrated that the cumulative probability distribution of travel time for the sample data and virtual data passed the Kolmogorov-Smirnov (K-S) test at permeabilities ranging from 10% to 100% and at significance levels of 0.01 and 0.05. Both datasets accepted the hypothesis that they originate from the same distribution. The reliability of the proposed method for generating virtual trajectories has been demonstrated.
HE Zhong-he, SHAO Ren-chi, XIANG Si-jia. Vehicle Trajectory Generation Based on Generation Adversarial Network[J]. Journal of Highway and Transportation Research and Development, 2024, 18(2): 82-88.
HE Zhong-he, SHAO Ren-chi, XIANG Si-jia. Vehicle Trajectory Generation Based on Generation Adversarial Network. Journal of Highway and Transportation Research and Development, 2024, 18(2): 82-88.
[1] ZHU N, LIU Y, MA S F, et al. Mobile Traffic Sensor Routing in Dynamic Transportation Systems[J]. IEEE Transactions. Intelligent Transportation Systems, 2014, 15(5):2273-2285. [2] VACA M, TRAVER J E, MILANES V, et al. Automated Global Planner for Cybernetic Transportation Systems[C]//2016 14th International Conference on Control, Automation, Robotics and Vision (ICARCV). Piscataway:IEEE, 2016:1-6. [3] XIAO Z, CHEN Y X, ALAZAB M, et al. Trajectory Data Acquisition via Private Car Positioning Based on Tightly-coupled GPS/OBD Integration in Urban Environments[J]. IEEE Transactions on Intelligent Transportation Systems, 2021, 23(7):9680-9691. [4] HE W, HWANG K, LI D Y. Intelligent Carpool Routing for Urban Ridesharing by Mining GPS Trajectories[J]. IEEE Transactions. Intelligent Transportation Systems, 2014, 15(5):2286-2296. [5] LI Z, PEI Q, MARKWOOD L, et al. Location Privacy Violation via GPS-Agnostic Smart Phone Car Tracking[J]. IEEE Transactions on Vehicular Technology, 2018, 67(6):5042-5053. [6] ZHANG S, TAO J YUAN Y. Anonymous Authentication-Oriented Vehicular Privacy Protection Technology Research in VANET[C]//2011 International Conference on Electrical and Control Engineering. Piscataway:IEEE, 2011:4365-4368. [7] WANG J B, CAI Z P, YU J G. Achieving Personalized k-Anonymity-Based Content Privacy for Autonomous Vehicles in CPS[J]. IEEE Transactions on Industrial Informatics, 2020, 16(6):4242-4251. [8] ECKHOFF D, SOMMER C. Driving for Big Data? Privacy Concerns in Vehicular Networking[J]. IEEE Security&Privacy, 2014, 12(1):77-79. [9] HAMIDA E B, NOURA H, ZNAIDI W. Security of Cooperative Intelligent Transport Systems:Standards, Threats Analysis and Cryptographic Countermeasures[J]. Electronics, 2015, 4(3):380-423. [10] ZHANG Z X, FENG T Y, SIKDAR B, et al. A Flickering Context-based Mix Strategy for Privacy Protection in VANETs[C]//ICC 2021-IEEE International Conference on Communications. Piscataway:IEEE, 2021:1-6. [11] SAMPIGETHAYA K, LI M Y, HUANG L P, et al. AMOEBA:Robust Location Privacy Scheme for VANET[J]. IEEE Journal on Selected Areas in Communications, 2007, 25(8):1569-1589. [12] LU R X, LIN X D, LUAN T H, et al. Anonymity Analysis on Social Spot Based Pseudonym Changing for Location Privacy in VANETs[C]//2011 IEEE International Conference on Communications (ICC). Piscataway:IEEE, 2011:1-5. [13] MEMON I, ALI Q, ZUBEDI A, et al. DPMM:Dynamic Pseudonym-Based Multiple Mix-Zones Generation for Mobile Traveler[J]. Multimedia Tools&Applications, 2017, 76(22):24359-24388. [14] LU Z J, QU G LIU Z L. A Survey on Recent Advances in Vehicular Network Security, Trust, and Privacy[J]. IEEE Transactions on Intelligent Transportation Systems, 2019, 20(2):760-776. [15] BOUALOUACHE A, SENOUCI S, MOUSSAOUI S. A Survey on Pseudonym Changing Strategies for Vehicular Ad-Hoc Networks[J]. IEEE Communications Surveys and Tutorials, 2018, 20(1):770-790. [16] SAXENA A S, BERA D, GOYAL V. Modeling Location Obfuscation for Continuous Query[J]. Journal of Information Security and Applications, 2019, 44(FEB):130-143. [17] SHAHID A R, PISSINOU N, IYENGAR S S, et al. KLAP for Real-World Protection of Location Privacy[C]//2018 IEEE World Congress on Services (SERVICES). Piscataway:IEEE, 2018:17-18. [18] LIU Y, YU J J Q, KANG J, et al. Privacy-Preserving Traffic Flow Prediction:A Federated Learning Approach[J]. IEEE Internet of Things Journal, 2020, 7(8):7751-7763. [19] MA Z, ZHANG T, LIU X, et al. Real-Time Privacy-Preserving Data Release over Vehicle Trajectory[J]. IEEE Transactions on Vehicular Technology, 2019, 68(8):8091-8102. [20] YU H L, LI G S, WU J H, et al. A Location-Based Path Privacy Protection Scheme in Internet of Vehicles[C]//IEEE INFOCOM 2020-IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS). Piscataway:IEEE, 2020:665-670. [21] ZHENG W B, WANG K F, WANG F Y. Background Subtraction Algorithm Based on Bayesian Generative Adversarial Network[J]. Acta Automatica Sinica, 2018, 44(5):878-890. [22] MURPHY K P. Dynamic Bayesian Networks:Representation, Inference and Learning[D]. Berkeley:University of California, 2002. [23] SUN Z B, ZAN B, BAN X G, et al. Privacy Protection Method for Fine-Grained Urban Traffic Modeling Using Mobile Sensors[J]. Transportation Research Part B:Methodological, 2013, 56:50-69.
2024, Vol. 18 
