A V2X-based Privacy Preserving Federated Measuring and Learning System (2401.13848v1)
Abstract: Future autonomous vehicles (AVs) will use a variety of sensors that generate a vast amount of data. Naturally, this data not only serves self-driving algorithms; but can also assist other vehicles or the infrastructure in real-time decision-making. Consequently, vehicles shall exchange their measurement data over Vehicle-to-Everything (V2X) technologies. Moreover, predicting the state of the road network might be beneficial too. With such a prediction, we might mitigate road congestion, balance parking lot usage, or optimize the traffic flow. That would decrease transportation costs as well as reduce its environmental impact. In this paper, we propose a federated measurement and learning system that provides real-time data to fellow vehicles over Vehicle-to-Vehicle (V2V) communication while also operating a federated learning (FL) scheme over the Vehicle-to-Network (V2N) link to create a predictive model of the transportation network. As we are yet to have real-world AV data, we model it with a non-IID (independent and identically distributed) dataset to evaluate the capabilities of the proposed system in terms of performance and privacy. Results indicate that the proposed FL scheme improves learning performance and prevents eavesdropping at the aggregator server side.
- “Gradient-based learning applied to document recognition” In Proc. of the IEEE 86.11, 1998, pp. 2278–2324 DOI: —non-IID— & $163$ & $98.45%$ & 10.0 “—data exchange— & $143$ & $98.65%$ & 1.1“ “hline 10.1109/5.726791
- Swaroop Darbha, Shyamprasad Konduri and Prabhakar R. Pagilla “Benefits of V2V Communication for Autonomous and Connected Vehicles” In IEEE Trans. on Intelligent Transportation Systems 20.5, 2019, pp. 1954–1963 DOI: 10.1109/TITS.2018.2859765
- Anis Boubarki and Sonia Mettali Gammar “Intra-Platoon Communication in Autonomous Vehicle: A survey” In 2020 9th IFIP Int. Conf. on Performance Evaluation and Modeling in Wireless Networks (PEMWN), Dec. 1–3, 2020, Berlin, Germany, pp. 1–6 DOI: 10.23919/PEMWN50727.2020.9293086
- Elnaz Namazi, Jingyue Li and Chaoru Lu “Intelligent Intersection Management Systems Considering Autonomous Vehicles: A Systematic Literature Review” In IEEE Access 7, 2019, pp. 91946–91965 DOI: 10.1109/ACCESS.2019.2927412
- “Value-Anticipating V2V Communications for Cooperative Perception” In 2019 IEEE Intelligent Vehicles Symposium (IV), 2019, pp. 1947–1952 DOI: 10.1109/IVS.2019.8814110
- “A Survey of Security and Privacy Issues in V2X Communication Systems” In ACM Comput. Surv. 55.9 New York, NY, USA: Association for Computing Machinery, 2023 DOI: 10.1145/3558052
- “Privacy and safety improvement of VANET data via a safety-related privacy scheme” In International Journal of Information Security, 2023 DOI: 10.1007/s10207-023-00662-6
- “Location Entropy-Based Privacy Protection Algorithm for Social Internet of Vehicles” In Wireless Personal Communications Springer ScienceBusiness Media LLC, 2023 DOI: 10.1007/s11277-023-10413-4
- “Communication-Efficient Learning of Deep Networks from Decentralized Data” In Proc. of the 20th Int. Conf. on Artificial Intelligence and Statistics (AISTATS) 2017. 54 Fort Lauderdale, FL, USA: PMLR, 2017, pp. 1273–1282
- “Federated Learning Framework Coping with Hierarchical Heterogeneity in Cooperative ITS” In 2022 IEEE 25th Int. Conf. on Intelligent Transportation Systems (ITSC), 2022, pp. 3502–3508 DOI: 10.1109/ITSC55140.2022.9922064
- “Joint resource management for mobility supported federated learning in Internet of Vehicles” In Future Generation Computer Systems 129, 2022, pp. 199–211 DOI: 10.1016/j.future.2021.11.020
- Xuefei Yin, Yanming Zhu and Jiankun Hu “A Comprehensive Survey of Privacy-Preserving Federated Learning: A Taxonomy, Review, and Future Directions” In ACM Computing Surveys, July 2022, 54.6, 2021, pp. 1–36 DOI: 10.1145/3460427
- Waleed Yamany, Nour Moustafa and Benjamin Turnbull “OQFL: An Optimized Quantum-Based Federated Learning Framework for Defending Against Adversarial Attacks in Intelligent Transportation Systems” In IEEE Trans. on Intelligent Transportation Systems 24.1, 2023, pp. 893–903 DOI: 10.1109/TITS.2021.3130906
- Levente Alekszejenkó and Tadeusz P. Dobrowiecki “The Conceptual Framework of a Privacy-Aware Federated Data Collecting and Learning System” doi: 10.3311/MINISY2022-013 In Proc. of the 29th MINISY@DMIS, Budapest, Hungary, Feb. 7–8, 2022, 2022, pp. 50–53
- “Towards an Efficient, Privacy-aware Federated Learning Scheme” Preprint (Version 1) available at Research Square; doi: 10.21203/rs.3.rs-2072660/v1, 2022
- “Securing Connected & Autonomous Vehicles: Challenges Posed by Adversarial Machine Learning and the Way Forward” In IEEE Communications Surveys & Tutorials 22.2, 2020, pp. 998–1026 DOI: 10.1109/COMST.2020.2975048
- “BDFL: A Byzantine-Fault-Tolerance Decentralized Federated Learning Method for Autonomous Vehicle” In IEEE Trans. Veh. Technol. 70.9, 2021, pp. 8639–8652 DOI: 10.1109/TVT.2021.3102121
- “Data-Driven Federated Autonomous Driving” In Mobile Web and Intelligent Information Systems, Lecture Notes in Computer Science Cham: Springer Int. Pub., 2022, pp. 79–90 DOI: 10.1007/978-3-031-14391-5“˙6
- “Efficient Decentralized Deep Learning by Dynamic Model Averaging” In Machine Learning and Knowledge Discovery in Databases, Lecture Notes in Computer Science Cham: Springer Int. Pub., 2019, pp. 393–409 DOI: 10.1007/978-3-030-10925-7“˙24
- G. Koehler, A. Amantini and P. Markovics “MNIST Handwritten Digit Recognition in PyTorch” [Online, accessed 12-September-2022], 2020 URL: https://nextjournal.com/gkoehler/pytorch-mnist
- “Flower: A Friendly Federated Learning Research Framework” In arXiv preprint, 2020 DOI: 10.48550/arXiv.2007.14390
- “Federated Optimization in Heterogeneous Networks” In arXiv preprint, 2020 DOI: 10.48550/arXiv.1812.06127
- “SCAFFOLD: Stochastic Controlled Averaging for Federated Learning” In arXiv preprint, 2021 DOI: 10.48550/arXiv.1910.0637
- “A Novel Framework for the Analysis and Design of Heterogeneous Federated Learning” In IEEE Trans. on Signal Processing 69, 2021, pp. 5234–5249 DOI: 10.1109/TSP.2021.3106104
- Levente Alekszejenkó (1 paper)
- Tadeusz Dobrowiecki (1 paper)