DAG-based swarm learning: A secure asynchronous learning framework for Internet of Vehicles^☆

Abstract

To provide diversified services in the intelligent transportation systems, smart vehicles will generate unprecedented amounts of data every day. Due to data security and user privacy issues, Federated Learning (FL) is considered a potential solution to ensure privacy-preserving in data sharing. However, there are still many challenges to applying the traditional synchronous FL directly in the Internet of Vehicles (IoV), such as unreliable communications and malicious attacks. In this paper, we propose a Directed Acyclic Graph (DAG) based Swarm Learning (DSL), which integrates edge computing, FL, and blockchain technologies to provide secure data sharing and model training in IoVs. To deal with the high mobility of vehicles, the dynamic vehicle association algorithm is introduced, which could optimize the connections between vehicles and road side units to improve the training efficiency. Moreover, to enhance the anti-attack property of the DSL algorithm, a malicious attack detection method is adopted, which could recognize malicious vehicles by the site confirmation rate. Furthermore, an accuracy-based reward mechanism is developed to promote vehicles to participate in the model training with honest behaviors. Finally, simulation results demonstrate that the proposed DSL algorithm could achieve better performance in terms of model accuracy, convergence rates and security compared with existing algorithms.

Keywords

Direct acyclic graph / Internet of Vehicles / Swarm learning / Asynchronous learning

References

[1] L. Xing, P. Zhao, J. Gao, H. Wu, H. Ma, A survey of the social internet of vehicles: secure data issues, solutions, and federated learning, IEEE Intell. Transp. Syst. Mag.(2022) 2-16.

[2] X. Zhou, W. Liang, J. She, Z. Yan, K.I.-K. Wang, Two-layer federated learning with heterogeneous model aggregation for 6g supported internet of vehicles, IEEE Trans. Veh. Technol. 70 (6) (2021) 5308-5317.

[3] X. Xu, H. Li, W. Xu, Z. Liu, L. Yao, F. Dai, Artificial intelligence for edge service optimization in internet of vehicles: a survey, Tsinghua Sci. Technol. 27 (2) (2022) 270-287.

[4] Y. He, K. Huang, G. Zhang, F.R. Yu, J. Chen, J. Li, Bift: a blockchain-based federated learning system for connected and autonomous vehicles, IEEE Int. Things J. 9 (14)(2022) 12311-12322.

[5] C. Qiu, H. Yao, X. Wang, N. Zhang, F.R. Yu, D. Niyato, Ai-chain: blockchain ener-gized edge intelligence for beyond 5g networks, IEEE Netw. 34 (6) (2020) 62-69.

[6] H. Yao, C. Liu, P. Zhang, S. Wu, C. Jiang, S. Yu, Identification of encrypted traffic through attention mechanism based long short term memory, IEEE Trans. Big Data 8(1) (2022) 241-252.

[7] M.S.H. Sassi, L.C. Fourati, Investigation on deep learning methods for privacy and security challenges of cognitive iov, in: 2020 International Wireless Communications and Mobile Computing (IWCMC), 2020, pp. 714-720.

[8] X. Xu, X. Zhang, X. Liu, J. Jiang, L. Qi, M.Z.A. Bhuiyan, Adaptive computation offloading with edge for 5g-envisioned internet of connected vehicles, IEEE Trans. Intell. Transp. Syst. 22 (8) (2021) 5213-5222.

[9] X. Xu, Q. Wu, L. Qi, W. Dou, S.-B. Tsai, M.Z.A. Bhuiyan, Trust-aware service of-floading for video surveillance in edge computing enabled internet of vehicles, IEEE Trans. Intell. Transp. Syst. 22 (3) (2021) 1787-1796.

[10] Y. Liu, F.R. Yu, X. Li, H. Ji, V.C.M. Leung, Blockchain and machine learning for communications and networking systems, IEEE Commun. Surv. Tutor. 22 (2) (2020) 1392-1431.

[11] D. Xu, Z. Ding, X. He, H. Zhao, M. Moze, F. Aioun, F. Guillemard, Learning from naturalistic driving data for human-like autonomous highway driving, IEEE Trans. Intell. Transp. Syst. 22 (12) (2021) 7341-7354.

[12] Y. He, Z. Zhang, F.R. Yu, N. Zhao, H. Yin, V.C.M. Leung, Y. Zhang, Deep-reinforcement-learning-based optimization for cache-enabled opportunistic inter-ference alignment wireless networks, IEEE Trans. Veh. Technol. 66 (11) (2017) 10433-10445.

[13] M. Cao, L. Zhang, B. Cao, Toward on-device federated learning: a direct acyclic graph-based blockchain approach, IEEE Trans. Neural Netw. Learn. Syst. (2021) 1-15.

[14] T. Li, A.K. Sahu, A. Talwalkar, V. Smith, Federated learning: challenges, methods, and future directions, IEEE Signal Process. Mag. 37 (3) (2020) 50-60.

[15] M.B. Mollah, J. Zhao, D. Niyato, Y.L. Guan, C. Yuen, S. Sun, K.-Y. Lam, L.H. Koh, Blockchain for the internet of vehicles towards intelligent transportation systems: a survey, IEEE Int. Things J. 8(6) (2021) 4157-4185.

[16] S. Nakamoto, Bitcoin: a peer to peer electronic cash system, https://bitcoin.org/bitcoin.pdf, 2008.

[17] F. Tschorsch, B. Scheuermann, Bitcoin and beyond: a technical survey on decentral-ized digital currencies, IEEE Commun. Surv. Tutor. 18 (3) (2016) 2084-2123.

[18] M. Belotti, N. Božić, G. Pujolle, S. Secci, A vademecum on blockchain technologies: when, which, and how, IEEE Commun. Surv. Tutor. 21 (4) (2019) 3796-3838.

[19] Y. Lu, X. Huang, K. Zhang, S. Maharjan, Y. Zhang, Blockchain empowered asyn-chronous federated learning for secure data sharing in internet of vehicles, IEEE Trans. Veh. Technol. 69 (4) (2020) 4298-4311.

[20] H.B. McMahan, E. Moore, D. Ramage, B.A. y Arcas, Federated learning of deep networks using model averaging, http://arxiv.org/abs/1602.05629, 2016.

[21] K.A. Bonawitz, H. Eichner, W. Grieskamp, D. Huba, A. Ingerman, V. Ivanov, C. Kiddon, J. Konečný, S. Mazzocchi, H.B. McMahan, T.V. Overveldt, D. Petrou, D. Ramage, J. Roselander, Towards federated learning at scale: system design, http://arxiv.org/abs/1902.01046, 2019.

[22] M. Fredrikson, S. Jha, T. Ristenpart, Model inversion attacks that exploit confidence information and basic countermeasures, in: Computer and Communications Secu-rity, 2015.

[23] B. Hitaj, G. Ateniese, F. Pérez-Cruz, Deep models under the GAN: information leak-age from collaborative deep learning, http://arxiv.org/abs/1702.07464, 2017.

[24] C. Ma, J. Li, M. Ding, H.H. Yang, F. Shu, T.Q.S. Quek, H.V. Poor, On safeguarding privacy and security in the framework of federated learning, IEEE Netw. 34 (4)(2020) 242-248.

[25] M. Alazab, S.P. RM, P. M, P.K.R. Maddikunta, T.R. Gadekallu, Q.-V. Pham, Federated learning for cybersecurity: concepts, challenges, and future directions, IEEE Trans. Ind. Inform. 18 (5) (2022) 3501-3509.

[26] H. Wang, K. Sreenivasan, S. Rajput, H. Vishwakarma, S. Agarwal, J. Sohn, K. Lee, D. S. Papailiopoulos, Attack of the tails: yes, you really can backdoor federated learn-ing, https://arxiv.org/abs/2007.05084, 2020.

[27] A. Shafahi, W.R. Huang, M. Najibi, O. Suciu, C. Studer, T. Dumitras, T. Goldstein, Poison frogs! targeted clean-label poisoning attacks on neural networks, http://arxiv.org/abs/1804.00792, 2018.

[28] S. Warnat-Herresthal, H. Schultze, et al., Swarm learning for decentralized and con-fidential clinical machine learning, Nature 594 (7862) (2021) 265-270.

[29] G.A. Kaissis, M.R. Makowski, D. Rückert, R.F. Braren, Secure, privacy-preserving and federated machine learning in medical imaging, Nat. Mach. Intell. 2(6) (2020) 305-311.

[30] E.S. Dove, Y. Joly, et al., Genomic cloud computing: legal and ethical points to consider, https://doi.org /10.1038 /ejhg.2014.196, 2015.

[31] D.C. Nguyen, M. Ding, P.N. Pathirana, A. Seneviratne, J. Li, H. Vincent Poor, Feder-ated learning for internet of things: a comprehensive survey, IEEE Commun. Surv. Tutor. 23 (3) (2021) 1622-1658.

[32] J. Konečný, H.B. McMahan, F.X. Yu, P. Richtárik, A.T. Suresh, D. Bacon, Federated learning: strategies for improving communication efficiency, http://arxiv.org/abs/1610.05492, 2016.

[33] S.R. Pokhrel, J. Choi, Federated learning with blockchain for autonomous vehicles: analysis and design challenges, IEEE Trans. Commun. 68 (8) (2020) 4734-4746.

[34] G. BitFury, Proof of stake versus proof of work, https://bitfury.com/content/downloads/pos-vs-pow-1.0.2.pdf, 2015.

[35] S. Popov, The tangle, https://bitfury.com/content/downloads/pos-vs-pow-1.0.2.pdf, 2015.

[36] H. Huang, W. Kong, S. Zhou, Z. Zheng, S. Guo, A survey of state-of-the-art on blockchains: theories, modelings, and tools, ACM Comput. Surv. 54 (2) (2021) 44.

[37] Y. Li, B. Cao, M. Peng, L. Zhang, L. Zhang, D. Feng, J. Yu, Direct acyclic graph-based ledger for internet of things: performance and security analysis, IEEE/ACM Trans. Netw. 28 (4) (2020) 1643-1656.

[38] J. Stallkamp, M. Schlipsing, J. Salmen, C. Igel, Man vs. computer: benchmarking machine learning algorithms for traffic sign recognition, http://www.sciencedirect.com/science/article/pii/S0893608012000457, 2012.