基于联邦学习的分布式物联网设备识别方法

doi:10.3778/j.issn.1002-8331.2402-0140

摘要/Abstract

摘要： 传统物联网设备识别方法通常采用集中式训练方式，将边缘设备的私有流量集中部署在中央服务器中用于学习指纹提取与识别，但集中式训练存在着数据隐私问题以及单点故障问题。针对上述问题，提出了基于联邦学习的分布式物联网设备识别方法。在边缘设备方面，提出了轻量级设备指纹识别模型，提取网络流量会话中的时序信息以及特征间信息以生成可识别的指纹，并训练一个高效的分类器实现指纹识别；在中央服务器方面，设计了基于生成式知识蒸馏的异构联邦学习算法，通过训练变分生成器以无代理数据的方式集成本地信息并利用集成知识指导局部模型，从而解决分布式场景下的统计异构问题。在四个公开的基准数据集上进行了大量实验，通过与先进的联邦学习方法及设备指纹识别方法进行比较与分析，验证了所提方法对于提升分布式物联网设备识别准确率及效率的有效性。

关键词: 物联网设备识别, 设备指纹, 联邦学习, 知识蒸馏

Abstract: Traditional IoT device identification methods usually use centralized training, where private traffic from edge devices is deployed in a central server for learning fingerprint extraction and identification. But centralized training suffers from data privacy issues as well as single-point-of-failure problems. To address these issues, a distributed IoT device identification method based on federated learning is proposed. For edge devices, a lightweight device fingerprint identification model is proposed, which extracts temporal information as well as inter-feature information from network traffic sessions to generate distinguishable fingerprints, and trains an efficient classifier to achieve fingerprint identification. For central servers, a heterogeneous federated learning algorithm based on generative knowledge distillation is designed, which integrates local information in an agentless data manner by training a variation generator and uses the integrated knowledge to guide local models, thus solving the statistical heterogeneity problem in distributed scenarios. Extensive experiments are conducted on four publicly available benchmark datasets, comparing it with state-of-the-art federated learning methods and device fingerprinting methods. It validates the effectiveness of the proposed method for improving distributed IoT device recognition accuracy and efficiency.

Key words: IoT device identification, device fingerprint, federated learning, knowledge distillation

邹徐熹, 周忠冉, 王虹岚, 李飞, 顾亚林, 魏训虎, 李静. 基于联邦学习的分布式物联网设备识别方法[J]. 计算机工程与应用, 2024, 60(23): 155-167.

ZOU Xuxi, ZHOU Zhongran, WANG Honglan, LI Fei, GU Yalin, WEI Xunhu, LI Jing. Distributed IoT Device Identification Based on Federated Learning[J]. Computer Engineering and Applications, 2024, 60(23): 155-167.

参考文献

[1] KUYPERS M, MAILLART T, PATé-CORNELL E. An empirical analysis of cyber security incidents at a large organization[EB/OL]. (2016-02-24)[2024-01-21]. https://fsi.stanford.edu/publication/empirical-analysis-cyber-security-incidents-large-organization.
[2] GEYER R C, KLEIN T, NABI M. Differentially private federated learning: a client level perspective[J]. arXiv:1712. 07557, 2017.
[3] YANG Q, LIU Y, CHEN T. Federated machine learning: concept and applications[J]. ACM Transactions on Intelligent Systems and Technology, 2019, 10(2): 1-19.
[4] BONAWITZ K, EICHNER H, GRIESKAMP W, et al. Towards federated learning at scale: system design[J]. arXiv:1902. 01046, 2019.
[5] MCMAHAN B, MOORE E, RAMAGE D, et al. Communication-efficient learning of deep networks from decentralized data[C]//Proceedings of the 20th International Conference on Artificial Intelligence and Statistics, 2017: 1273-1282.
[6] SAMARAKOON S, BENNIS M, SAAD W, et al. Distributed federated learning for ultra-reliable low-latency vehicular communications[J]. IEEE Transactions on Communications, 2019, 68(2): 1146-1159.
[7] KAIROUZ P, MCMAHAN H B, AVENT B, et al. Advances and open problems in federated learning[J]. arXiv:1912. 04977, 2019.
[8] LI T, SAHU A K, ZAHEER M, et al. Federated optimization in heterogeneous networks[J]. arXiv:1812.06127, 2018.
[9] SIVANATHAN A, SHERRATT D, GHARAKHEILI H H, et al. Characterizing and classifying IoT traffic in smart cities and campuses[C]//Proceedings of the 2017 IEEE Conference on Computer Communications Workshops, 2017: 559-564.
[10] BEZAWADA B, BACHANI M, PETERSON J, et al. Behavioral fingerprinting of IoT devices[C]//Proceedings of the 2018 Workshop on Attacks and Solutions in Hardware Security, 2018: 41-50.
[11] BREMLER-BARR A, LEVY H, YAKHINI Z. IoT or NoT: identifying IoT devices in a short time scale[C]//Proceedings of the 2020 IEEE/IFIP Network Operations and Management Symposium, 2020: 1-9.
[12] LOPEZ-MARTIN M, CARRO B, SANCHEZ-ESGUEVILLAS A, et al. Network traffic classifier with convolutional and recurrent neural networks for internet of things[J]. IEEE Access, 2017, 5: 18042-18050.
[13] MIETTINEN M, MARCHAL S, HAFEEZ I, et al. IoT SENTINEL: automated device?type identification for security enforcement in IoT[C]//Proceedings of the 2017 IEEE 37th International Conference on Distributed Computing Systems, 2017: 2177-2184.
[14] MEIDAN Y, BOHADANA M, SHABTAI A, et al. Detection of unauthorized IoT devices using machine learning techniques[J]. arXiv:1709.04647, 2017.
[15] LI T, SAHU A K, TALWALKAR A, et al. Federated learning: challenges, methods, and future directions[J]. IEEE Signal Processing Magazine, 2020, 37(3): 50-60.
[16] BARAL P, YANG N, WENG N. IoT device identification using device fingerprint and deep learning[M]//Deep learning and reinforcement learning. Cham: Springer, 2023.
[17] CHOWDHURY R R, IDRIS A C, ABAS P E. A deep learning approach for classifying network connected IoT devices using communication traffic characteristics[J]. Journal of Network and Systems Management, 2023, 31(1): 26.
[18] SHENOY M V, FedDI: a novel privacy preserving horizontal federated learning based scheme for IoT device identification[J]. Journal of Network and Computer Applications, 2023, 214: 103616.
[19] WANG H, EKLUND D, OPREA A, et al. FL4IoT: IoT device fingerprinting and identification using federated learning[J]. ACM Transactions on Internet of Things, 2023, 4(3): 1-24.
[20] ACAR D A E, ZHAO Y, NAVARRO R M, et al. Federated learning based on dynamic regularization[J]. arXiv:2111. 04263, 2021.
[21] SHOHAM N, AVIDOR T, KEREN A, et al. Overcoming forgetting in federated learning on Non-IID data[J]. arXiv:1910.07796, 2019.
[22] KARIMIREDDY S P, KALE S, MOHRI M, et al. Scaffold: stochastic controlled averaging for federated learning[C]//Proceedings of the International Conference on Machine Learning, 2020: 5132-5143.
[23] WANG J, LIU Q, LIANG H, et al. Tackling the objective inconsistency problem in heterogeneous federated optimization[C]//Advances in Neural Information Processing Systems, 2020: 7611-7623.
[24] LI X C, ZHAN D C. FedRS: federated learning with restricted softmax for label distribution Non-IID data[C]//Proceedings of the 27th ACM Conference on Knowledge Discovery & Data Mining, 2021: 995-1005.
[25] LIN T, KONG L, STICH S U, et al. Ensemble distillation for robust model fusion in federated learning[C]//Advances in Neural Information Processing Systems, 2020: 2351-2363.
[26] SUN L, LYU L. Federated model distillation with noise-free differential privacy[J]. arXiv:2009.05537, 2020.
[27] LI D, WANG J. FedMD: heterogenous federated learning via model distillation[J]. arXiv:1910.03581, 2019.
[28] SATTLER F, KORJAKOW T, RISCHKE R, et al. FedAUX: leveraging unlabeled auxiliary data in federated learning[J]. IEEE Transactions on Neural Networks and Learning Systems, 2021, 34(9): 5531-5543.
[29] YOON T, SHIN S, HWANG S J, et al. FedMIX: approximation of mixup under mean augmented federated learning[J]. arXiv:2107.00233, 2021.
[30] SEO H, PARK J, OH S, et al. Federated knowledge distillation[J]. arXiv:2011.02367, 2020.
[31] YAO D, PAN W, DAI Y, et al. FedGKD: towards heterogeneous federated learning via global knowledge distillation[J]. IEEE Transactions on Computers, 2023, 73(1): 3-17.
[32] 唐跃中, 卢士达, 钱李烽, 等. IDFE: 面向物联网设备识别的指纹深度提取方法[J]. 计算机工程与应用, 2024, 60(17): 117-128.
TANG Y Z, LU S D, QIAN L F, et al. IDFE: fingerprint deep extraction method for IoT device identification[J]. Computer Engineering and Applications, 2024, 60(17): 117-128.
[33] NOGUCHI H, DEMIZU T, HOSHIKAWA N, et al. Autonomous device identification architecture for internet of things[C]//Proceedings of the 2018 IEEE 4th World Forum on Internet of Things, 2018: 407-411.
[34] WANG W, ZHU M, ZENG X, et al. Malware traffic classification using convolutional neural network for representation learning[C]//Proceedings of the 2017 International Conference on Information Networking, 2017: 712-717.
[35] TOLSTIKHIN I O, HOULSBY N, KOLESNIKOV A, et al. MLP-Mixer: an all-MLP architecture for vision[C]//Advances in Neural Information Processing Systems, 2021: 24261-24272.
[36] KITAEV N, KAISER ?, LEVSKAYA A. Reformer: the efficient transformer[J]. arXiv:2001.04451, 2020.
[37] BAI S, KOLTER J Z, KOLTUN V. An empirical evaluation of generic convolutional and recurrent networks for sequence modeling[J]. arXiv:1803.01271, 2018.
[38] MARCHAL S, MIETTINEN M, NGUYEN T D, et al. AuDI: toward autonomous IoT device-type identification using periodic communication[J]. IEEE Journal on Selected Areas in Communications, 2019, 37(6): 1402-1412.
[39] BIKMUKHAMEDOV R F, NADEEV A F. Multi-class network traffic generators and classifiers based on neural networks[C]//Proceedings of the 2021 Systems of Signals Generating and Processing in the Field of on Board Communications, 2021: 1-7.
[40] YIN F, YANG L, MA J, et al. Identifying IoT devices based on spatial and temporal features from network traffic[J]. Security and Communication Networks, 2021, 2021: 1-16.
[41] ZHU Z, HONG J, ZHOU J. Data-free knowledge distillation for heterogeneous federated learning[C]//Proceedings of the International Conference on Machine Learning, 2021: 12878-12889.
[42] FRANKLIN J, MCCOY D, TABRIZ P, et al. Passive data link layer 802. 11 wireless device driver fingerprinting[C]//Proceedings of the 15th Conference on USENIX Security Symposium, 2006: 16-89.
[43] ALRAWI O, LEVER C, ANTONAKAKIS M, et al. SoK: security evaluation of home-based IoT deployments[C]//Proceedings of the 2019 IEEE Symposium on Security and Privacy, 2019: 1362-1380.
[44] CHARYYEV B, GUNES M H. IoT traffic flow identification using locality sensitive hashes[C]//Proceedings of the 2020 IEEE International Conference on Communications, 2020: 1-6.
[45] REN J, DUBOIS D J, CHOFFNES D, et al. Information exposure from consumer IoT devices: a multidimensional, network-informed measurement approach[C]//Proceedings of the Internet Measurement Conference, 2019: 267-279.
[46] VAN DER MAATEN L, HINTON G. Visualizing data using t-SNE[J]. Journal of Machine Learning Research, 2008, 9(86): 2579-2605.