In federated learning, Byzantine nodes can carefully manipulate the model updates of clients. As a result, the central model accuracy decreases or fails to converge after aggregation. The number of communication rounds also increases. Without trusted reference gradients, the central model can not be properly aggregated solely from updates provided by untrustworthy clients. In this paper, we introduce a trusted reference and we regard it as a shadow model. To overcome this challenge, we propose a novel Byzantine robust federated aggregation method. The central server collects the shadow dataset in advance and trains a model called the shadow model. The central server compares the update direction between the client model and the trusted shadow model. Accordingly, the central server computes malicious score and marks the malicious clients. Then, the central model deletes or prunes the updates from the malicious clients. Finally, the central model aggregates the corrected gradients to ensure good convergence and maintain accuracy. The proposed method has been evaluated on a variety of model architectures and real datasets. The results show that the proposed method can effectively defend against six different Byzantine node attacks on three datasets.
QasimR, BangyalW H, AlqarniM A, et al. A fine-tuned BERT-based transfer learning approach for text classification[J]. Journal of Healthcare Engineering, 2022, 2022:3498123. DOI:10.1155/2022/3498123 .
[2]
LiY L. Research and application of deep learning in image recognition[C]//2022 IEEE 2nd International Conference on Power,Electronics and Computer Applications (ICPECA). January 21-23, 2022, Shenyang, China. IEEE, 2022:994-999. DOI:10.1109/ICPECA53709.2022.9718847 .
McMahanH B, MooreE, RamageD, et al. Communication-efficient learning of deep networks from decentralized data[EB/OL]. arXiv 2023:1602.05629. (2023-01-26) [2023-12-10].
[9]
CheC J, LiX L, ChenC, et al. A decentralized federated learning framework via committee mechanism with convergence guarantee[J]. IEEE Transactions on Parallel and Distributed Systems, 2022, 33(12): 4783-4800. DOI: 10.1109/TPDS.2022.3202887 .
[10]
KarrasA, KarrasC, GiotopoulosK C, et al. Peer to peer federated learning: towards decentralized machine learning on edge devices [C]//2022 7th South-East Europe Design Automation,Computer Engineering, Computer Networks and Social Media Conference (SEEDA-CECNSM). September 23-25, 2022, Ioannina, Greece. IEEE, 2022: 1-9.DOI: 10.1109/SEEDA-CECNSM57760.2022.9932980 .
[11]
NasrM, ShokriR, HoumansadrA. Comprehensive privacy analysis of deep learning: passive and active white-box inference attacks against centralized and federated learning[C]//2019 IEEE Symposium on Security and Privacy (SP). May 19-23, 2019, San Francisco, CA, USA. IEEE, 2019:739-753. DOI:10.1109/SP.2019.00065 .
[12]
GarovK, DimitrovD I, JovanovićN, et al. Hiding in plain sight: disguising data stealing attacks in federated learning[EB/OL]. arXiv 2023:2306.03013.(2023-06-25)[2023-08-25].
[13]
BhagojiA N, ChakrabortyS, MittalP, et al. Analyzing federated learning through an adversarial lens[EB/OL]. arXiv 2019: 1811.12470. (2019-11-25)[2023-12-10].
[14]
ChenJ Y, HuangG H, ZhengH B, et al. Graph-fraudster: Adversarial attacks on graph neural network-based vertical federated learning[J]. IEEE Transactions on Computational Social Systems, 2023, 10(2): 492-506. DOI: 10.1109/TCSS.2022.3161016 .
[15]
TolpeginV, TruexS, GursoyM E, et al. Data poisoning attacks against federated learning systems[C]//25th European Symposium on Research in Computer Security (ESORICS). September 14-18, 2020, Guildford, UK. Springer, 2020: 480-501. DOI: 10.1007/978-3-030-58951-6_24 .
[16]
FangM H, CaoX Y, JiaJ Y, et al. Local model poisoning attacks to byzantine-robust federated learning. [EB/OL]. arXiv 2021:1911.11815. (2021-11-21)[2023-12-10].
[17]
XiaoX, TangZ, LiC Y, et al. SCA:Sybil-based collusion attacks of IIoT data poisoning in federated learning[J]. IEEE Transactions on Industrial Informatics, 2023, 19(3): 2608-2618. DOI:10.1109/TII.2022.3172310 .
[18]
HidanoS, MurakamiT, KawamotoY. TransMIA: membership inference attacks using transfer shadow training[C]//2021 International Joint Conference on Neural Networks (IJCNN). July 18-22, 2021, Shenzhen, China. IEEE, 2021:1-10. DOI:10.1109/IJCNN52387.2021.9534207 .
[19]
TanJ X, ZhongN, QianZ X, et al. Deep neural network watermarking against model extraction attack[C]//Proceedings of the 31st ACM International Conference on Multimedia (ACM MM). October 29, 2023, Ottawa, Canada. ACM, 2023: 1588-1597. DOI: 10.1145/3581783.3612515 .
[20]
BlanchardP, MhamdiE M E, GuerraouiR, et al. Machine learning with adversaries: Byzantine tolerant gradient descent[C]// Advances in Neural Information Processing Systems (NeurIPS). December 4-9, 2017, Long Beach, USA. MIT Press, 2017:118–128. DOI:10.5555/3294771.3294783 .
[21]
YinD, ChenY D, RamchandranK, et al. Byzantine-robust distributed learning: towards optimal statistical rates[EB/OL]. arXiv 2021: 1803.01498. (2021-2-25) [2023-12-10].
[22]
CaoX Y, FangM H, LiuJ, et al. FLTrust: Byzantine-robust federated learning via trust bootstrapping[C]//28th Annual Network and Distributed System Security Symposium (NDSS). February 21-25, 2021, virtually. ISOC, 2021.DOI:10.14722/ndss.2021.24434 .
LiY Z, LiY M, WuB Y, et al. Invisible backdoor attack with sample-specific triggers[C]//2021 IEEE/CVF International Conference on Computer Vision (ICCV). October 10-17, 2021, Montreal, QC, Canada. IEEE, 2021: 16443-16452. DOI:10.1109/ICCV48922.2021.01615 .
[25]
ZhouX C, XuM, WuY M, et al. Deep model poisoning attack on federated learning[J]. Future Internet, 2021, 13(3): 73. DOI: 10.3390/fi13030073 .
[26]
BagdasaryanE, VeitA, HuaY Q, et al. How to backdoor federated learning[EB/OL]. arXiv 2019:1807.00459.(2019-08-06) [2023-12-10].
[27]
CaoX Y, GongN Z. MPAF: model poisoning attacks to federated learning based on fake clients[C]//2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). June 19-20, 2022, New Orleans, LA, USA. IEEE, 2022: 3395-3403. DOI: 10.1109/CVPRW56347.2022.00383 .
[28]
QayyumA, JanjuaM U, QadirJ. Making federated learning robust to adversarial attacks by learning data and model association[J]. Computers Security, 2022, 121: 102827. DOI: 10.1016/j.cose.2022.102827 .
[29]
CaoX Y, ZhangZ X, JiaJ Y, et al. FLCert: provably secure federated learning against poisoning attacks[J]. IEEE Transactions on Information Forensics and Security, 2022, 17: 3691-3705. DOI: 10.1109/TIFS.2022.3212174 .
[30]
GuoS W, ZhangT W, YuH, et al. Byzantine-resilient decentralized stochastic gradient descent[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2022, 32(6): 4096-4106. DOI: 10.1109/TCSVT.2021.3116976 .
[31]
PillutlaK, KakadeS M, HarchaouiZ. Robust aggregation for federated learning[J]. IEEE Transactions on Signal Processing, 2022, 70: 1142-1154. DOI: 10.1109/TSP.2022.3153135 .
[32]
KieuT, YangB, GuoC J, et al. Anomaly detection in time series with robust variational quasi-recurrent autoencoders[C]//2022 IEEE 38th International Conference on Data Engineering (ICDE). May 9-12, 2022, Kuala Lumpur, Malaysia. IEEE, 2022: 1342-1354. DOI: 10.1109/ICDE53745.2022.00105 .
[33]
ZhangZ, ZhangY, GuoD, et al. SecFedNIDS: robust defense for poisoning attack against federated learning-based network intrusion detection system[J]. Future Generation Computer Systems, 2022, 134: 154-169. DOI: 10.1016/j.future.2022.04.010 .
[34]
WangX X, ZhangH Q, BilalA, et al. WGM-dSAGA: federated learning strategies with Byzantine robustness based on weighted geometric Median[J]. Electronics, 2023, 12(5): 1190. DOI: 10.3390/electronics12051190 .
[35]
LiX Y, QuZ, ZhaoS Q, et al. LoMar: a local defense against poisoning attack on federated learning[J]. IEEE Transactions on Dependable and Secure Computing, 2023, 20(1): 437–450. DOI: 10.1109/TDSC.2021.3135422 .
[36]
SharmaA, ChenW, ZhaoJ, et al. TESSERACT: gradient flip score to secure federated learning against model poisoning attacks[EB/OL]. arXiv 2021:2110.10108. (2021-10-19) [2023-12-10].