Abstract
Federated Learning has been praised for several years for collaborating machine learning paradigm while providing the data privacy of users who participate in the FL network. Even though there are many advantages of adopting FL architecture on their system, this is still suffered from security concerns because of various components. Mainly, a poisoning attack can be applied in the FL network to compromise the gradient update of the global model. In this case, a parameter server might lose the robustness of the global model. Several gradient aggregation rules have been proposed to prevent Byzantine from attacking the global model by adding malicious gradients. However, existing aggregation solutions such as Krum, Multi-krum, and Geometric Median cannot offer a high detection rate or effectively filter outliers. To handle untargeted poisoning attacks by Byzantine on the FL network, we propose a new aggregation rule MDagg which uses Mahalanobis Distance to consider the distance between gradients and covariance among gradients simultaneously. Whenever the server receives gradients from clients, the server computes Mahalanobis Distance between all gradients by calculating the covariance matrix and multiplying the difference between gradients’ vectors. Our evaluation results show that MDagg provides the robustness of the FL network, wherein Byzantine compromises some of the clients.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Fang M, Cao X, Jia J, Gong NZ (2020) Local model poisoning attacks to Byzantine-robust federated learning, p 18
Shejwalkar V, Houmansadr A (2021) Manipulating the byzantine: optimizing model poisoning attacks and defenses for federated learning. In: Network and distributed system security symposium, Virtual
McMahan B, Moore E, Ramage D, Hampson S, Arcas BAY (2017) Communication-efficient learning of deep networks from decentralized data. In: Proceedings of the 20th international conference on artificial intelligence and statistics, pp 1273–1282
Konečný J, McMahan HB, Yu FX, Richtárik P, Suresh AT, Bacon D (2017) Federated learning: strategies for improving communication efficiency. arXiv
Bonawitz K et al (2019) Towards federated learning at scale: system design. System Design, p 15
Mothukuri V, Parizi RM, Pouriyeh S, Huang Y, Dehghantanha A, Srivastava G (2021) A survey on security and privacy of federated learning. Future Gener Comput Syst 115:619–640
Lyu L et al (2022) Privacy and robustness in federated learning: attacks and defenses. arXiv
Blanchard P, El Mhamdi EM, Guerraoui R, Stainer J (2017) Machine learning with adversaries: Byzantine tolerant gradient descent. In: Advances in neural information processing systems, vol 30
Pillutla K, Kakade SM, Harchaoui Z (2022) Robust aggregation for federated learning. arXiv
Wan CP, Chen Q (2021) Robust federated learning with attack-adaptive aggregation. arXiv
Acknowledgements
This research was supported by the Ministry of Science and ICT (MSIT), Korea, under the Information Technology Research Center (ITRC) support program (IITP-2022-2020-0-01602) supervised by the Institute for Information and Communications Technology Planning and Evaluation (IITP).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Gwak, S., Jung, S. (2023). MDagg: A New Aggregation Method Using Mahalanobis Distance. In: Park, J.S., Yang, L.T., Pan, Y., Park, J.H. (eds) Advances in Computer Science and Ubiquitous Computing. CUTECSA 2022. Lecture Notes in Electrical Engineering, vol 1028. Springer, Singapore. https://doi.org/10.1007/978-981-99-1252-0_5
Download citation
DOI: https://doi.org/10.1007/978-981-99-1252-0_5
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-1251-3
Online ISBN: 978-981-99-1252-0
eBook Packages: EngineeringEngineering (R0)