Abstract
Traditional machine learning systems were designed in a centralized manner. In such designs, the central entity maintains both the machine learning model and the data used to adjust the model’s parameters. As data centralization yields privacy issues, Federated Learning was introduced to reduce data sharing and have a central server coordinate the learning of multiple devices. While Federated Learning is more decentralized, it still relies on a central entity that may fail or be subject to attacks, provoking the failure of the whole system. Then, Decentralized Federated Learning removes the need for a central server entirely, letting participating processes handle the coordination of the model construction. This distributed control urges studying the possibility of malicious attacks by the participants themselves. While poisoning attacks on Federated Learning have been extensively studied, their effects in Decentralized Federated Learning did not get the same level of attention. Our work is the first to propose a methodology to assess poisoning attacks in Decentralized Federated Learning in both churn free and churn prone scenarios. Furthermore, in orde r to evaluate our methodology on a case study representative for gossip learning we extended the gossipy simulator with an attack injector module.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
- 1.
- 2.
- 3.
This is done to evaluate the model against unseen data, but close to data that were used for adjusting model’s parameters. This allows us to see whether the model generalize well.
- 4.
This means that data is equally distributed among nodes, every node has approximately 25 images of each number.
- 5.
We borrow the idea behind these strategies from Magnien et al. [12], where they use these strategies in order to select nodes to be removed from a graph to study the graph connectivity.
- 6.
- 7.
References
Belal, Y., Bellet, A., Mokhtar, S.B., Nitu, V.: PEPPER: empowering user-centric recommender systems over gossip learning. In: Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies, 6(3), 101:1–101:27, September 2022
Beltrán, E.T.M., Pérez, M.Q., Sánchez, P.M.S., Bernal, S.L., Bovet, G., Pérez, M.G., Pérez, G.M., Celdrán, A.H.: Decentralized federated learning: fundamentals, state of the art, frameworks, trends, and challenges. IEEE Commun. Surv. Tutor., 1 (2023)
Bernstein, J., Wang, Y.-X., Azizzadenesheli, K., Anandkumar, A.: signSGD: compressed optimisation for non-convex problems. In: Proceedings of the 35th International Conference on Machine Learning, pp. 560–569. PMLR, July 2018
Bernstein, J., Zhao, J., Azizzadenesheli, K., Anandkumar, A.: signSGD with majority vote is communication efficient and fault tolerant. In: International Conference on Learning Representations, September 2018
Danner, G., Hegedűs, I., Jelasity, M.: Improving gossip learning via limited model merging. In: Advances in Computational Collective Intelligence, Communications in Computer and Information Science, pp. 351–363. Springer, Cham (2023). https://doi.org/10.1007/978-3-031-41774-0_28
Erdős, P., Rényi, A.: On random graphs I. Publicationes Mathematicae Debrecen 6, 290–297 (1959)
Giaretta, L., Girdzijauskas, Š.: Gossip Learning: Off the Beaten Path. In: 2019 IEEE International Conference on Big Data (Big Data), pp. 1117–1124, December 2019
Guo, J., Zuo, Y., Wen, C.-K., Jin, S.: User-centric online gossip training for autoencoder-based CSI feedback. IEEE J. Sel. Top. Signal Process. 16(3), 559–572 (2022)
Hegedűs, I., Danner, G., Jelasity, M.: Decentralized learning works: an empirical comparison of gossip learning and federated learning. J. Parallel Distributed Comput. 148, 109–124 (2021)
LeCun, Y., Cortes, C., Burges, C.J.: MNIST handwritten digit database. ATT Labs [Online], 2 (2010)
Liu, P., Xiangrui, X., Wang, W.: Threats, attacks and defenses to federated learning: issues, taxonomy and perspectives. Cybersecurity 5(1), 1–19 (2022)
Magnien, C., Latapy, M., Guillaume, J.-L.: Impact of random failures and attacks on Poisson and power-law random networks. ACM Comput. Surv. 43(3), 13:1–13:31 (2011)
Brendan McMahan, H., Moore, E., Ramage, D., Hampson, S., Arcas, B.J.: Communication-Efficient Learning of Deep Networks from Decentralized Data, February 2016
Ormándi, R., Hegedűs, I., Jelasity, M.: Gossip learning with linear models on fully distributed data. Concurrency Comput. Pract. Exp. 25(4), 556–571 (2013)
Paszke, A., et al.: PyTorch: an imperative style, high-performance deep learning library. In: Advances in Neural Information Processing Systems, vol. 32. Curran Associates, Inc. (2019)
Youyang, Q., Chenhao, X., Gao, L., Xiang, Y., Shui, Yu.: FL-SEC: privacy-preserving decentralized federated learning using SignSGD for the internet of artificially intelligent things. IEEE Internet Things Mag. 5(1), 85–90 (2022)
Watts, D.J., Strogatz, S.H.: Collective dynamics of ‘small-world’ networks. Nature 393(6684), 440–442 (1998)
Wu, C., Yang, X., Zhu, S., Mitra, P.: Mitigating Backdoor Attacks in Federated Learning, January 2021
Xia, G., Chen, J., Chaodong, Yu., Ma, J.: Poisoning attacks in federated learning: a survey. IEEE Access 11, 10708–10722 (2023)
Acknowledgements
The work presented in this document has received funding from the EU Horizon Europe research and innovation Programme under Grant Agreement No. 101070118.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Pham, A., Potop-Butucaru, M., Tixeuil, S., Fdida, S. (2024). Data Poisoning Attacks in Gossip Learning. In: Barolli, L. (eds) Advanced Information Networking and Applications. AINA 2024. Lecture Notes on Data Engineering and Communications Technologies, vol 200. Springer, Cham. https://doi.org/10.1007/978-3-031-57853-3_18
Download citation
DOI: https://doi.org/10.1007/978-3-031-57853-3_18
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-57852-6
Online ISBN: 978-3-031-57853-3
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)