Abstract
In federated learning framework, data are kept locally by clients, which provides naturally a certain level of privacy. However, we show in this paper that a curious onlooker can still infer some sensitive information of clients by looking at the exchanged messages. More precisely, for the linear regression task, the onlooker can decode the exact local model of each client in a constant number of rounds under both cross-device and cross-silo federated learning settings. We improve one of the learning algorithms and experimentally show that it makes the onlooker harder to decode the local model of clients.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsNotes
- 1.
- 2.
UMAP is a general purpose manifold learning and dimension reduction algorithm: https://umap-learn.readthedocs.io/en/latest/basic_usage.html.
- 3.
Boston House Dataset:https://scikit-learn.org/stable/modules/generated/sklearn.datasets.load_bost-on.html.
References
McMahan, B., Moore, E., Ramage, D., et al.: Communication-efficient learning of deep networks from decentralized data. In: Artificial Intelligence and Statistics. PMLR, pp. 1273–1282 (2017)
Ma, C., Li, J., Ding, M., Shu, F., et al.: On safeguarding privacy and security in the framework of federated learning. IEEE Network 34(4), 242–248 (2020)
Wang, Z., Song, M., Zhang, Z., Song, Y., Qi, H.: Beyond inferring class representatives: user-level privacy leakage from federated learning. In: IEEE INFOCOM 2019 - IEEE Conference on Computer Communications, pp. 2512–2520. IEEE (2019)
Dwork, C., Roth, A.: The algorithmic foundations of differential privacy. Found. Trends Theor. Comput. Sci. 9(3–4), 211–407 (2014)
Li, J., Khodak, M., Caldas, S., Talwalkar, A.: Differentially Private Meta-Learning. arXiv preprint arXiv:1909.05830 (2019)
Truex, S., Baracaldo, N., Anwar, A., Steinke, T., et al.: A hybrid approach to privacy-preserving federated learning. In: Proceedings of the 12th ACM Workshop on Artificial Intelligence and Security, pp. 1–11. ACM (2019)
Fredrikson, M., Lantz, E., Jha, S., et al.: Privacy in pharmacogenetics: an end-to-end case study of personalized warfarin dosing. In: 23rd USENIX Security Symposium (USENIX Security 2014), pp. 17–32. USENIX (2014)
Fredrikson, M., Jha, S., Ristenpart, T.: Model inversion attacks that exploit confidence information and basic countermeasures. In: Proceedings of the 22nd ACM SIGSAC Conference on Computer and Communications Security, pp. 1322–1333. ACM (2015)
Kairouz, P., McMahan, H.B., Avent, B., et al.: Advances and open problems in federated learning. arXiv preprint arXiv:1912.04977 (2019)
Apple: Designing for privacy (video and slide deck). Apple WWDC (2019). https://developer.apple.com/videos/play/wwdc2019/708
ai.google: Under the hood of the Pixel 2: How AI is supercharging hardware (2018). https://ai.google/stories/ai-in-hardware
Hard, A., Rao, K., Mathews, R., et al.: Federated learning for mobile keyboard prediction. arXiv preprint arXiv:1811.03604 (2018)
Musketeer: The MUSKETEER cross-domain platform will validate progress in the two industrial scenarios: SMART MANUFACTURING and HEALTH CARE (2019). http://musketeer.eu/project
WeBank: WeBank and Swiss resigned cooperation MOU (2019). https://finance.yahoo.com/news/webank-swiss-signed-cooperation-mou-112300218.html
Blondel, V.D., Hendrickx, J.M., Olshevsky, A., et al.: Convergence in multiagent coordination, consensus, and flocking. In: Proceedings of the 44th IEEE Conference on Decision and Control, pp. 2996–3000. IEEE (2005)
Jadbabaie, A., Lin, J., Morse, A.S.: Coordination of groups of mobile autonomous agents using nearest neighbor rules. IEEE Trans. Autom. Control 48(6), 988–1001 (2003)
Tsitsiklis, J., Bertsekas, D., Athans, M.: Distributed asynchronous deterministic and stochastic gradient optimization algorithms. IEEE Trans. Autom. Control 31(9), 803–812 (1986)
Gao, H., Wang, Y.: Dynamics Based Privacy Protection for Average Consensus on Directed Graphs. arXiv preprint arXiv:1812.02255 (2018)
Dwork, C.: Differential privacy. In: Bugliesi, M., Preneel, B., Sassone, V., Wegener, I. (eds.) ICALP 2006. LNCS, vol. 4052, pp. 1–12. Springer, Heidelberg (2006). https://doi.org/10.1007/11787006_1
Dwork, C., Kenthapadi, K., McSherry, F., Mironov, I., Naor, M.: Our data, ourselves: privacy via distributed noise generation. In: Vaudenay, S. (ed.) EUROCRYPT 2006. LNCS, vol. 4004, pp. 486–503. Springer, Heidelberg (2006). https://doi.org/10.1007/11761679_29
Kempe, D., Dobra, A., Gehrke, J.: Gossip-based computation of aggregate information. In: 44th Annual IEEE Symposium on Foundations of Computer Science, Proceedings, pp. 482–491. IEEE (2003)
Bénézit, F., Blondel, V., Thiran, P., Tsitsiklis, J., Vetterli, M.: Weighted gossip: distributed averaging using non-doubly stochastic matrices. In: 2010 IEEE International Symposium on Information Theory, pp. 1753–1757. IEEE (2010)
Nedic, A., Ozdaglar, A.: Distributed subgradient methods for multi-agent optimization. IEEE Trans. Autom. Control 54(1), 48–61 (2009)
Boyd, S., Ghosh, A., Prabhakar, B., Shah, D.: Randomized gossip algorithms. IEEE Trans. Inf. Theory 52(6), 2508–2530 (2006)
Nedić, A., Olshevsky, A.: Distributed optimization over time-varying directed graphs. IEEE Trans. Autom. Control 60(3), 601–615 (2015)
Balcan, M.F., Blum, A., Fine, S., et al.: Distributed learning, communication complexity and privacy. In: Conference on Learning Theory. JMLR Workshop and Conference Proceedings, pp. 26-1 (2012)
Shamir, O., Srebro, N.: Distributed stochastic optimization and learning. In: 2014 52nd Annual Allerton Conference on Communication, Control, and Computing (Allerton), pp. 850–857. IEEE (2014)
Tsianos, K.I., Lawlor, S., Rabbat, M.G.: Push-sum distributed dual averaging for convex optimization. In: 2012 IEEE 51st IEEE Conference on Decision and Control (CDC), pp. 5453–5458. IEEE (2012)
Geyer, R.C., Klein, T., Nabi, M.: Differentially private federated learning: a client level perspective. arXiv preprint arXiv:1712.07557 (2017)
Wei, K., Li, J., Ding, M., et al.: Federated learning with differential privacy: algorithms and performance analysis. IEEE Trans. Inf. Forensics Secur. 15, 3454–3469 (2020)
Nagumey, A.: Book review: parallel and distributed computation: numerical methods. Int. J. Supercomput. Appl. 3(4), 73–74 (1989)
Fawaz, H.I., Lucas, B., Forestier, G., et al.: Inceptiontime: finding alexnet for time series classification. Data Min. Knowl. Disc. 34(6), 1936–1962 (2020)
Tsianos, K.I.: The Role of the Network in Distributed Optimization Algorithms: Convergence Rates, Scalability, Communication/Computation Tradeoffs and Communication Delays. McGill University Libraries (2013)
Fercoq, O., Qu, Z., Richtárik, P., Takáč, M.: Fast distributed coordinate descent for non-strongly convex losses. In: 2014 IEEE International Workshop on Machine Learning for Signal Processing (MLSP), pp. 1–6. IEEE (2014)
Tsianos, K.I., Lawlor, S., Rabbat, M.G.: Consensus-based distributed optimization: practical issues and applications in large-scale machine learning. In: 2012 50th Annual Allerton Conference on Communication, Control, and Computing (allerton), pp. 1543–1550. IEEE (2012)
Acknowledgment
Most of the work was finished during the master internship of the first author in Inria Sophia Antipolis, France. We would like to thank Prof. Giovanni Neglia and Dr. Chuan Xu for their ideas and suggestions. And this research is supported by the National Key R&D Program of China (2017YFB0801701 and 2017YFB0802805), the National Natural Science Foundation of China (Grants: U1936120, U1636216), Joint Fund of Ministry of Education of China for Equipment Preresearch (No. 6141A020333), the Fundamental Research Funds for the Central Universities, and the Basic Research Program of State Grid Shanghai Municipal Electric Power Company (52094019007F). Daojing He is the corresponding author of this article.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering
About this paper
Cite this paper
Pan, K., He, D., Xu, C. (2021). Local Model Privacy-Preserving Study for Federated Learning. In: Garcia-Alfaro, J., Li, S., Poovendran, R., Debar, H., Yung, M. (eds) Security and Privacy in Communication Networks. SecureComm 2021. Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering, vol 398. Springer, Cham. https://doi.org/10.1007/978-3-030-90019-9_15
Download citation
DOI: https://doi.org/10.1007/978-3-030-90019-9_15
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-90018-2
Online ISBN: 978-3-030-90019-9
eBook Packages: Computer ScienceComputer Science (R0)