Abstract
Federated matrix factorization (FedMF) has recently emerged as a privacy-friendly paradigm which runs matrix factorization (MF) in a federated learning (FL) setting and enables users to keep their individual rating data local in the training process. In FedMF, users only need to share out item gradients for aggregation. However, prior work has shown that the item gradients, if directly exposed, can still leak users’ rating data. Meanwhile, the rating data are typically sparse and simply uploading the gradients of rated items will leak which and how many items a user rates. In light of the above, in this paper, we present SARA, a new sparsity-aware efficient oblivious aggregation service for FedMF. SARA protects the confidentiality of item gradients as well as hides which and how many items a user rates, through a custom sparsity-aware design that delicately builds on differential privacy and lightweight cryptography. Extensive experiments over real-world datasets demonstrate that SARA is utility-preserving and can bring the users significant savings (up to 98.28%) in the number of transmitted item gradients, compared to the baseline of fully transmitting gradients for all possible items.
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
References
Apple and Google: Exposure notification privacy-preserving analytics (ENPA) white paper (2021). https://covid19-static.cdn-apple.com/applications/covid19/current/static/contact-tracing/pdf/ENPA%20White%20Paper.pdf. Accessed 1 June 2022
Bell, J., et al.: Distributed, private, sparse histograms in the two-server model. In: Proceedings of ACM CCS (2022)
Boyle, E., Gilboa, N., Ishai, Y.: Function secret sharing. In: Oswald, E., Fischlin, M. (eds.) EUROCRYPT 2015. LNCS, vol. 9057, pp. 337–367. Springer, Heidelberg (2015). https://doi.org/10.1007/978-3-662-46803-6_12
Boyle, E., Gilboa, N., Ishai, Y.: Function secret sharing: improvements and extensions. In: Proceedings of ACM SIGSAC (2016)
Chai, D., Wang, L., Chen, K., Yang, Q.: Secure federated matrix factorization. IEEE Intell. Syst. 36(5), 11–20 (2021)
Chai, D., Wang, L., Chen, K., Yang, Q.: Efficient federated matrix factorization against inference attacks. ACM Trans. Intell. Syst. Technol. 13(4), 59:1–59:20 (2022)
Cormode, G., Jha, S., Kulkarni, T., Li, N., Srivastava, D., Wang, T.: Privacy at scale: local differential privacy in practice. In: Proceedings of ACM SIGMOD (2018)
Curran, M., Liang, X., Gupta, H., Pandey, O., Das, S.R.: ProCSA: protecting privacy in crowdsourced spectrum allocation. In: Sako, K., Schneider, S., Ryan, P.Y.A. (eds.) ESORICS 2019. LNCS, vol. 11735, pp. 556–576. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-29959-0_27
Dauterman, E., Rathee, M., Popa, R.A., Stoica, I.: Waldo: a private time-series database from function secret sharing. In: Proceedings of IEEE S &P (2022)
Demmler, D., Schneider, T., Zohner, M.: ABY - a framework for efficient mixed-protocol secure two-party computation. In: Proceedings of NDSS (2015)
Du, M., Wu, S., Wang, Q., Chen, D., Jiang, P., Mohaisen, A.: GraphShielad: dynamic large graphs for secure queries with forward privacy. IEEE Trans. Knowl. Data Eng. 34(7), 3295–3308 (2022)
Dwork, C.: Differential privacy. In: Proceedings of ICALP (2006)
Dwork, C., McSherry, F., Nissim, K., Smith, A.D.: Calibrating noise to sensitivity in private data analysis. In: Proceedings of TCC (2006)
He, X., Machanavajjhala, A., Flynn, C.J., Srivastava, D.: Composing differential privacy and secure computation: a case study on scaling private record linkage. In: Proceedings of ACM CCS (2017)
Katz, J., Lindell, Y.: Handling expected polynomial-time strategies in simulation-based security proofs. In: Proceedings of TCC (2005)
Kim, S., Kim, J., Koo, D., Kim, Y., Yoon, H., Shin, J.: Efficient privacy-preserving matrix factorization via fully homomorphic encryption: extended abstract. In: Proceedings of ACM AsiaCCS (2016)
Koenigstein, N., Ram, P., Shavitt, Y.: Efficient retrieval of recommendations in a matrix factorization framework. In: Proceedings of CIKM (2012)
Koren, Y., Bell, R.M., Volinsky, C.: Matrix factorization techniques for recommender systems. Computer 42(8), 30–37 (2009)
Li, T., Sahu, A.K., Talwalkar, A., Smith, V.: Federated learning: challenges, methods, and future directions. IEEE Signal Process. Mag. 37(3), 50–60 (2020)
Li, Z., Ding, B., Zhang, C., Li, N., Zhou, J.: Federated matrix factorization with privacy guarantee. VLDB Endow. 15(4), 900–913 (2021)
McMahan, B., Moore, E., Ramage, D., Hampson, S., y Arcas, B.A.: Communication-efficient learning of deep networks from decentralized data. In: Proceedings of AISTATS (2017)
Mozilla Security Blog: Next steps in privacy-preserving telemetry with prio (2022). https://blog.mozilla.org/security/2019/06/06/next-steps-in-privacy-preserving-telemetry-with-prio/
Nikolaenko, V., Ioannidis, S., Weinsberg, U., Joye, M., Taft, N., Boneh, D.: Privacy-preserving matrix factorization. In: Proceedings of ACM CCS (2013)
Ryffel, T., Tholoniat, P., Pointcheval, D., Bach, F.R.: AriaNN: low-interaction privacy-preserving deep learning via function secret sharing. Proc. Priv. Enhancing Technol. 2022(1), 291–316 (2022)
Shin, H., Kim, S., Shin, J., Xiao, X.: Privacy enhanced matrix factorization for recommendation with local differential privacy. IEEE Trans. Knowl. Data Eng. 30(9), 1770–1782 (2018)
Tan, S., Knott, B., Tian, Y., Wu, D.J.: CryptGPU: fast privacy-preserving machine learning on the GPU. In: Proceedings of IEEE S &P (2021)
Weinsberg, U., Bhagat, S., Ioannidis, S., Taft, N.: BlurMe: inferring and obfuscating user gender based on ratings. In: Proceedings of ACM RecSys (2012)
Zhou, H., Yang, G., Xiang, Y., Bai, Y., Wang, W.: A lightweight matrix factorization for recommendation with local differential privacy in big data. IEEE Trans. Big Data 9(1), 160–173 (2023)
Acknowledgments
This work was supported in part by the Guangdong Basic and Applied Basic Research Foundation (No. 2023A1515010714 and No. 2024A1515012299), and by the Shenzhen Science and Technology Program (No. JCYJ20220531095416037 and No. JCYJ20230807094411024).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2025 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Zheng, Y., Xiong, T., Ouyang, H., Wang, S., Hua, Z., Gao, Y. (2025). SARA: A Sparsity-Aware Efficient Oblivious Aggregation Service for Federated Matrix Factorization. In: Barhamgi, M., Wang, H., Wang, X. (eds) Web Information Systems Engineering – WISE 2024. WISE 2024. Lecture Notes in Computer Science, vol 15437. Springer, Singapore. https://doi.org/10.1007/978-981-96-0567-5_17
Download citation
DOI: https://doi.org/10.1007/978-981-96-0567-5_17
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-96-0566-8
Online ISBN: 978-981-96-0567-5
eBook Packages: Computer ScienceComputer Science (R0)