research-article

MPCFL: Towards Multi-party Computation for Secure Federated Learning Aggregation

Authors:

Hiroki Kaminaga,

Feras M. Awaysheh,

Liina KammAuthors Info & Claims

UCC '23: Proceedings of the IEEE/ACM 16th International Conference on Utility and Cloud Computing

Article No.: 19, Pages 1 - 10

https://doi.org/10.1145/3603166.3632144

Published: 04 April 2024 Publication History

Abstract

In the rapidly evolving machine learning (ML) and distributed systems realm, the escalating concern for data privacy naturally comes to the forefront of discussions. Federated learning (FL) emerges as a pivotal technology capable of addressing the inherent issues of centralized data privacy. However, FL architectures with centralized orchestration are still vulnerable, especially in the aggregation phase. A malicious server can exploit the aggregation process to learn about participants' data. This study proposes MPCFL, a secure FL algorithm based on secure multi-party computation (MPC) and secret sharing. The proposed algorithm leverages the Sharemind MPC framework to aggregate local model updates for securely formulating a global model. MPCFL provides practical mitigation of trending FL concerns, e.g., inference attack, gradient leakage attack, model poisoning, and model inversion. The algorithm is evaluated on several benchmark datasets and shows promising results. Our results demonstrate that the proposed algorithm is viable for developing secure and privacy-preserving FL applications, significantly improving all performance metrics while maintaining security and reliability. This investigation is a precursor to deeper explorations to craft robust FL aggregation algorithms.

References

[1]

Sadi Alawadi, Khalid Alkharabsheh, Fahed Alkhabbas, Victor Kebande, Feras M Awaysheh, and Fabio Palomba. 2023. FedCSD: A Federated Learning Based Approach for Code-Smell Detection. arXiv preprint arXiv:2306.00038 (2023).

[2]

Jan Philipp Albrecht. 2016. How the GDPR will change the world. Eur. Data Prot. L. Rev. 2 (2016), 287.

[3]

Fahed Alkhabbas, Mohammed Alsadi, Sadi Alawadi, Feras M Awaysheh, Victor R Kebande, and Mahyar T Moghaddam. 2022. Assert: A blockchain-based architectural approach for engineering secure self-adaptive iot systems. Sensors 22, 18 (2022), 6842.

[4]

David W. Archer, Dan Bogdanov, Y. Lindell, Liina Kamm, Kurt Nielsen, Jakob Illeborg Pagter, Nigel P. Smart, and Rebecca N. Wright. 2018. From Keys to Databases - Real-World Applications of Secure Multi-Party Computation., 1749--1771 pages.

[5]

Feras M Awaysheh. 2022. From the Cloud to the Edge Towards a Distributed and Light Weight Secure Big Data Pipelines for IoT Applications. In Trust, Security and Privacy for Big Data. CRC Press, 50--68.

[6]

Feras M Awaysheh, Sadi Alawadi, and Sawsan AlZubi. 2022. FLIoDT: A Federated Learning Architecture from Privacy by Design to Privacy by Default over IoT. In 2022 Seventh International Conference on Fog and Mobile Edge Computing (FMEC). IEEE, 1--6.

[7]

Feras M Awaysheh, Mamoun Alazab, Sahil Garg, Dusit Niyato, and Christos Verikoukis. 2021. Big data resource management & networks: Taxonomy, survey, and future directions. IEEE Communications Surveys & Tutorials 23, 4 (2021), 2098--2130.

[8]

Feras M Awaysheh, Riccardo Tommasini, and Ahmed Awad. 2023. Big Data Analytics from the Rich Cloud to the Frugal Edge. In 2023 IEEE International Conference on Edge Computing and Communications (EDGE). IEEE, 319--329.

[9]

Catherine Barrett. 2019. Are the EU GDPR and the California CCPA becoming the de facto global standards for data privacy and protection? Scitech Lawyer 15, 3 (2019), 24--29.

[10]

Dan Bogdanov. 2013. Sharemind: programmable secure computations with practical applications. Ph. D. Dissertation. University of Tartu. http://hdl.handle.net/10062/29041

[11]

Dan Bogdanov, Liina Kamm, Baldur Kubo, Reimo Rebane, Ville Sokk, and Riivo Talviste. 2016. Students and Taxes: a Privacy-Preserving Study Using Secure Computation. PoPETs 2016, 3 (2016), 117--135. http://www.degruyter.com/view/j/popets.2016.2016.issue-3/popets-2015-0019/popets-2016-0019.xml

[12]

Keith Bonawitz, Vladimir Ivanov, Ben Kreuter, Antonio Marcedone, H. Brendan McMahan, Sarvar Patel, Daniel Ramage, Aaron Segal, and Karn Seth. 2017. Practical Secure Aggregation for Privacy-Preserving Machine Learning. In Proceedings of the 2017 ACM SIGSAC Conference on Computer and Communications Security (Dallas, Texas, USA) (CCS '17). Association for Computing Machinery, New York, NY, USA, 1175--1191.

Digital Library

[13]

Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, et al. 2020. Language models are few-shot learners. Advances in neural information processing systems 33 (2020), 1877--1901.

[14]

Diane Cook, Aaron Crandall, and Brian Thomas. 2019. Human Activity Recognition from Continuous Ambient Sensor Data. UCI Machine Learning Repository.

[15]

R. Cramer, I. Damgård, and J. Nielsen. 2015. Secure Multiparty Computation and Secret Sharing. Cambridge University Press.

[16]

Matt Fredrikson, Somesh Jha, and Thomas Ristenpart. 2015. Model inversion attacks that exploit confidence information and basic countermeasures. In Proceedings of the 22nd ACM SIGSAC conference on computer and communications security. 1322--1333.

Digital Library

[17]

Ian Goodfellow, Yoshua Bengio, and Aaron Courville. 2016. Deep learning. MIT press.

Digital Library

[18]

Marcella Hastings, Brett Hemenway, Daniel Noble, and Steve Zdancewic. 2019. SoK: General Purpose Compilers for Secure Multi-Party Computation. In 2019 IEEE Symposium on Security and Privacy (SP). 1220--1237.

[19]

Geoffrey E Hinton, Simon Osindero, and Yee-Whye Teh. 2006. A fast learning algorithm for deep belief nets. Neural computation 18, 7 (2006), 1527--1554.

Digital Library

[20]

Liina Kamm and Jan Willemson. 2015. Secure floating point arithmetic and private satellite collision analysis. International Journal of Information Security 14, 6 (2015), 531--548.

Digital Library

[21]

Victor R Kebande, Feras M Awaysheh, Richard A Ikuesan, Sadi A Alawadi, and Mohammad Dahman Alshehri. 2021. A blockchain-based multi-factor authentication model for a cloud-enabled internet of vehicles. Sensors 21, 18 (2021), 6018.

[22]

Alex Krizhevsky. 2009. Learning multiple layers of features from tiny images. https://www.cs.toronto.edu/~kriz/learning-features-2009-TR.pdf

[23]

Yann LeCun, Corinna Cortes, and CJ Burges. 2010. MNIST handwritten digit database. ATT Labs [Online]. Available: http://yann.lecun.com/exdb/mnist 2 (2010).

[24]

Lingjuan Lyu, Han Yu, and Qiang Yang. 2020. Threats to federated learning: A survey. arXiv preprint arXiv:2003.02133 (2020).

[25]

Mohamad Mansouri, Melek Onen, Wafa Ben Jaballah, and Mauro Conti. 2023. Sok: Secure aggregation based on cryptographic schemes for federated learning. Proc. Priv. Enhancing Technol 1 (2023), 140--157.

[26]

Brendan McMahan, Eider Moore, Daniel Ramage, Seth Hampson, and Blaise Aguera y Arcas. 2017. Communication-efficient learning of deep networks from decentralized data. In Artificial intelligence and statistics. PMLR, 1273--1282.

[27]

Andre Ostrak, Jaak Randmets, Ville Sokk, Sven Laur, and Liina Kamm. 2021. Implementing Privacy-Preserving Genotype Analysis with Consideration for Population Stratification. Cryptography 5, 3 (2021).

[28]

Dario Pasquini, Danilo Francati, and Giuseppe Ateniese. 2022. Eluding secure aggregation in federated learning via model inconsistency. In Proceedings of the 2022 ACM SIGSAC Conference on Computer and Communications Security. 2429--2443.

Digital Library

[29]

Jaak Randmets. 2017. Programming Languages for Secure Multi-party Computation Application Development. Ph. D. Dissertation. University of Tartu. http://hdl.handle.net/10062/56298

[30]

Mayank Rathee, Conghao Shen, Sameer Wagh, and Raluca Ada Popa. 2023. Elsa: Secure aggregation for federated learning with malicious actors. In 2023 IEEE Symposium on Security and Privacy (SP). IEEE, 1961--1979.

[31]

Ahmed Roushdy Elkordy, Jiang Zhang, Yahya H Ezzeldin, Konstantinos Psounis, and Salman Avestimehr. 2022. How Much Privacy Does Federated Learning with Secure Aggregation Guarantee? arXiv e-prints (2022), arXiv-2208.

[32]

Joshua C Zhao, Atul Sharma, Ahmed Roushdy Elkordy, Yahya H Ezzeldin, Salman Avestimehr, and Saurabh Bagchi. 2023. Secure aggregation in federated learning is not private: Leaking user data at large scale through model modification. arXiv preprint arXiv:2303.12233 (2023).

[33]

Ligeng Zhu, Zhijian Liu, and Song Han. 2019. Deep leakage from gradients. Advances in neural information processing systems 32 (2019).

Cited By

Tajabadi MMartin RHeider D(2024)Privacy-Preserving Decentralized Learning Methods for Biomedical ApplicationsComputational and Structural Biotechnology Journal10.1016/j.csbj.2024.08.024Online publication date: Aug-2024
https://doi.org/10.1016/j.csbj.2024.08.024
Asad MOtoum S(2024)Bppfl: a blockchain-based framework for privacy-preserving federated learningCluster Computing10.1007/s10586-024-04834-428:2Online publication date: 26-Nov-2024
https://doi.org/10.1007/s10586-024-04834-4

Index Terms

MPCFL: Towards Multi-party Computation for Secure Federated Learning Aggregation
1. Computing methodologies
  1. Machine learning
2. Security and privacy
  1. Security services
    1. Privacy-preserving protocols

Index terms have been assigned to the content through auto-classification.

Recommendations

Benchmarking robustness and privacy-preserving methods in federated learning
Highlight
- There is a conflict between robust aggregation methods and privacy protection methods in Federated Learning.
- The greater the resistance of robust aggregators to Byzantine.
- attacks, the more their privacy leakage will also be.
- ...
Abstract
Federated learning (FL) is a machine learning framework that enables the use of user data for training without the need to share the data with the central server. FL's decentralized structure can lead to security and privacy issues, as it allows ...
Survey on federated learning threats: Concepts, taxonomy on attacks and defences, experimental study and challenges
Abstract
Federated learning is a machine learning paradigm that emerges as a solution to the privacy-preservation demands in artificial intelligence. As machine learning, federated learning is threatened by adversarial attacks against the ...
Highlights
- We claim that adversarial attacks are a significant challenge in federated learning.
Performance trade-offs on a secure multi-party relational database
SAC '17: Proceedings of the Symposium on Applied Computing

The privacy of information is an increasing concern of software applications users. This concern was caused by attacks to cloud services over the last few years, that have leaked confidential information such as passwords, emails and even private ...

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

cover image ACM Conferences

UCC '23: Proceedings of the IEEE/ACM 16th International Conference on Utility and Cloud Computing

December 2023

502 pages

ISBN:9798400702341

DOI:10.1145/3603166

Co-chairs:
Omer Rana,
Massimo Villari,
Program Co-chairs:
Song Fu,
Lorenzo Carnevale

Copyright © 2023 Copyright is held by the owner/author(s). Publication rights licensed to ACM.

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].

Sponsors

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 04 April 2024

Check for updates

Author Tags

Qualifiers

Research-article

Conference

UCC '23

Sponsor:

SIGARCH

UCC '23: IEEE/ACM 16th International Conference on Utility and Cloud Computing

December 4 - 7, 2023

Taormina (Messina), Italy

Acceptance Rates

Overall Acceptance Rate 38 of 125 submissions, 30%

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

2
Total Citations
View Citations
244
Total Downloads

Downloads (Last 12 months)244
Downloads (Last 6 weeks)21

Reflects downloads up to 26 Dec 2024

Other Metrics

View Author Metrics

Citations

Cited By

Tajabadi MMartin RHeider D(2024)Privacy-Preserving Decentralized Learning Methods for Biomedical ApplicationsComputational and Structural Biotechnology Journal10.1016/j.csbj.2024.08.024Online publication date: Aug-2024
https://doi.org/10.1016/j.csbj.2024.08.024
Asad MOtoum S(2024)Bppfl: a blockchain-based framework for privacy-preserving federated learningCluster Computing10.1007/s10586-024-04834-428:2Online publication date: 26-Nov-2024
https://doi.org/10.1007/s10586-024-04834-4

View Options

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Media

Figures

Other

Tables

View Table of Contents