research-article

PPFL: Enhancing Privacy in Federated Learning with Confidential Computing

Authors:

Fan Mo,

Nicolas KourtellisAuthors Info & Claims

GetMobile: Mobile Computing and Communications, Volume 25, Issue 4

Pages 35 - 38

https://doi.org/10.1145/3529706.3529715

Published: 30 March 2022 Publication History

Get Access

Abstract

Mobile networks and devices provide the users with ubiquitous connectivity, while many of their functionality and business models rely on data analysis and processing. In this context, Machine Learning (ML) plays a key role and has been successfully leveraged by the different actors in the mobile ecosystem (e.g., application and Operating System developers, vendors, network operators, etc.). Traditional ML designs assume (user) data are collected and models are trained in a centralized location. However, this approach has privacy consequences related to data collection and processing. Such concerns have incentivized the scientific community to design and develop Privacy-preserving ML methods, including techniques like Federated Learning (FL) where the ML model is trained or personalized on user devices close to the data; Differential Privacy, where data are manipulated to limit the disclosure of private information; Trusted Execution Environments (TEE), where most of the computation is run under a secure/ private environment; and Multi-Party Computation, a cryptographic technique that allows various parties to run joint computations without revealing their private data to each other.

References

[1]

Eugene Bagdasaryan, Andreas Veit, Yiqing Hua, Deborah Estrin, and Vitaly Shmatikov. 2020. How to backdoor federated learning. Proceedings of the Twenty Third International Conference on Artificial Intelligence and Statistics, PMLR, 2938--2948. https:// proceedings.mlr.press/v108/bagdasaryan20a.html

Google Scholar

[2]

Kleomenis Katevas, Eugene Bagdasaryan, Jason Waterman, Mohamad Mounir Safadieh, Eleanor Birrell, Hamed Haddadi, and Deborah Estrin. 2021. Policy-based federated learning. http://arxiv.org/ abs/2003.06612

Google Scholar

[3]

Nicolas Kourtellis, Kleomenis Katevas, and Diego Perino. 2020. FLaaS: Federated learning as a service. Proceedings of the 1st Workshop on Distributed Machine Learning (DistributedML'20), ACM, New York, NY, USA, 7--13. org/10.1145/3426745.3431337

Digital Library

Google Scholar

[4]

Tian Li, Anit Kumar Sahu, Manzil Zaheer, Maziar Sanjabi, Ameet Talwalkar, and Virginia Smith. 2020. Federated optimization in heterogeneous networks. Proceedings of Machine Learning and Systems 2, 429--450.

Google Scholar

[5]

Brendan McMahan, Eider Moore, Daniel Ramage, Seth Hampson, and Blaise Aguera y Arcas. 2017. Communication-efficient learning of deep networks from decentralized data. Proceedings of the 20th International Conference on Artificial Intelligence and Statistics, PMLR, 1273--1282. https://proceedings. mlr.press/v54/mcmahan17a.html

Google Scholar

[6]

Luca Melis, Congzheng Song, Emiliano De Cristofaro, and Vitaly Shmatikov. 2019. Exploiting unintended feature leakage in collaborative learning. 2019 IEEE Symposium on Security and Privacy (SP), 691--706. https://doi.org/10.1109/SP.2019.00029

Crossref

Google Scholar

[7]

Fan Mo, Anastasia Borovykh, Mohammad Malekzadeh, Hamed Haddadi, and Soteris Demetriou. 2020. Layer-wise characterization of latent information leakage in federated learning. International Conference of Learning Representations: Workshop on Distributed and Private Machine Learning (DPML).

Google Scholar

[8]

Fan Mo, Hamed Haddadi, Kleomenis Katevas, Eduard Marin, Diego Perino, and Nicolas Kourtellis. 2021. PPFL: Privacy-preserving federated learning with trusted execution environments. Proceedings of the 19th Annual International Conference on Mobile Systems, Applications, and Services (MobiSys '21), ACM, New York, NY, USA, 94--108. https://doi.org/10.1145/3458864.3466628

Digital Library

Google Scholar

[9]

Fan Mo, Ali Shahin Shamsabadi, Kleomenis Katevas, Soteris Demetriou, Ilias Leontiadis, Andrea Cavallaro, and Hamed Haddadi. 2020. DarkneTZ: Towards model privacy at the edge using trusted execution environments. Proceedings of the 18th International Conference on Mobile Systems, Applications, and Services (June 2020), 161--174. https://doi.org/10.1145/ 3386901.3388946

Digital Library

Google Scholar

[10]

Milad Nasr, Reza Shokri, and Amir Houmansadr. 2019. Comprehensive privacy analysis of deep learning: Passive and active white-box inference attacks against centralized and federated learning. In 2019 IEEE Symposium on Security and Privacy (SP), 739--753. https://doi.org/10.1109/ SP.2019.00065

Crossref

Google Scholar

[11]

Alexandre Sablayrolles, Matthijs Douze, Cordelia Schmid, Yann Ollivier, and Herve Jegou. 2019. White-box vs black-box: Bayes optimal strategies for membership inference. Proceedings of the 36th International Conference on Machine Learning, PMLR, 5558--5567. https://proceedings. mlr.press/v97/sablayrolles19a.html

Google Scholar

[12]

Hongyi Wang, Mikhail Yurochkin, Yuekai Sun, Dimitris Papailiopoulos, and Yasaman Khazaeni. 2019. Federated learning with matched averaging. International Conference on Learning Representations. https://openreview.net/forum?id=BkluqlSFDS

Google Scholar

[13]

S. Yeom, I. Giacomelli, M. Fredrikson, and S. Jha. 2018. Privacy risk in machine learning: Analyzing the connection to overfitting. 2018 IEEE 31st Computer Security Foundations Symposium (CSF), 268--282. https://doi. org/10.1109/CSF.2018.00027

Crossref

Google Scholar

[14]

Ligeng Zhu, Zhijian Liu, and Song Han. 2019. Deep leakage from gradients. Advances in Neural Information Processing Systems, Curran Associates, Inc. https://proceedings.neurips.cc/ paper/2019/hash/60a6c4002cc7b29142def887153 1281a-Abstract.html

Google Scholar

Cited By

View all

Guo JPietzuch PPaverd AVaswani K(2024)Trustworthy AI Using Confidential Federated LearningCommunications of the ACM10.1145/367739067:9(48-53)Online publication date: 15-Aug-2024
https://dl.acm.org/doi/10.1145/3677390
Guo JPietzuch PPaverd AVaswani K(2024)Trustworthy AI using Confidential Federated LearningQueue10.1145/366522022:2(87-107)Online publication date: 24-May-2024
https://dl.acm.org/doi/10.1145/3665220
Majeed AHwang S(2024)A Multifaceted Survey on Federated Learning: Fundamentals, Paradigm Shifts, Practical Issues, Recent Developments, Partnerships, Trade-Offs, Trustworthiness, and Ways ForwardIEEE Access10.1109/ACCESS.2024.341306912(84643-84679)Online publication date: 2024
https://doi.org/10.1109/ACCESS.2024.3413069
Show More Cited By

Recommendations

PPFL: privacy-preserving federated learning with trusted execution environments
MobiSys '21: Proceedings of the 19th Annual International Conference on Mobile Systems, Applications, and Services

We propose and implement a Privacy-preserving Federated Learning (PPFL) framework for mobile systems to limit privacy leakages in federated learning. Leveraging the widespread presence of Trusted Execution Environments (TEEs) in high-end and mobile ...
Personalised anonymity for microdata release

Individual privacy protection in the released data sets has become an important issue in recent years. The release of microdata provides a significant information resource for researchers, whereas the release of person‐specific data poses a threat to ...
A new unpredictability-based radio frequency identification forward privacy model and a provably secure construction

The privacy model of radio frequency identification RFID systems is for formalizing the adversarial capabilities and the security requirements of RFID anonymity and untraceability. Existing unpredictability-based privacy models such as unp-privacy, eunp-...

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

cover image GetMobile: Mobile Computing and Communications

GetMobile: Mobile Computing and Communications Volume 25, Issue 4

December 2021

34 pages

ISSN:2375-0529

EISSN:2375-0537

DOI:10.1145/3529706

Editor:
Landon Cox
Microsoft Research

Issue’s Table of Contents

Permission to make digital or hard copies of part or all 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 third-party components of this work must be honored. For all other uses, contact the Owner/Author.

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 30 March 2022

Published in SIGMOBILE-GETMOBILE Volume 25, Issue 4

Check for updates

Qualifiers

Research-article

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

5
Total Citations
View Citations
429
Total Downloads

Downloads (Last 12 months)73
Downloads (Last 6 weeks)7

Reflects downloads up to 21 Nov 2024

Other Metrics

View Author Metrics

Citations

Cited By

View all

Guo JPietzuch PPaverd AVaswani K(2024)Trustworthy AI Using Confidential Federated LearningCommunications of the ACM10.1145/367739067:9(48-53)Online publication date: 15-Aug-2024
https://dl.acm.org/doi/10.1145/3677390
Guo JPietzuch PPaverd AVaswani K(2024)Trustworthy AI using Confidential Federated LearningQueue10.1145/366522022:2(87-107)Online publication date: 24-May-2024
https://dl.acm.org/doi/10.1145/3665220
Majeed AHwang S(2024)A Multifaceted Survey on Federated Learning: Fundamentals, Paradigm Shifts, Practical Issues, Recent Developments, Partnerships, Trade-Offs, Trustworthiness, and Ways ForwardIEEE Access10.1109/ACCESS.2024.341306912(84643-84679)Online publication date: 2024
https://doi.org/10.1109/ACCESS.2024.3413069
Majeed AKhan SHwang S(2022)Group Privacy: An Underrated but Worth Studying Research Problem in the Era of Artificial Intelligence and Big DataElectronics10.3390/electronics1109144911:9(1449)Online publication date: 30-Apr-2022
https://doi.org/10.3390/electronics11091449
Messaoud AMokhtar SNitu VSchiavoni VBellavista PZhang KGherbi ABagchi SPatiño MDi Modica GGascon-Samson J(2022)Shielding federated learning systems against inference attacks with ARM TrustZoneProceedings of the 23rd ACM/IFIP International Middleware Conference10.1145/3528535.3565255(335-348)Online publication date: 7-Nov-2022
https://dl.acm.org/doi/10.1145/3528535.3565255

View Options

Login options

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

Cited By

Recommendations

PPFL: privacy-preserving federated learning with trusted execution environments

Personalised anonymity for microdata release

A new unpredictability-based radio frequency identification forward privacy model and a provably secure construction