Privacy-aware Berrut Approximated Coded Computing for Federated Learning
Not on the map. Why?
Abstract (arXiv)
Federated Learning (FL) is an interesting strategy that enables the collaborative training of an AI model among different data owners without revealing their private datasets. Even so, FL has some privacy vulnerabilities that have been tried to be overcome by applying some techniques like Differential Privacy (DP), Homomorphic Encryption (HE), or Secure Multi-Party Computation (SMPC). However, these techniques have some important drawbacks that might narrow their range of application: problems to work with non-linear functions and to operate large matrix multiplications and high communication and computational costs to manage semi-honest nodes. In this context, we propose a solution to guarantee privacy in FL schemes that simultaneously solves the previously mentioned problems. Our proposal is based on the Berrut Approximated Coded Computing, a technique from the Coded Distributed Computing paradigm, adapted to a Secret Sharing configuration, to provide input privacy to FL in a scalable way. It can be applied for computing non-linear functions and treats the special case of distributed matrix multiplication, a key primitive at the core of many automated learning tasks. Because of these characteristics, it could be applied in a wide range of FL scenarios, since it is independent of the machine learning models or aggregation algorithms used in the FL scheme. We provide analysis of the achieved privacy and complexity of our solution and, due to the extensive numerical results performed, a good trade-off between privacy and precision can be observed.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 25 of its 51 references that are in the map. First posted on arXiv 2 May 2024.
Builds on
25 of 51 references.
References · 25
- 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
- 2019Advances and Open Problems in Federated Learningcited by 3,021
- 2021Membership Inference Attacks From First Principlescited by 839
- 2020Inverting Gradients -- How easy is it to break privacy in federated learning?cited by 707
- 2018Exploiting Unintended Feature Leakage in Collaborative Learningcited by 509
- 2021Data-Free Knowledge Distillation for Heterogeneous Federated Learningcited by 380
- 2019Robust Aggregation for Federated Learningcited by 314
- 2021Membership Inference Attacks on Machine Learning: A Surveycited by 306
- 2018Beyond Inferring Class Representatives: User-Level Privacy Leakage From Federated Learningcited by 242
- 2020Threats to Federated Learning: A Surveycited by 171
- 2020Privacy and Robustness in Federated Learning: Attacks and Defensescited by 163
- 2015Speeding Up Distributed Machine Learning Using Codescited by 76
13 more
- 2018Lagrange Coded Computing: Optimal Design for Resiliency, Security and Privacycited by 66
- 2020SpArch: Efficient Architecture for Sparse Matrix Multiplicationcited by 47
- 2021Precise Approximation of Convolutional Neural Networks for Homomorphically Encrypted Datacited by 26
- 2020Berrut Approximated Coded Computing: Straggler Resistance Beyond Polynomial Computingcited by 19
- 2018CodedSketch: A Coding Scheme for Distributed Computation of Approximated Matrix Multiplicationcited by 16
- 2020Analog Lagrange Coded Computingcited by 13
- 2021Private Retrieval, Computing and Learning: Recent Progress and Future Challengescited by 12
- 2016A Fundamental Tradeoff between Computation and Communication in Distributed Computingcited by 11
- 2020Entangled Polynomial Codes for Secure, Private, and Batch Distributed Matrix Multiplication: Breaking the "Cubic" Barriercited by 8
- 2020A Survey of Coded Distributed Computingcited by 8
- 2015Coded MapReducecited by 6
- 2018Improving the condition number of estimated covariance matricescited by 4
- 2018Private Polynomial Computation from Lagrange Encodingcited by 3
Built on by
Citing papers per year: 2025: 1.
1 paper.