Distributed Machine Learning and the Semblance of Trust
Not on the map. Why?
Abstract (arXiv)
The utilisation of large and diverse datasets for machine learning (ML) at scale is required to promote scientific insight into many meaningful problems. However, due to data governance regulations such as GDPR as well as ethical concerns, the aggregation of personal and sensitive data is problematic, which prompted the development of alternative strategies such as distributed ML (DML). Techniques such as Federated Learning (FL) allow the data owner to maintain data governance and perform model training locally without having to share their data. FL and related techniques are often described as privacy-preserving. We explain why this term is not appropriate and outline the risks associated with over-reliance on protocols that were not designed with formal definitions of privacy in mind. We further provide recommendations and examples on how such algorithms can be augmented to provide guarantees of governance, security, privacy and verifiability for a general ML audience without prior exposure to formal privacy techniques.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 18 of its 45 references that are in the map. First posted on arXiv 21 Dec 2021.
Builds on
18 of 45 references.
References · 18
- 2016Membership Inference Attacks against Machine Learning Modelscited by 2,221
- 2016Federated Learning: Strategies for Improving Communication Efficiencycited by 1,461
- 2018Federated Learning with Non-IID Datacited by 1,099
- 2019Towards Federated Learning at Scale: System Designcited by 826
- 2018How To Backdoor Federated Learningcited by 745
- 2020Inverting Gradients -- How easy is it to break privacy in federated learning?cited by 707
- 2019Local Model Poisoning Attacks to Byzantine-Robust Federated Learningcited by 479
- 2018Certified Robustness to Adversarial Examples with Differential Privacycited by 462
- 2018Split learning for health: Distributed deep learning without sharing raw patient datacited by 391
- 2019The Secret Revealer: Generative Model-Inversion Attacks Against Deep Neural Networkscited by 241
- 2020Blind Backdoors in Deep Learning Modelscited by 174
- 2019BrainTorrent: A Peer-to-Peer Environment for Decentralized Federated Learningcited by 115
6 more
- 2017CryptoDL: Deep Neural Networks over Encrypted Datacited by 56
- 2017Generative Poisoning Attack Method Against Neural Networkscited by 49
- 2017DeepSecure: Scalable Provably-Secure Deep Learningcited by 48
- 2021Differentially private federated deep learning for multi-site medical image segmentationcited by 12
- 2021NeuraCrypt is not privatecited by 10
- 2021HyFed: A Hybrid Federated Framework for Privacy-preserving Machine Learningcited by 3
Built on by
Citing papers per year: 2023: 1.
1 paper.