Collaborative Machine Learning: Schemes, Robustness, and Privacy
- 26 May 2022
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 34 (12) , 9625-9642
Abstract
Distributed machine learning (ML) was originally introduced to solve a complex ML problem in a parallel way for more efficient usage of computation resources. In recent years, such learning has been extended to satisfy other objectives, namely, performing learning in situ on the training data at multiple locations and keeping the training datasets private while still allowing sharing of the model. However, these objectives have led to considerable research on the vulnerabilities of distributed learning both in terms of privacy concerns of the training data and the robustness of the learned overall model due to bad or maliciously crafted training data. This article provides a comprehensive survey of various privacy, security, and robustness issues in distributed ML.Keywords
Funding Information
- National Natural Science Foundation of China (62072485)
- Basic and Applied Basic Research Foundation of Guangdong Province (2022A1515011294)
This publication has 81 references indexed in Scilit:
- Distributed event-triggered control of multi-agent systems with combinational measurementsAutomatica, 2013
- Evasion Attacks against Machine Learning at Test Time2013
- A survey of methods for distributed machine learningProgress in Artificial Intelligence, 2012
- Parallel Graph-Based Semi-Supervised Learning2011
- PSVM: Parallelizing Support Vector Machines on Distributed Computers2011
- Introduction to Semi-Supervised LearningSynthesis Lectures on Artificial Intelligence and Machine Learning, 2009
- Biconvex sets and optimization with biconvex functions: a survey and extensionsMathematical Methods of Operations Research, 2007
- A Fast Parallel Clustering Algorithm for Large Spatial Databases2006
- Scalable Density-Based Distributed Clustering2004
- DBDC: Density Based Distributed Clustering2004