RECORD
Reliability Check via Weight Similarity in Privacy-Preserving Multi-Party Machine Learning
Machine Learning · Submitted 14 Jan 2021
abstract compiled · 2026-09-23 · no language-model review
The authors' main claim The analytical and experimental evaluations of our scheme demonstrate that it is accurate and ensures data and model privacy.
The compiled record
The paper's own sentences, arranged. Each label is drawn from a closed vocabulary; the number beside it is the probability the classifier gave that label. Numbers in the tables are the authors', checked by code. No sentence in this record was written by a model.
Open the compiled record
The abstract, sentence by sentence
Multi-party machine learning is a paradigm in which multiple participants collaboratively train a machine learning model to achieve a common learning objective without sharing their privately owned data. The paradigm has recently received a lot of attention from the research community aimed at addressing its associated privacy concerns. In this work, we focus on addressing the concerns of data privacy, model privacy, and data quality associated with privacy-preserving multi-party machine learning, i.e., we present a scheme for privacy-preserving collaborative learning that checks the participants' data quality while guaranteeing data and model privacy. In particular, we propose a novel metric called weight similarity that is securely computed and used to check whether a participant can be categorized as a reliable participant (holds good quality data) or not. The problems of model and data privacy are tackled by integrating homomorphic encryption in our scheme and uploading encrypted weights, which prevent leakages to the server and malicious participants, respectively. The analytical and experimental evaluations of our scheme demonstrate that it is accurate and ensures data and model privacy.
background contribution method result interpretation main claim
| # | sentence | role | the authors' own work | states the main conclusion | strength |
|---|---|---|---|---|---|
| s0 | Multi-party machine learning is a paradigm in which multiple participants collaboratively train a machine learning model to achieve a common learning objective without sharing their privately owned data. | background 1.00 | 0.04 | 0.02 | asserted 1.00 |
| s1 | The paradigm has recently received a lot of attention from the research community aimed at addressing its associated privacy concerns. | background 1.00 | 0.03 | 0.02 | asserted 1.00 |
| s2 | In this work, we focus on addressing the concerns of data privacy, model privacy, and data quality associated with privacy-preserving multi-party machine learning, i.e., we present a scheme for privacy-preserving collaborative learning that checks the participants' data quality while guaranteeing data and model privacy. | contribution 0.99 | 0.81 | 0.18 | asserted 0.99 |
| s3 | In particular, we propose a novel metric called weight similarity that is securely computed and used to check whether a participant can be categorized as a reliable participant (holds good quality data) or not. | contribution 0.68 | 0.93 | 0.15 | asserted 1.00 |
| s4 | The problems of model and data privacy are tackled by integrating homomorphic encryption in our scheme and uploading encrypted weights, which prevent leakages to the server and malicious participants, respectively. | method 0.99 | 0.87 | 0.07 | asserted 1.00 |
| s5 | The analytical and experimental evaluations of our scheme demonstrate that it is accurate and ensures data and model privacy. | result 0.98 | 0.95 | 0.79 | asserted 1.00 |
What was examined, and what was not
- arXiv listing abstract v1
- full text
- figures and tables
- references and citing sentences
- relations to other papers
- P abstract
- S sections
- T body sentences
- C citations
- R cross-paper relations
The paper
Original abstract
Multi-party machine learning is a paradigm in which multiple participants collaboratively train a machine learning model to achieve a common learning objective without sharing their privately owned data. The paradigm has recently received a lot of attention from the research community aimed at addressing its associated privacy concerns. In this work, we focus on addressing the concerns of data privacy, model privacy, and data quality associated with privacy-preserving multi-party machine learning, i.e., we present a scheme for privacy-preserving collaborative learning that checks the participants' data quality while guaranteeing data and model privacy. In particular, we propose a novel metric called weight similarity that is securely computed and used to check whether a participant can be categorized as a reliable participant (holds good quality data) or not. The problems of model and data privacy are tackled by integrating homomorphic encryption in our scheme and uploading encrypted weights, which prevent leakages to the server and malicious participants, respectively. The analytical and experimental evaluations of our scheme demonstrate that it is accurate and ensures data and model privacy.
Human review
How the literature uses it
What this paper does with the arXiv papers it cites
What it cites · 1 sentence without a confident label
Cites as background 1 paper
-
Cao et al. [ref] presented a scheme for synchronous and parallel privacy-preserving collaborative learning in which the participants only send their local cost values to the server during global parameter updates.
A Federated Deep Learning Framework for Privacy Preservation and Communication Efficiency · Other Related Works · 0.98
Discussion
Know something about this paper? Leave a comment, or highlight any passage above to comment on it.