Accessibility of covariance information creates vulnerability in Federated Learning frameworks
Related Experiment Video
Updated: Jul 17, 2025

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
Published on: December 6, 2024
Manuel Huth1,2, Jonas Arruda2, Roy Gusinow1,2
1Institute of Computational Biology, Helmholtz Munich, Neuherberg 85764, Germany.
Motivation:
Federated Learning (FL) is gaining traction in various fields as it enables integrative data analysis without sharing sensitive data, such as in healthcare. However, the risk of data leakage caused by malicious attacks must be considered. In this study, we introduce a novel attack algorithm that relies on being able to compute sample means, sample covariances, and construct known linearly independent vectors on the data owner side.
Results:
We show that these basic functionalities, which are available in several established FL frameworks, are sufficient to reconstruct privacy-protected data. Additionally, the attack algorithm is robust to defense strategies that involve adding random noise. We demonstrate the limitations of existing frameworks and propose potential defense strategies analyzing the implications of using differential privacy. The novel insights presented in this study will aid in the improvement of FL frameworks.
Availability And Implementation:
The code examples are provided at GitHub (https://github.com/manuhuth/Data-Leakage-From-Covariances.git). The CNSIM1 dataset, which we used in the manuscript, is available within the DSData R package (https://github.com/datashield/DSData/tree/main/data).
Related Concept Videos
Variability: Analysis
The range is a simple measure of variability, indicating the difference between the highest and...
Propagation of Uncertainty from Systematic Error
Avoidance Learning and Learned Helplessness
Avoidance learning occurs when an organism learns that a specific behavior can prevent an unpleasant outcome. For example, a student who receives a bad grade may start studying harder to avoid future poor grades. This behavior persists even when the negative outcome is no longer present. Avoidance learning is powerful because it maintains behavior in the absence of the...
Uncertainty: Overview
Propagation of Uncertainty from Random Error
Observational Learning

