A Differential Privacy Framework for Federated Learning
Abstract
Federated Learning (FL) has emerged as a promising paradigm for training machine learning models on decentralized data, addressing privacy concerns by keeping data localized. However, traditional FL approaches often lack robust privacy protection, exposing sensitive user information during model aggregation. This paper proposes a novel framework integrating Differential Privacy (DP) into the FL process. Our framework introduces a DP mechanism within the model aggregation step, guaranteeing that the aggregated model does not reveal information about any individual user's data. We formally define the framework and analyze its privacy-utility trade-off, demonstrating improved privacy guarantees compared to standard FL. This work provides a significant step towards realizing truly private and secure FL systems.
Read the paper
Related studies
- Active Learning during Federated Learning for Object Detection
- Fairness-aware federated learning
- Decentralized Federated Learning
- Building a Personally Identifiable Information Recognizer in a Privacy Preserved Manner Using Automated Annotation and Federated Learning
- Preservation of Patient Level Privacy: Federated Classification and Calibration Models
- Efficient explainable federated learning
Go deeper in Evidence Hub
Evidence Hub adds a study data sheet (design, sample size, evidence level, key numbers), an AI summary and a chat grounded in the paper's text.