Privacy Preserved Federated Learning with Optimized Differential Privacy (FL-ODP)
Abstract
Privacy-preserving methods and techniques are aimed at safeguarding the privacy of individuals and groups while facilitating data sharing for specific purposes. Federated Learning (FL) is a machine learning approach that enables multiple devices or systems to collaboratively train a model without directly sharing their data with each other or a central server. To ensure individual data points’ privacy while still enabling the extraction of valuable information, this paper proposes an Optimized Differential Privacy (ODP) approach. The proposed model is validated using the MNIST dataset and analyzed using the FedAvg aggregator. The Differential Privacy (DP) with FL is optimized by varying the noise and delta values. The analysis of data privacy is conducted in three phases: the first phase evaluates simple FL, and the second and third phases utilize different DP parameters to obtain optimized results. The optimized results demonstrate improved accuracy and privacy, establishing the efficacy of the proposed ODP approach.
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.