The field of federated learning is moving towards developing more robust and privacy-preserving methods for healthcare and other applications where data privacy is a major concern. Recent research has focused on improving the accuracy and efficiency of federated learning models, as well as developing new methods for secure and private data sharing. Notable advancements include the development of novel frameworks for federated learning, such as PQFed and FedDA, which have shown promising results in improving model performance and preserving data privacy. Additionally, researchers have explored the use of techniques such as differential privacy and secure aggregation to protect sensitive data. Overall, the field is advancing towards more secure and efficient federated learning methods that can be applied to a wide range of applications. Noteworthy papers include PQFed, which proposes a novel privacy-preserving personalized federated learning framework, and FedDA, which introduces a feature-level adversarial learning approach for cross-domain federated medical image segmentation.
Advances in Federated Learning for Healthcare and Privacy-Preserving Applications
Sources
Differentially-Private Decentralized Learning in Heterogeneous Multicast Networks
PQFed: A Privacy-Preserving Quality-Controlled Federated Learning Framework
Non-Linear Trajectory Modeling for Multi-Step Gradient Inversion Attacks in Federated Learning
I-ETL: an interoperability-aware health (meta) data pipeline to enable federated analyses
Role-Aware Multi-modal federated learning system for detecting phishing webpages
FedDAPL: Toward Client-Private Generalization in Federated Learning
Adversarial Versus Federated: An Adversarial Learning based Multi-Modality Cross-Domain Federated Medical Segmentation
H+: An Efficient Similarity-Aware Aggregation for Byzantine Resilient Federated Learning
The Open Syndrome Definition
Enhancing Split Learning with Sharded and Blockchain-Enabled SplitFed Approaches
Lightweight and Robust Federated Data Valuation
Federated Learning with Enhanced Privacy via Model Splitting and Random Client Participation
The Average Patient Fallacy
Robust Federated Inference
Adaptive Federated Few-Shot Rare-Disease Diagnosis with Energy-Aware Secure Aggregation
Privacy Preserved Federated Learning with Attention-Based Aggregation for Biometric Recognition
Adaptive Federated Learning Defences via Trust-Aware Deep Q-Networks
Secure Multi-Modal Data Fusion in Federated Digital Health Systems via MCP
Private Federated Multiclass Post-hoc Calibration
FRIEREN: Federated Learning with Vision-Language Regularization for Segmentation