In this paper, we propose an adaptable heterogeneous Blockchain-based Personalized Federated Learning approach with Model Similarity (BPFL-MS). We first introduce a two-layer network framework and then conduct an in- ...

To address the security and privacy concerns associated with medical data in the IoMT scenario, we propose a blockchain-based personalized federated learning system that enables the global model to be trained collaboratively among distributed devices while keeping private patient data locally.

A robust and generalizable privacy-preserving personalized federal learning method for heterogeneous medical image analysis. •. A novel decentralized cyclic secure aggregation mechanism with homomorphic encryption. •. PPPML-HMI has demonstrated high performance and robustness in two real-life cases.

In this context, we propose a novel personalized federated learning (pFL) with blockchain-assisted semi-centralized framework, pFedBASC. This approach, tailored for the Internet of Things (IoT) scenarios, constructs a semi-centralized IoT structure and utilizes trusted network connections to support FL.

Jun 22, 2024 · BDFL [18] aims at privacy preservation in autonomous vehicles using the HyRand protocol, facing scalability challenges. In IoHT, a multi-agent system [95] secures medical data processing with real-time capabilities, hindered by latency.

Jan 7, 2024 · It systematically explores Blockchain fundamentals and Federated Learning along with its categorization. It delves into relevant literature on privacy attacks and protection methods in BCFL. Moreover, it highlights the essential need for privacy preservation in BCFL-focused applications across ...

Jun 20, 2024 · A tight BCFL enabled data sharing with flexible privacy enhancing. We propose a decentralized IoT data-sharing process enabled by the tightly-coupled BCFL. In particular, we enhance privacy protection by introducing a personalized differential privacy (PDP) algorithm during the training phases.

Furthermore, endangering human life is what happens when a medical machine learning system is tricked or hacked. As a result, robust protections against cyberattacks are essential in the medical sector. This research uses two technologies, namely federated learning and blockchain, to solve these problems.

Missing: Personalized | Show results with:Personalized

The concept of FL was initially invented by Google, primarily for locally training ML models on devices, with the benefit of providing additional privacy preservation. This invention is motivated by the issues associated with centralized ML. Furthermore, the distributed nature of IoT devices and their reasonable ...