Abstract
The development of artificial intelligence and worldwide epidemic events has promoted the implementation of smart healthcare while bringing issues of data privacy, malicious attack, and service quality. The Medical Internet of Things (MIoT), along with the technologies of federated learning and blockchain, has become a feasible solution for these issues. In this paper, we present a blockchain-based federated learning method for smart healthcare in which the edge nodes maintain the blockchain to resist a single point of failure and MIoT devices implement the federated learning to make full of the distributed clinical data. In particular, we design an adaptive differential privacy algorithm to protect data privacy and gradient verification-based consensus protocol to detect poisoning attacks. We compare our method with two similar methods on a real-world diabetes dataset. Promising experimental results show that our method can achieve high model accuracy in acceptable running time while also showing good performance in reducing the privacy budget consumption and resisting poisoning attacks.
Highlights
With the growth in volume and types of clinical data, there is an urgent need for efficient mining models to analyze these data so as to help disease diagnosis, provide medical solutions, and improve the medical care for patients
(2) To add an extra layer of security of blockchain-based Federated learning (FL), we propose adaptive differential privacy (DP) algorithm that adapts noise according to the training process, balancing privacy, and model accuracy
Our method limits the attack success rate to less than 20% in the later stage of training, and experimental data shows that four MIoT devices have been put into the blacklist at the end of the training, indicating that the consensus protocol based on gradient verification we design can effectively resist a certain proportion of poisoning attack
Summary
With the growth in volume and types of clinical data, there is an urgent need for efficient mining models to analyze these data so as to help disease diagnosis, provide medical solutions, and improve the medical care for patients. A typical FL-based smart healthcare application is shown, where onboard sensors collect clinical data from patients, multiple edge devices perform FL algorithm collaboratively, and the final machine learning models evaluate the patient’s physical health and even request the emergency service in the cloud if necessary. As a ledger with properties of tamper-proof, collective maintenance, and traceability, blockchain can replace the central server to decentralize the coordination process in FL, resisting single points of failure and illegal tampering attacks In this way, the traditional elements in blockchain can be mapped into the training stages of FL as follows: each block represents a single training round, where the stored transactions represent model parameters uploaded by devices in that round.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
