A Blockchain‐Based Federated Learning Method for Smart Healthcare

Chang, Yuxia; Chen, Fang; Sun, Wenzhao

doi:10.1155/2021/4376418

Cited by 63 publications

(41 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…While an alternate block is generated after the verification procedure is completed, the parameters are obtained by the clients or the local models. Thus the medical data through the blockchain and Federated Learning security is ensured, and an efficient model can be assured [232].…”

Section: Applying Fl-blockchain For Accessing Medical Datamentioning

confidence: 99%

Federated learning-based AI approaches in smart healthcare: concepts, taxonomies, challenges and open issues

et al. 2022

View full text Add to dashboard Cite

Federated Learning (FL), Artificial Intelligence (AI), and Explainable Artificial Intelligence (XAI) are the most trending and exciting technology in the intelligent healthcare field. Traditionally, the healthcare system works based on centralized agents sharing their raw data. Therefore, huge vulnerabilities and challenges are still existing in this system. However, integrating with AI, the system would be multiple agent collaborators who are capable of communicating with their desired host efficiently. Again, FL is another interesting feature, which works decentralized manner; it maintains the communication based on a model in the preferred system without transferring the raw data. The combination of FL, AI, and XAI techniques can be capable of minimizing several limitations and challenges in the healthcare system. This paper presents a complete analysis of FL using AI for smart healthcare applications. Initially, we discuss contemporary concepts of emerging technologies such as FL, AI, XAI, and the healthcare system. We integrate and classify the FL-AI with healthcare technologies in different domains. Further, we address the existing problems, including security, privacy, stability, and reliability in the healthcare field. In addition, we guide the readers to solving strategies of healthcare using FL and AI. Finally, we address extensive research areas as well as future potential prospects regarding FL-based AI research in the healthcare management system.

show abstract

Section: Applying Fl-blockchain For Accessing Medical Datamentioning

confidence: 99%

Federated learning-based AI approaches in smart healthcare: concepts, taxonomies, challenges and open issues

et al. 2022

View full text Add to dashboard Cite

show abstract

“…The client uses the interface programming environment to form a transaction proposal, which includes the channel name, the chained code name, and the input parameters of the code to be executed. The customer then sends a transaction proposal to all prospective escorts to satisfy the validation policy of that chain code [ 5 , 23 ]. The peers simulate the transaction based on the parameters received by the customer, interacting with the chain code to record the updates and produce results in the form of a read and write set following the set signature and returning the results to the customer.…”

Section: Proposed Prototypementioning

confidence: 99%

Combination of Blockchain and AI for Music Intellectual Property Protection

2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

In the last two years, due to the pandemic and restrictive measures, the dependence of music creators and artists on the Internet, where they could promote their work, organize live streaming concerts, and talk to the public, has increased and expanded even more and seeks higher revenue from digital music platforms. An important issue that arises from the above statement is protecting the authors’ copyright regarding the uses and sharing in the digital services of their works with protected content. Although circulated in digital information, the protected content is not information but a product of ethical and commercial value. While it has an intangible owner and it owes its existence to the creative idea of its creator, it is not an idea. The imposition of legal and commercial conditions on its movement cannot be associated with any restrictions on the free movement of information, as it is not related to them. In general, the unauthorized exchange of digital music files via peer-to-peer violates copyright law. The exchange of files is unauthorized, as it does not have the relevant permission from the creators and beneficiaries and is therefore illegal. With this in mind, this paper proposes a highly effective way of protecting the copyright of music technology, which is based on the widespread use of artificial intelligence, blockchain, and cryptography technologies. Specifically, an advanced blockchain model based on Hyperledger Fabric is introduced, which, however, uses Quantum Homomorphic Encryption and Quantum Zero-Knowledge Arguments. Music files are implemented as Nonfungible Tokens (NFTs), which activate smart contracts. Finally, an advanced collaborative filtering algorithm provides recommendations for effectiveness in securing the copyrights of music industry creators. A specialized scenario was built to model the proposed system to verify the degree of protection on music intellectual property in developing a security simulation with an innovative consensus-based zero knowledge and the quantum fully homomorphic encryption technique. Experiment results show that this technique can aid in implementing a technologically aware system capable of providing a powerful answer to a current real-world problem.

show abstract

“…Differential privacy Differential Privacy (DP) is a technology developed to combine two con icting concepts: privacy and data learning. DP aims to utilize useful information from data, however, it does not focus on learning anything from the data itself [35]. The primary purpose of DP is to share data.…”

Section: Privacy Protection Technologies I Blockchainmentioning

confidence: 99%

“…Research on differential privacy technologies is often aimed at developing privacy capabilities by assisting technologies other than direct and primary use technologies. Major privacy protection technologies include blockchain [35,41], combined learning [35][36][37], deep learning [38,44], binary classi cation [39,42], and data sharing [40,43]. Differential privacy is applied to these technologies in research because each technology has limitations in protecting personal information.…”

Section: Privacy Protection Technologies I Blockchainmentioning

confidence: 99%

“…Differential privacy is applied to these technologies in research because each technology has limitations in protecting personal information. For example, federated learning requires the use of a central server for data learning and data movement, which allows an attacker to launch a single point of failure attack that attacks the central server and in blockchain technology, it is a challenge to overcome attacks by malicious participants [35]. Therefore, two or three technologies are often combined to prevent the leakage of personal information that can occur when only one technology is used.…”

Section: Privacy Protection Technologies I Blockchainmentioning

confidence: 99%

See 1 more Smart Citation

Application of privacy protection technology to healthcare big data

Shin

Ryu

Kim

et al. 2022

Preprint

View full text Add to dashboard Cite

With the emergence of the 4th industrial revolution, demand for technologies that process and analyze big data in the healthcare has increased. As research is actively conducted, problems related to the protection of personal information included in healthcare data are being raised. We investigated privacy protection technology and their limitations applied to healthcare big data over the last decade to find solutions to these problems. For 4 technologies, blockchain, federated learning, differential privacy, and homomorphic encryption, we reviewed 10 studies each and summarized the used data, key findings, and limitations. It is necessary to establish a research environment that can utilize healthcare data, including sensitive personal and medical information of patients, more safely and widely by grasping the cases and current status of privacy protection technology. We aim to provide opinions on future research directions and insights of privacy protection technology to relevant researchers through this study.

show abstract

A Blockchain‐Based Federated Learning Method for Smart Healthcare

Cited by 63 publications

References 25 publications

Federated learning-based AI approaches in smart healthcare: concepts, taxonomies, challenges and open issues

Federated learning-based AI approaches in smart healthcare: concepts, taxonomies, challenges and open issues

Combination of Blockchain and AI for Music Intellectual Property Protection

Application of privacy protection technology to healthcare big data

Contact Info

Product

Resources

About