A Privacy-Preserving Medical Data Sharing Scheme Based on Blockchain

Xu, Guangquan; Chen, Qi; Dong, Wenyu; Gong, Lixiao; Liu, Shaoying; Chen, Si; Liu, Jian; Zheng, Xi

doi:10.1109/jbhi.2022.3203577

Cited by 33 publications

(12 citation statements)

References 59 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The delay required for serving cloud requests without attacks is a critical performance metric in the evaluation of security models for big data environments. In the provided data, we have compared four different models: STFM [5], DLBI [12], PPQCM [18], and the proposed model MAQSPBT. The delay values (D) are measured in milliseconds (ms) for different request loads, ranging from 45,000 to 450,000 requests.…”

Section: Results Analysis and Comparisonmentioning

confidence: 99%

“…Jitter obtained for serving requests under attacks is a critical metric for assessing the stability and predictability of performance in security models when faced with adversarial conditions. In this analysis, we compare four different models: STFM [5], DLBI [12], PPQCM [18], and the proposed model MAQSPBT. Jitter values (J) are measured in milliseconds (ms) for various request loads, ranging from 45,000 to 450,000 requests, with approximately 10% of these requests simulated as attack requests.…”

Section: Analysis Of the Model Under Attacksmentioning

confidence: 99%

“…Despite the convenience and benefits of cloud services, concerns about security vulnerabilities remain one of the primary obstacles to universal adoption under real-time use cases [4,5,6]. The multiple layers of cloud architecture-from data storage and transfer to user access and authentication-each come with their own set of risks, making it critical to have a comprehensive approach to security process [7,8,9].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

IBMESR: Towards Next-Generation Big Data Security with An Integrated Blockchain Model for Efficient, Scalable, and Robust Operations

Tota,

Karmore

2023

Preprint

View full text Add to dashboard Cite

As the utilization of big data environments becomes increasingly widespread, the demand for robust and efficient security mechanisms within this context becomes paramount, especially in real-time scenarios. Ensuring data integrity, trust, and availability in multi-cloud environments is of utmost importance. Existing solutions often fall short in these aspects, resulting in issues such as latency, energy inefficiency, and vulnerability to access attacks, among other drawbacks. Traditional security models designed for big data environments tend to rely on ineffective proof mechanisms and static encryption methods. These conventional approaches lead to increased data processing delays, heightened energy consumption, and reduced communication throughput. Furthermore, these existing models have demonstrated limited capabilities in accurately identifying unauthorized access attempts, thereby escalating security risks. This paper introduces an innovative security framework tailored for big data environments, which leverages a suite of cutting-edge technologies to address the limitations of current models. The proposed architecture integrates several key components, including a Proof of Spatial & Temporal Trust-based Blockchain for secure storage operations, Grey Wolf Optimization (GWO) for efficient blockchain sharding, Fully Homomorphic Encryption (FHE) for safeguarding data across various data nodes, Physical Unclonable Functions (PuFs) for resilient inter-data node communications, and Fuzzy Rule-Based Access Control to enhance overall security. Our research results demonstrate that this proposed model significantly mitigates the inefficiencies and vulnerabilities that currently plague big data security systems. Specifically, it achieves an 8.3% reduction in data processing delays, a 4.5% reduction in energy consumption, a 2.9% improvement in communication throughput, an 8.5% enhancement in the accuracy of detecting access attacks, and a 3.5% increase in access speed levels. This innovative security framework tailored for big data environments offers a comprehensive and effective approach to overcome the limitations of existing solutions. It represents a significant advancement in the field of big data security, contributing significantly to ongoing efforts aimed at creating more secure, efficient, and resilient big data ecosystems.

show abstract

Section: Results Analysis and Comparisonmentioning

confidence: 99%

Section: Analysis Of the Model Under Attacksmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

IBMESR: Towards Next-Generation Big Data Security with An Integrated Blockchain Model for Efficient, Scalable, and Robust Operations

Tota,

Karmore

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Every piece of data, once recorded on the blockchain, is virtually immutable. Any attempt to change a data block requires the consensus of the majority of participants in the network, ensuring that records remain pristine and unchanged [14] , [15] .…”

Section: Related Workmentioning

confidence: 99%

Dual blockchain-based data sharing mechanism with privacy protection for medical internet of things

Liu,

et al. 2024

Heliyon

View full text Add to dashboard Cite

“…The data itself is sensitive, and must be kept private and secure. 9,10 In particular, regulations concerning medically vulnerable populations, rare diseases, and potential misuse of research data create a complex landscape to navigate for aggregating training data.…”

mentioning

confidence: 99%

Federated learning in computational pathology: classification of tall cell patterns in papillary thyroid carcinoma

Shukla,

Brandwein-Weber,

Samankan

et al. 2024

Medical Imaging 2024: Digital and Computational Pathology

View full text Add to dashboard Cite

This paper presents an exploration of Federated Learning (FL) in medical imaging, focusing on Computational Pathology (CP) with Whole Slide Images (WSIs) for head and neck cancer. While previous FL approaches in healthcare targeted radiology, genetics, and Electronic Health Records (EHRs), our research addresses the understudied area of CP datasets. Our aim is to develop robust AI models for CP datasets without sacrificing data privacy and security. To this end, we demonstrate the use of FL applied to a CP dataset consisting of papillary thyroid carcinoma, specifically focusing on the rare and aggressive variant called Tall Cell Morphology (TCM). Patients with TCM require more aggressive treatment and rigorous follow-up due to its aggressiveness and increased recurrence rates. In this work, we perform a simulated FL training experiment by dividing a dataset into three virtual "clients". We locally train a Convolutional Neural Network (CNN), to classify patches of tissue labelled from the local WSI dataset as "tall" (expressing TCM) or "non-tall". Models are then aggregated and convergence is ensured through the Federated Averaging (FedAVG) algorithm. The decentralized approach of FL creates a secure and privacy-preserving collaborative training environment, keeping individual client data local through horizontal data partitioning. This enables collective training of deep learning models on distributed data, benefiting from a diverse and rich dataset while safeguarding patient privacy. We compare the efficacy of the FL-trained model to a centralized model (trained using all "client" data together) using accuracy, sensitivity, specificity, and F-1 score. Our findings indicate that the simulated FL models exhibit performance on par with or superior to centralized learning, achieving accuracy scores between 75-87%, while centralized learning attains an accuracy of 82%. This novel approach holds promise for revolutionizing computational pathology and contributing to more effective medical decision-making.

show abstract

A Privacy-Preserving Medical Data Sharing Scheme Based on Blockchain

Cited by 33 publications

References 59 publications

IBMESR: Towards Next-Generation Big Data Security with An Integrated Blockchain Model for Efficient, Scalable, and Robust Operations

IBMESR: Towards Next-Generation Big Data Security with An Integrated Blockchain Model for Efficient, Scalable, and Robust Operations

Dual blockchain-based data sharing mechanism with privacy protection for medical internet of things

Federated learning in computational pathology: classification of tall cell patterns in papillary thyroid carcinoma

Contact Info

Product

Resources

About