DS2PM: A Data-Sharing Privacy Protection Model Based on Blockchain and Federated Learning

Chen, Yanru; Li, Jingpeng; Wang, Fan; Yue, Kaifeng; Li, Yang; Xing, Bin; Zhang, Lei; Chen, Liangyin

doi:10.1109/jiot.2021.3134755

Cited by 24 publications

(7 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(4) Blockchain Consensus Mechanism: Enhancing consensus efficiency facilitates the completion of FL tasks at a faster rate. By considering RSU's historical contributions, we incorporated a consensus based on the delegated Byzantine fault-tolerant algorithm (dBFT) [38] in this paper. The dBFT is a consensus developed based on the PBFT.…”

Section: Global Model Update and Blockchain Consensusmentioning

confidence: 99%

Improving Security in the Internet of Vehicles: A Blockchain-Based Data Sharing Scheme

Wang,

Guan

2024

Electronics

View full text Add to dashboard Cite

To ensure the aggregation of a high-quality global model during the data-sharing process in the Internet of Vehicles (IoV), current approaches primarily utilize gradient detection to mitigate malicious or low-quality parameter updates. However, deploying gradient detection in plain text neglects adequate privacy protection for vehicular data. This paper proposes the IoV-BDSS, a novel data-sharing scheme that integrates blockchain and hybrid privacy technologies to protect private data in gradient detection. This paper utilizes Euclidean distance to filter the similarity between vehicles and gradients, followed by encrypting the filtered gradients using secret sharing. Moreover, this paper evaluates the contribution and credibility of participating nodes, further ensuring the secure storage of high-quality models on the blockchain. Experimental results demonstrate that our approach achieves data sharing while preserving privacy and accuracy. It also exhibits resilience against 30% poisoning attacks, with a test error rate remaining below 0.16. Furthermore, our scheme incurs a lower computational overhead and faster inference speed, markedly reducing experimental costs by approximately 26% compared to similar methods, rendering it suitable for highly dynamic IoV systems with unstable communication.

show abstract

Section: Global Model Update and Blockchain Consensusmentioning

confidence: 99%

Improving Security in the Internet of Vehicles: A Blockchain-Based Data Sharing Scheme

Wang,

Guan

2024

Electronics

View full text Add to dashboard Cite

show abstract

“…relevant to this study's exploration of privacy in distributed networks. Chen et al [24] discussed a datasharing privacy protection model combining blockchain and federated learning [24], directly aligning with the current research's focus.…”

Section: Kus and Levimentioning

confidence: 99%

PMNBARL: Enhancing Efficiency of Privacy Management in Digital Networks through Blockchain and Adaptive Reinforcement Learning

Research,

Bhaladhare,

Potgantwar

2024

Preprint

View full text Add to dashboard Cite

The urgent need for advanced privacy mechanisms in the digital era is underscored by the growing concerns over data breaches and privacy invasions. Traditional privacy management methods often fall short in addressing these challenges, primarily due to their static nature and limited adaptability to evolving cyber threats. This work presents an efficient method to privacy management by integrating blockchain technology with adaptive privacy mechanisms, leveraging the power of machine learning (ML) and deep learning (DL) algorithms. Existing privacy management systems are predominantly rigid, offering limited scope for dynamic adaptation to changing network conditions and user behaviors. Such systems are increasingly inadequate in handling the complexities of modern data environments, often leading to compromised data confidentiality and higher instances of unauthorized data access or policy violations for different use cases. In response, this paper introduces an innovative model that employs smart contracts on the blockchain for privacy policy enforcement operations. These smart contracts ensure secure, transparent, and immutable privacy management, markedly enhancing data confidentiality and reducing policy violations under different attacks. Furthermore, the application of Reinforcement Learning (RL), enables dynamic privacy policy management operations. RL's ability to learn and adjust policies adaptively in response to environmental feedback ensures improved responsiveness and efficiency in privacy settings. A novel aspect of this work is the integration of Anomaly Detection using Deep Neural Networks (DNNs) with blockchain technology for self-adaptive security. DNNs' proficiency in identifying complex patterns in large datasets allows for the early detection of privacy breaches, enhancing the overall security performance levels. Additionally, the implementation of Differential Privacy in Federated Learning addresses the challenge of preserving data privacy during collective model training, thus ensuring robust privacy protection operations. The proposed methods were tested on various real-time simulation datasets, showcasing superior performance over existing methods in terms of energy efficiency, speed, throughput, consistency, and packet delivery ratio sets. This work not only presents a significant advancement in privacy management but also sets a new standard for future research in the field of data privacy and security levels.

show abstract

“…Current challenges in data sharing and privacy protection in computational pharmaceutics include difficulties in safeguarding data integrity, privacy, and ownership (Chen et al, 2023), regulatory and institutional challenges in addressing data breaches and misuse, and the evolving landscape of data collection and privacy laws (Dankar, 2023). To address these challenges, a datasharing privacy protection model (DS2PM) based on blockchain and federated learning mechanisms has been proposed, showing superior performance in ensuring data security and integrity.…”

Section: A Lack Of Sufficient Data and Challenges In Data Sharingmentioning

confidence: 99%

Computational Pharmaceutics: A Comprehensive Review of Past Achievements, Present Applications, and Future Challenges

Chaudhari,

Puri

et al. 2024

Preprint

View full text Add to dashboard Cite

This paper explores the transformative impact of computational pharmaceutics, integrating AI, multi-scale modeling, quantum computing, AI-driven drug discovery, and blockchain frameworks. Molecular dynamics simulations provide insights into atomic behaviors crucial for drug design. Quantum computing reduces computational costs for simulating protein-drug interactions. AI and Graph Neural Networks accelerate drug discovery and personalized medicine. Blockchain frameworks facilitate secure pharmacogenetic data sharing. These advancements revolutionize drug development, offering unprecedented efficiency, innovation, and personalized treatments.

show abstract

DS2PM: A Data-Sharing Privacy Protection Model Based on Blockchain and Federated Learning

Cited by 24 publications

References 21 publications

Improving Security in the Internet of Vehicles: A Blockchain-Based Data Sharing Scheme

Improving Security in the Internet of Vehicles: A Blockchain-Based Data Sharing Scheme

PMNBARL: Enhancing Efficiency of Privacy Management in Digital Networks through Blockchain and Adaptive Reinforcement Learning

Computational Pharmaceutics: A Comprehensive Review of Past Achievements, Present Applications, and Future Challenges

Contact Info

Product

Resources

About