A group key exchange and secure data sharing based on privacy protection for federated learning in edge-cloud collaborative computing environment

Article Computer Science, Artificial Intelligence

A fine-grained and traceable multidomain secure data-sharing model for intelligent terminals in edge-cloud collaboration scenarios

Haipeng Sun et al.

Summary: The proposed secure data-sharing model for intelligent terminals in multi-domain settings ensures fine-grained and traceable sharing of data through key self-certification algorithm and blockchain technology.

INTERNATIONAL JOURNAL OF INTELLIGENT SYSTEMS (2022)

Add to Collection

Article Computer Science, Artificial Intelligence

Privacy-preserving federated learning based on multi-key homomorphic encryption

Jing Ma et al.

Summary: With the advancement of machine learning and IoT, security and privacy have become critical concerns. This paper proposes an improved federated learning scheme, which encrypts model updates and requires collaboration among participating devices to prevent privacy leakage.

INTERNATIONAL JOURNAL OF INTELLIGENT SYSTEMS (2022)

Add to Collection

Article Computer Science, Hardware & Architecture

Auditable attribute-based data access control using blockchain in cloud storage

V. Ezhil Arasi et al.

Summary: This paper proposes an auditable attribute-based encryption scheme that integrates blockchain technology with attribute-based access control to address the issues in traditional cloud data sharing systems. It provides efficient and secure data sharing, reliable traceability, and fair mediation.

JOURNAL OF SUPERCOMPUTING (2022)

Add to Collection

Article Engineering, Electrical & Electronic

Federated Learning-Based Collaborative Authentication Protocol for Shared Data in Social IoV

Pengcheng Zhao et al.

Summary: This paper proposes a collaborative authentication protocol for federated learning to protect the private data of vehicle clients and reduce data transmission delay in the Social Internet of Vehicles. By encrypting the parameters of the vehicle client model and implementing efficient anonymous mutual authentication and key agreement, the protocol effectively prevents data leakage and resolves overfitting of the globally aggregated model.

IEEE SENSORS JOURNAL (2022)

Add to Collection

Article Automation & Control Systems

Blockchain-Enabled Federated Learning Data Protection Aggregation Scheme With Differential Privacy and Homomorphic Encryption in IIoT

Bin Jia et al.

Summary: This article presents a blockchain-enabled federated learning application model and data protection methods based on differential privacy and homomorphic encryption. Experimental results demonstrate that the method has better performance in data sharing and model sharing.

IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS (2022)

Add to Collection

Article Computer Science, Artificial Intelligence

A blockchain-enabled learning model based on distributed deep learning architecture

Yang Zhang et al.

Summary: This study proposes a learning model based on distributed deep learning and blockchain architecture to address the performance issues of existing architectures, achieving promising results in experiments.

INTERNATIONAL JOURNAL OF INTELLIGENT SYSTEMS (2022)

Add to Collection

Article Automation & Control Systems

CeCO: Cost-Efficient Computation Offloading of IoT Applications in Green Industrial Fog Networks

Abhishek Hazra et al.

Summary: This article proposes a computation offloading framework for industrial networks called cost-efficient computation offloading (CeCO) to reduce the cost and energy consumption of smart industrial IoT devices. By designing a cost optimization function and using frequency control mechanism, controller-based device adaptation strategy and policy-based reinforcement learning technique, the CeCO strategy achieves up to 13%-18% improvement in cost utilization and performance maximization for industrial applications.

IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS (2022)

Add to Collection

Article Engineering, Multidisciplinary

Intelligent Service Deployment Policy for Next-Generation Industrial Edge Networks

Abhishek Hazra et al.

Summary: This paper aims to design an intelligent service deployment strategy for handling dynamic service requests and edge resources in Industrial Internet of Things (IIoT) networks. By utilizing a heuristic-based task execution strategy and Deep Reinforcement Learning (DRL), the proposed strategy can learn and control the industrial networks, efficiently handling as many service requests as possible by utilizing available edge servers.

IEEE TRANSACTIONS ON NETWORK SCIENCE AND ENGINEERING (2022)

Add to Collection

Article Computer Science, Information Systems

A Cross-Domain Authentication Optimization Scheme between Heterogeneous IoT Applications

Shichang Xuan et al.

Summary: This article proposes a cross-domain authentication scheme based on certificate-less public key cryptography and smart contract technology, supporting parameter differentiation, which improves cross-domain identity authorization authentication ability.

WIRELESS COMMUNICATIONS & MOBILE COMPUTING (2021)

Add to Collection

Article Computer Science, Hardware & Architecture

A secure and efficient authentication and data sharing scheme for Internet of based on blockchain

Qing Fan et al.

Summary: Internet of Things (IoT) is a network convergence of multiple intelligent devices and advanced technologies aiming at connecting and exchanging data over the Internet. Security issues such as authentication and data privacy are critical concerns in IoT applications, and blockchain technology supports secure data sharing. An improved scheme has been proposed to overcome security flaws and achieve a well tradeoff between security and efficiency.

JOURNAL OF SYSTEMS ARCHITECTURE (2021)

Add to Collection

Article Telecommunications

Pairing Free Certified Common Asymmetric Group Key Agreement Protocol for Data Sharing Among Users with Different Access Rights

An Braeken

Summary: The research introduces a new protocol - the CAGKA protocol - which aims to more effectively address the data protection requirements in epidemiological research by sharing the same private-public key pair.

WIRELESS PERSONAL COMMUNICATIONS (2021)

Add to Collection

Proceedings Paper Computer Science, Theory & Methods

Secure Decentralized Access Control Policy for Data Sharing in Smart Grid

Yadi Ye et al.

Summary: Smart grid has enhanced the security and efficiency of the power system through intelligent management, but it may lead to issues such as leakage of user privacy and loss of data control rights. Existing solutions have limitations, and this paper introduces a decentralized attribute-based data sharing scheme to address these problems.

IEEE CONFERENCE ON COMPUTER COMMUNICATIONS WORKSHOPS (IEEE INFOCOM WKSHPS 2021) (2021)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

An Efficient Anonymous Authentication Scheme for Medical Services Based on Blockchain

Shu Wu et al.

Summary: Telemedicine is a rapidly developing field in healthcare, and our proposed scheme efficiently combines blockchain and biometric technology for patient and server authentication, achieving better experimental performance in both computation and communication efficiencies.

2021 INTERNATIONAL CONFERENCE ON CYBER-PHYSICAL SOCIAL INTELLIGENCE (ICCSI) (2021)

Add to Collection

Proceedings Paper Computer Science, Software Engineering

Access Control Tree for Testing and Learning

Davrondzhon Gafurov et al.

Summary: Our work focuses on testing the access control of a large national e-health Internet portal with millions of monthly visits. We aim to improve testing by applying systematic and rigorous approaches, while also obtaining a holistic view of the portal's complex access control structure. By using a set-theoretic approach and visualizing it as an access control tree, we are able to better understand the attributes and values that influence access, resulting in over 2000 pairs of abstract test scenarios implemented into 600 automated test cases. The access control tree not only speeds up testing processes significantly, but also serves as a valuable collaboration and learning tool for better familiarity with the solution.

2021 36TH IEEE/ACM INTERNATIONAL CONFERENCE ON AUTOMATED SOFTWARE ENGINEERING ASE 2021 (2021)

Add to Collection

Proceedings Paper Computer Science, Hardware & Architecture

FLRA: A Reference Architecture for Federated Learning Systems

Sin Kit Lo et al.

Summary: Federated learning is a new machine learning paradigm that allows multiple devices to train models locally and formulate a global model without sharing local data, necessitating considerations of software system design and machine learning knowledge. The FLRA reference architecture proposed in this paper provides a template design for federated learning-based solutions, based on a review of existing patterns in literature and industrial implementations.

SOFTWARE ARCHITECTURE, ECSA 2021 (2021)

Add to Collection

Article Computer Science, Interdisciplinary Applications

Privacy protection in government data sharing: an improved LDP-based approach

Chunhui Piao et al.

Summary: The article discusses privacy protection issues in government data sharing and proposes an improved LDP approach that combines data binning techniques with CMS algorithms to protect data. Experimental results show that this method effectively reduces statistical errors and enhances the utility of data.

SERVICE ORIENTED COMPUTING AND APPLICATIONS (2021)

Add to Collection

Article Computer Science, Information Systems