Related references
Note: Only part of the references are listed.
Article
Computer Science, Hardware & Architecture
Yifeng Zheng et al.
Summary: Federated learning is a new paradigm that utilizes diverse data sources to train high quality models without sharing the training datasets. However, sharing model updates in federated learning still poses privacy risks. In this paper, we propose a system design that protects individual model updates efficiently, allowing clients to provide obscured updates while a cloud server performs aggregation. We also explore bandwidth efficiency optimization and security mechanisms against an adversarial cloud server. Experiments on benchmark datasets show that our system achieves comparable accuracy to the plaintext baseline with practical performance.
IEEE TRANSACTIONS ON DEPENDABLE AND SECURE COMPUTING
(2023)
Article
Computer Science, Artificial Intelligence
Mingrui Cao et al.
Summary: This article introduces a framework called DAG-FL, which leverages a directed acyclic graph (DAG)-based blockchain to enhance federated learning (FL). DAG-FL addresses the challenges of device asynchrony and anomaly detection in FL, while avoiding the extra resource consumption caused by traditional blockchain consensus mechanisms. Extensive simulations and experiments demonstrate that DAG-FL achieves better performance in terms of training efficiency and model accuracy compared to existing on-device FL systems.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Computer Science, Information Systems
Hemant Ghayvat et al.
Summary: The paper proposes a blockchain-based confidentiality-privacy preserving scheme for sensitive analysis, secure communication and authentication in healthcare big data, outperforming traditional schemes in experiments.
IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS
(2022)
Article
Computer Science, Information Systems
Laizhong Cui et al.
Summary: This article introduces a system that combines IoT, edge computing, remote cloud, and blockchain. The authors propose a new algorithm called CREAT, which combines federated learning and blockchain technology to improve cache hit rate and data security.
IEEE INTERNET OF THINGS JOURNAL
(2022)
Article
Computer Science, Hardware & Architecture
Minrui Xu et al.
Summary: This article introduces the application of transfer learning in 6G-enabled Internet of Vehicles (IoV) and designs a secure and reliable framework using reputation evaluation and consortium blockchain. It motivates high-reputation vehicles to participate in model sharing through a deep learning-based auction scheme.
IEEE WIRELESS COMMUNICATIONS
(2022)
Article
Computer Science, Hardware & Architecture
Lei Peng et al.
Summary: The paper introduces a framework that combines blockchain and federated learning to address security and trust issues in FL on mobile edge networks. The framework includes a two-layered architecture with local and global model update chains, as well as a reputation-learning based incentive mechanism to make participant devices more trustworthy.
Article
Engineering, Electrical & Electronic
Weiting Zhang et al.
Summary: This paper aims to optimize the performance of FL in distributed IIoT networks by introducing a collaborative FL architecture and a RoF scheme, proposing a resource allocation strategy for IIoT devices, and verifying its effectiveness through simulation results.
IEEE JOURNAL ON SELECTED AREAS IN COMMUNICATIONS
(2021)
Article
Computer Science, Artificial Intelligence
Tianshu Chu et al.
Summary: Efficient model inference is crucial in deploying deep neural networks on resource constraint platforms, and network quantization effectively addresses this issue by utilizing low-bit representation. By assigning progressively decreasing bitwidth to different layers, a mixed-precision quantized neural network can achieve a better trade-off between accuracy and compression.
PATTERN RECOGNITION
(2021)
Article
Computer Science, Theory & Methods
Yuanhang Qi et al.
Summary: Traffic flow prediction is crucial for traffic management, and federated learning has been introduced as an efficient solution for privacy protection in model updates sharing. A consortium blockchain-based federated learning framework is proposed to achieve decentralized, reliable, and secure federated learning, enhancing privacy protection for traffic flow prediction.
FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE
(2021)
Article
Multidisciplinary Sciences
Mingzhe Chen et al.
Summary: Federated Learning allows edge devices to collaboratively train ML models without sharing private data, but communication delays are a major bottleneck. A communication-efficient framework is proposed, incorporating device selection and parameter quantization to improve convergence speed and training accuracy.
PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA
(2021)
Article
Computer Science, Hardware & Architecture
Paul Duetting et al.
Summary: Designing an incentive compatible auction that maximizes expected revenue is a complex task, with solutions for single-item cases but remains unsolved for settings with multiple items. Recent research shows that utilizing deep learning tools can automate the design of near-optimal auctions.
COMMUNICATIONS OF THE ACM
(2021)
Article
Engineering, Electrical & Electronic
Shuping Dang et al.
Summary: This study introduces an enabling technique of multi-carrier relay selection based on sensing fusion and cascaded artificial neural networks to address the challenges in implementing multi-carrier relay selection. Experimental results demonstrate the promising vision of deploying multi-carrier relay selection rapidly with the powerful processing ability of intelligent vehicles.
IEEE SENSORS JOURNAL
(2021)
Article
Engineering, Electrical & Electronic
Weiting Zhang et al.
Summary: This study introduces an end-edge-cloud orchestration architecture to tackle the challenges of performing deep neural network inference in resource-limited industrial Internet of things networks. By flexibly coordinating inference task assignment and DNN model placement, as well as implementing a resource management scheme based on deep reinforcement learning, efficient DNN inference and improved accuracy can be achieved.
IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY
(2021)
Article
Engineering, Electrical & Electronic
R. Lakshmana Kumar et al.
Summary: This paper discusses the importance of aerial communication and the potential role of blockchain technology in addressing security issues in aerial communication networks.
PHYSICAL COMMUNICATION
(2021)
Article
Computer Science, Information Systems
Jun Li et al.
Summary: To address the high detection complexity of OFDM-SNM signals, a cascaded artificial neural network (CANN) is designed to provide a simplified solution, with numerical simulations confirming its effectiveness and efficiency.
IEEE WIRELESS COMMUNICATIONS LETTERS
(2021)
Proceedings Paper
Computer Science, Information Systems
Boxin Wang et al.
Summary: This paper introduces a novel privacy-preserving generative model DATALENS, utilizing generative adversarial networks and the PATE framework to generate synthetic data while protecting privacy through voting. A new dimension compression and aggregation approach ToPAGG is proposed, along with theoretical proof of guaranteed differential privacy for the generated data, demonstrating a tradeoff between privacy and convergence rates.
CCS '21: PROCEEDINGS OF THE 2021 ACM SIGSAC CONFERENCE ON COMPUTER AND COMMUNICATIONS SECURITY
(2021)
Article
Computer Science, Hardware & Architecture
Yuzheng Li et al.
Summary: Federated learning allows users to collaboratively train a shared global model without exposing private data, but security concerns arise due to potential attacks from malicious clients or central servers. A decentralized federated learning framework based on blockchain, called BFLC, is proposed to address these security issues. It utilizes a Committee consensus mechanism to enhance security and scalability, as demonstrated in experiments using real-world datasets.
Article
Computer Science, Hardware & Architecture
Yunlong Lu et al.
Summary: The paper proposes a blockchain-empowered federated learning framework to enhance security and privacy while maintaining trained parameters. A deep reinforcement learning algorithm is designed to solve the optimization problem of resource sharing, achieving high accuracy and good convergence according to numerical results.
Article
Computer Science, Artificial Intelligence
Hao Song et al.
IEEE COMPUTATIONAL INTELLIGENCE MAGAZINE
(2020)
Article
Engineering, Electrical & Electronic
Nguyen Cong Luong et al.
IEEE COMMUNICATIONS MAGAZINE
(2020)
Article
Computer Science, Hardware & Architecture
Jiawen Kang et al.
IEEE WIRELESS COMMUNICATIONS
(2020)
Article
Telecommunications
Yi Liu et al.
China Communications
(2020)
Article
Computer Science, Artificial Intelligence
Felix Sattler et al.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2020)
Article
Computer Science, Hardware & Architecture
Wen Sun et al.
IEEE WIRELESS COMMUNICATIONS
(2020)
Article
Telecommunications
Bin Cao et al.
DIGITAL COMMUNICATIONS AND NETWORKS
(2020)
Article
Engineering, Electrical & Electronic
Mohammed Amine Togou et al.
IEEE COMMUNICATIONS MAGAZINE
(2020)
Article
Chemistry, Analytical
Yiming Jiang et al.
Article
Computer Science, Information Systems
Jiawen Kang et al.
IEEE INTERNET OF THINGS JOURNAL
(2019)
Proceedings Paper
Computer Science, Software Engineering
Ingo Weber et al.
2019 IEEE INTERNATIONAL CONFERENCE ON SOFTWARE ARCHITECTURE (ICSA)
(2019)