Privacy protection against attack scenario of federated learning using internet of things

Article Computer Science, Information Systems

Intellectual structure of cybersecurity research in enterprise information systems

Nitin Singh et al.

Summary: This study reveals five core themes of cybersecurity research in enterprises and discusses the implications for enterprise information systems and opportunities for research in each of these themes.

ENTERPRISE INFORMATION SYSTEMS (2023)

添加到收藏夹

Article Automation & Control Systems

Privacy Threat and Defense for Federated Learning With Non-i.i.d. Data in AIoT

Zuobin Xiong et al.

Summary: This article explores innovative approaches to privacy protection in federated learning with non-i.i.d. data. A novel algorithm, 2DP-FL, is designed to achieve differential privacy by adding noise during training local models and when distributing global model. The results of theoretical analysis and real-data experiments validate the advantages of 2DP-FL in privacy protection, learning convergence, and model accuracy.

IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS (2022)

添加到收藏夹

Article Automation & Control Systems

Joint Protection of Energy Security and Information Privacy for Energy Harvesting: An Incentive Federated Learning Approach

Qianqian Pan et al.

Summary: This article proposes a joint protection framework for energy security and information privacy in energy harvesting (EH) systems using an incentive federated learning approach. The framework includes malicious energy user detection, differential privacy-based information preservation, and a noncooperative game-enabled incentive mechanism. Evaluation results demonstrate the effectiveness of the proposed joint protection mechanism.

IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS (2022)

添加到收藏夹

Article Green & Sustainable Science & Technology

Federated Learning Approach to Protect Healthcare Data over Big Data Scenario

Gaurav Dhiman et al.

Summary: This article thoroughly discusses the benefits and drawbacks of various technologies and their scope of application. By utilizing anonymity technology and differential privacy in data collection, attacks based on background knowledge can be prevented. Encryption, auditing procedures, and access control mechanisms are used to ensure the confidentiality and integrity of medical big data during storage and sharing stages. Machine learning is employed for privacy protection during the data analysis stage. Acceptable ideas are proposed from the management level to address privacy concerns throughout the life cycle of medical big data.

SUSTAINABILITY (2022)

添加到收藏夹

Article Computer Science, Information Systems

Secure and Privacy-Preserving Federated Learning via Co-Utility

Josep Domingo-Ferrer et al.

Summary: This article introduces a federated learning framework that provides privacy protection and security against attacks. The framework utilizes protocols to offer strong privacy protection and ensures sustainability and rationality.

IEEE INTERNET OF THINGS JOURNAL (2022)

添加到收藏夹

Article Computer Science, Information Systems

FedDetect: A Novel Privacy-Preserving Federated Learning Framework for Energy Theft Detection in Smart Grid

Mi Wen et al.

Summary: In this article, we propose a privacy-preserving federated learning framework called FedDetect for energy theft detection in smart grids. By processing data from multiple detection stations and using a secure protocol and deep learning model for training, high accuracy energy theft detection is achieved.

IEEE INTERNET OF THINGS JOURNAL (2022)

添加到收藏夹

Article Computer Science, Cybernetics

A DRL-Based Service Offloading Approach Using DAG for Edge Computational Orchestration

M. S. Mekala et al.

Summary: This article proposes a deep reinforcement learning-based service offloading approach to reduce edge server costs by optimizing resource sharing and execution time.

IEEE TRANSACTIONS ON COMPUTATIONAL SOCIAL SYSTEMS (2022)

添加到收藏夹

Article Computer Science, Hardware & Architecture

Privacy-Preserving Federated Deep Learning With Irregular Users

Guowen Xu et al.

Summary: This article introduces a privacy-preserving federated deep learning framework, PPFDL, which aims to address the negative impact of irregular users on training accuracy and ensure the confidentiality of user-related information. Extensive experiments demonstrate the superior performance of PPFDL in terms of training accuracy, computation, and communication overheads.

IEEE TRANSACTIONS ON DEPENDABLE AND SECURE COMPUTING (2022)

添加到收藏夹

Article Automation & Control Systems

Deep-IFS: Intrusion Detection Approach for Industrial Internet of Things Traffic in Fog Environment

Mohamed Abdel-Basset et al.

Summary: This article presents a forensics-based deep learning model, Deep-IFS, for intrusion detection in IIoT traffic. By utilizing local gated recurrent unit and multihead attention layers to learn local and global representations, and deploying and training the model in a fog computing environment, it effectively handles large-scale IIoT traffic data and achieves good distributed processing results.

IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS (2021)

添加到收藏夹

Article Computer Science, Information Systems

Privacy-Preserving Blockchain-Based Federated Learning for IoT Devices

Yang Zhao et al.

Summary: This study introduces a federated learning system leveraging a reputation mechanism to assist home appliance manufacturers in developing a smart home system. The system involves two stages: centralized training of customer data and model sharing among manufacturers through a reputation-based mechanism.

IEEE INTERNET OF THINGS JOURNAL (2021)

添加到收藏夹

Article Computer Science, Hardware & Architecture

An efficient combined deep neural network based malware detection framework in 5G environment

Ning Lu et al.

Summary: The study proposes an efficient malware detection framework based on deep neural network, which can handle large-scale samples on Android application platform. By combining rapid pre-detection and deep detection, an effective detection framework is designed, and experimental results show that the classification index of the method can reach as high as 95.69%.

COMPUTER NETWORKS (2021)

添加到收藏夹

Article Automation & Control Systems

PDM: Privacy-Aware Deployment of Machine-Learning Applications for Industrial Cyber-Physical Cloud Systems

Xiaolong Xu et al.

Summary: The article introduces a privacy-aware deployment method (PDM) for hosting ML applications in industrial CPCSs to improve implementation performance and resource utility.

IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS (2021)

添加到收藏夹

Proceedings Paper Computer Science, Theory & Methods

POI Recommendation with Federated Learning and Privacy Preserving in Cross Domain Recommendation

Li-E Wang et al.

Summary: The study introduces a cross-domain POI recommendation framework that utilizes federated learning and privacy protection features to improve recommendation accuracy and protect user privacy.

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

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

Federated Regularization Learning: an Accurate and Safe Method for Federated Learning

Tianqi Su et al.

Summary: A novel federated learning model is proposed to protect data privacy and defend against attacks, experimental results demonstrate that the model can successfully resist various external attacks with negligible accuracy loss.

2021 IEEE 3RD INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE CIRCUITS AND SYSTEMS (AICAS) (2021)

添加到收藏夹

Article Computer Science, Artificial Intelligence

A Privacy-Preserving Distributed Contextual Federated Online Learning Framework with Big Data Support in Social Recommender Systems

Pan Zhou et al.

Summary: This paper proposes a privacy-preserving distributed recommender system (DRS), where each service provider is modeled as a context-aware distributed online learner. The federated learning framework is adopted to train a high quality privacy-preserving centralized model to handle big data scenarios.

IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING (2021)

添加到收藏夹

Article Computer Science, Information Systems

Privacy Protection in Prosumer Energy Management Based on Federated Learning

Yunfeng Li et al.

Summary: The FedClusAvg algorithm proposed in this paper efficiently addresses privacy concerns of prosumers by utilizing cluster stratified sampling and multiple iterations, improving model accuracy and reducing communication rounds.

IEEE ACCESS (2021)

添加到收藏夹

Article Computer Science, Information Systems