Article
Computer Science, Theory & Methods
Yili Jiang, Kuan Zhang, Yi Qian, Liang Zhou
Summary: Distributed learning is an effective technique to reduce data transmissions and protect data privacy in centralized machine learning. A novel anonymous authentication approach is proposed in this work, which is applicable to all machine learning algorithms, ensuring data utility and privacy protection.
IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY
(2022)
Article
Computer Science, Theory & Methods
Antonio M. Larriba, Damian Lopez
Summary: In this paper, three protocols are proposed to allocate the responsibility of granting anonymous access to a resource among a set of competing entities. The protocols take into account central or distributed registration and ensure that no subset of guardian authorities can tamper with or forge new access-key tokens. Additionally, two of the proposed methods are resistant to the potential impact of quantum computers. These protocols open up new possibilities for cryptographic applications like electronic voting or blockchain access.
IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY
(2023)
Article
Computer Science, Information Systems
Fushan Wei, Pandi Vijayakumar, Neeraj Kumar, Ruijie Zhang, Qingfeng Cheng
Summary: The Internet of Things provides complex value-added services to mobile intelligent terminal users, but security breaches and privacy leaks severely threaten application development. A privacy-preserving implicit authentication framework using users' behavior features has been proposed to enhance the security of mobile intelligent terminals.
IEEE INTERNET OF THINGS JOURNAL
(2021)
Article
Computer Science, Information Systems
Qiuyun Lyu, Hao Li, Zhining Deng, Jingyu Wang, Yizhi Ren, Ning Zheng, Junliang Liu, Huaping Liu, Kim-Kwang Raymond Choo
Summary: This article proposes an auditable anonymous user authentication (A2UA) protocol based on blockchain technology, which achieves anonymous mutual authentication and accountability between users and cloud service providers while protecting user privacy. The analysis results show that the A2UA protocol outperforms existing schemes in terms of security, performance, and cost, and it is feasible in terms of Ethereum Gas cost.
IEEE TRANSACTIONS ON CLOUD COMPUTING
(2023)
Article
Computer Science, Theory & Methods
Xiaoyu Zhang, Hong Zhong, Chunyang Fan, Irina Bolodurina, Jie Cui
Summary: Caching content in vehicular networks is widely accepted to improve service quality by responding quickly to vehicle requests and reducing content retrieval delay. However, ensuring efficient security and privacy protection is crucial when vehicles access the cached content. This paper proposes a lightweight cryptography-based access control scheme for software defined vehicular networks (SDVN), utilizing TESLA broadcast authentication protocol and Pederson commitment. The scheme achieves direct and efficient authentication between vehicles and fog nodes, restricts access to legitimate vehicles, and overcomes limitations in existing access control schemes. Additionally, a cooperative cache update mechanism is provided to optimize the limited cache space of the fog node. Security verification and analyses demonstrate that the scheme meets the security requirements in SDVN and outperforms related works in terms of computation and communication costs.
IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY
(2022)
Article
Computer Science, Information Systems
Zaher Haddad
Summary: This paper proposes an authentication protocol based on pseudonyms and blockchain to achieve security and privacy for 5G networks. Security analysis shows that the proposed scheme is secure and preserves privacy against different types of attacks. Furthermore, performance evaluation demonstrates the efficiency of the proposed scheme compared to existing schemes.
JOURNAL OF KING SAUD UNIVERSITY-COMPUTER AND INFORMATION SCIENCES
(2023)
Article
Automation & Control Systems
Jegadeesan Subramani, Azees Maria, Arun Sekar Rajasekaran, Fadi Al-Turjman
Summary: This article proposes a computationally efficient privacy-preserving anonymous authentication scheme for resource-limited WBAN, which protects the privacy and security of BI and user's personal data.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2022)
Article
Engineering, Multidisciplinary
Lihua Yin, Jiyuan Feng, Hao Xun, Zhe Sun, Xiaochun Cheng
Summary: The paper introduces a new hybrid privacy-preserving method for addressing data leakage threats in existing federated learning training processes. It utilizes advanced functional encryption algorithms and local Bayesian differential privacy to enhance data protection, while also implementing Sparse Differential Gradient to improve transmission and storage efficiency.
IEEE TRANSACTIONS ON NETWORK SCIENCE AND ENGINEERING
(2021)
Article
Automation & Control Systems
Amitesh Singh Rajput, Balasubramanian Raman
Summary: The popularity of wearable smart healthcare devices has led to a new service paradigm. However, the collection of massive sensitive medical data in order to improve service quality raises concerns about security risks and complexity. In this paper, the authors propose a solution using a directing authority called the transcryptor and polymorphic encryption to address the problems of entity authentication and data integrity. The proposed approach is demonstrated to be superior through performance testing and security analysis.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2022)
Article
Computer Science, Information Systems
Yudan Cheng, Jianfeng Ma, Zhiquan Liu, Libo Wang, Zuobin Ying, Xin Chen
Summary: This article proposes an efficient anonymous authentication and privacy-preserving reliability evaluation scheme for mobile crowdsensing (MCS). It improves the efficiency of mutual authentication and guarantees the reliability of sensing vehicles. By using an anonymous authentication method and a privacy-preserving reliability evaluation algorithm, the reliability of sensing vehicles is effectively evaluated in this scheme.
IEEE INTERNET OF THINGS JOURNAL
(2023)
Article
Computer Science, Information Systems
Shiwen Zhang, Biao Hu, Wei Liang, Kuan-Ching Li, Brij B. Gupta
Summary: This article proposes a caching-based dual K-anonymous (CDKA) location privacy-preserving scheme in edge computing environments. The scheme uses an edge server to protect user location privacy by reducing device load and providing dual anonymity. Through security analysis and performance evaluation, the robustness and relatively low communication cost of the scheme are demonstrated.
IEEE INTERNET OF THINGS JOURNAL
(2023)
Article
Computer Science, Information Systems
Leyou Zhang, Yadi Ye, Yi Mu
Summary: This article introduces a patient-centric personal health record sharing framework, which protects PHRs through multiauthority attribute-based encryption and proposes anonymous authentication between the cloud and the user to protect data integrity and user privacy. The proposed authentication system can resist collusion attacks, enhancing patients' control over their health records.
IEEE INTERNET OF THINGS JOURNAL
(2021)
Article
Computer Science, Information Systems
Mohammad Ali, Mohammad-Reza Sadeghi, Ximeng Liu, Athanasios V. Vasilakos
Summary: The rapid development of cloud computing and IoT has the potential to significantly improve healthcare quality through smart health (s-health). However, existing s-health solutions have not adequately addressed concerns regarding data integrity, user anonymity, and authentication. To address these issues, a new aggregate anonymous attribute-based remote data verification scheme called A(3)B-RDV is introduced. It provides efficient and secure verification of the integrity of multiple cloud data files, while also ensuring complete anonymity and supporting dishonest-user traceability.
IEEE TRANSACTIONS ON CLOUD COMPUTING
(2023)
Article
Computer Science, Information Systems
Sungjin Yu, Kisung Park
Summary: This study presents a secure, anonymous, and lightweight privacy-preserving scheme called SALS-TMIS in the context of Internet of Medical Things (IoMT)-enabled Telecare Medical Information System (TMIS). The security of SALS-TMIS is evaluated through both informal and formal security analyses, including ROR oracle model and AVISPA implementation. The results show that SALS-TMIS offers superior security and efficiency compared to existing schemes.
Article
Computer Science, Information Systems
Jingwei Liu, Weiyang Jiang, Rong Sun, Ali Kashif Bashir, Mohammad Dahman Alshehri, Qiaozhi Hua, Keping Yu
Summary: Electronic Medical Records (EMRs) are valuable research materials for AI and machine learning. Traditional centralized data sharing architectures cannot balance privacy and traceability effectively. Our proposed scheme using decentralized blockchain allows trackable anonymous remote healthcare data storing and sharing, providing efficient overall performance.
IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS
(2023)
Article
Computer Science, Artificial Intelligence
Amit Kumar Jaiswal, Prayag Tiwari, M. Shamim Hossain
NEURAL COMPUTING & APPLICATIONS
(2023)
Article
Computer Science, Artificial Intelligence
Mehedi Masud, Amr E. Eldin Rashed, M. Shamim Hossain
Summary: Breast cancer is a common and deadly disease affecting millions of women worldwide. Researchers have proposed various convolutional neural network models to assist in diagnostic process. However, the lack of standard models and large datasets for training and validation remains a challenge. This study explores the use of transfer learning and evaluates eight pre-trained models on ultrasound images of breast cancers, as well as introduces a custom convolutional neural network that outperforms the pre-trained models.
NEURAL COMPUTING & APPLICATIONS
(2022)
Article
Computer Science, Artificial Intelligence
Heena Rathore, Amr Mohamed, Mohsen Guizani, Shailendra Rathore
Summary: This paper introduces a machine learning approach called NueroFATH for the physical assessment of athletes. It uses neural networks and fuzzy c-means techniques to predict the potential of athletes winning medals. The study also identifies important physical characteristics related to the assessment results.
NEURAL COMPUTING & APPLICATIONS
(2023)
Article
Computer Science, Theory & Methods
Honnesh Rohmetra, Navaneeth Raghunath, Pratik Narang, Vinay Chamola, Mohsen Guizani, Naga Rajiv Lakkaniga
Summary: The COVID-19 pandemic has overwhelmed healthcare systems and posed risks to healthcare professionals. Remote monitoring of patient symptoms using machine learning and deep learning techniques offers a promising solution, utilizing common devices like smartphones.
Article
Computer Science, Artificial Intelligence
Yuwen Chen, Bin Song, Yuan Zeng, Xiaojiang Du, Mohsen Guizani
Summary: This study proposes a fault diagnosis method for the current-carrying ring based on an improved CenterNet model in the Industrial Internet of Things. By using attention modules and weighted loss, the accuracy of fault diagnosis for the current-carrying rings is improved.
NEURAL COMPUTING & APPLICATIONS
(2023)
Article
Computer Science, Artificial Intelligence
Mangena Venu Madhavan, Aditya Khamparia, Deepak Gupta, Sagar Pande, Prayag Tiwari, M. Shamim Hossain
Summary: Major countries are facing difficulties due to the COVID-19 pandemic. Existing medical practices, such as PCR and RT-PCR, may result in false positives and false negatives when identifying COVID-19 symptoms. CT imaging or X-rays of the lungs can provide more accurate identification of patients with COVID-19 symptoms. Automating the identification of COVID-19 using feasible technology can improve facilities. The Res-CovNet framework is a hybrid methodology that integrates different platforms into a single platform to identify and classify pneumonia and COVID-19 cases.
NEURAL COMPUTING & APPLICATIONS
(2023)
Article
Computer Science, Hardware & Architecture
Sherief Hashima, Zubair Md Fadlullah, Mostafa M. Fouda, Ehab Mahmoud Mohamed, Kohei Hatano, Basem M. ElHalawany, Mohsen Guizani
Summary: This article introduces the concept of intelligent softwareization in 6G networks to address the impact of dynamically changing environments on reliability. Through evaluation in multiple scenarios and the use of optimal strategies to meet various demands, the results show promising performance.
Article
Computer Science, Information Systems
Praveen Gorla, Mohammad Saif, Vinay Chamola, Biplab Sikdar, Mohsen Guizani
Summary: This article presents a novel machine learning-based framework for intelligent resource provisioning mechanisms for micro-grid connected green small cell base stations. By using prediction and energy flow control mechanisms, the article proposes an algorithmic implementation for redistribution of renewable resources, improving the resource management and traffic provisioning capability of small cell base stations.
IEEE SYSTEMS JOURNAL
(2023)
Article
Engineering, Civil
Moayad Aloqaily, Haya Elayan, Mohsen Guizani
Summary: The advancement of wireless connectivity in smart cities enhances connections between key elements, and the federated intelligent health monitoring systems in autonomous vehicles contribute to improving quality of life. This study proposes C-HealthIER, a cooperative health intelligent emergency response system that monitors passengers' health and conducts cooperative behavior to reduce emergency treatment time and distance by sharing information between vehicles and infrastructure.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2023)
Article
Engineering, Multidisciplinary
Naram Mhaisen, Alaa Awad Abdellatif, Amr Mohamed, Aiman Erbad, Mohsen Guizani
Summary: Distributed learning algorithms aim to utilize diverse data stored at users' devices to learn a global phenomena. However, when the data is strongly skewed, the performance of the global model can decrease. To tackle this issue, the paper proposes a hierarchical learning system that optimizes user-edge assignment to improve model accuracy.
IEEE TRANSACTIONS ON NETWORK SCIENCE AND ENGINEERING
(2022)
Article
Computer Science, Information Systems
Ikram Ud Din, Aniqa Bano, Kamran Ahmad Awan, Ahmad Almogren, Ayman Altameem, Mohsen Guizani
Summary: The increasing usage of the Internet has improved the quality of trust in the Internet of Things (IoT). Trust plays a crucial role in providing a secure environment for users to share private information and enable easy and trustworthy data exchange among IoT devices. Trust management is essential for secure data transmission in a large-scale IoT network, and a lightweight approach called LightTrust is proposed to address security issues in Industrial IoT nodes. LightTrust utilizes a centralized trust agent to generate and manage trust certificates, and direct observations and recommendations are used to develop trust between nodes. Comparative simulations demonstrate the effectiveness and resilience of the proposed approach.
IEEE INTERNET OF THINGS JOURNAL
(2023)
Article
Engineering, Electrical & Electronic
Yitao Xing, Kaiping Xue, Yuan Zhang, Jiangping Han, Jian Li, David S. L. Wei, Ruidong Li, Qibin Sun, Jun Lu
Summary: The QUIC protocol is designed to improve HTTP traffic, and its extension, MPQUIC, provides higher bandwidth and smoother network handover. However, some issues in the existing MPQUIC, such as packet scheduling and managing dynamic network paths, hinder the improvement of HTTP traffic. This paper proposes a stream-aware per-packet scheduler, HBES, to address these issues and improve the performance of MPQUIC in mobile networks by providing fair bandwidth allocation and mitigating HoL blocking and excessive buffer usage.
IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS
(2023)
Article
Computer Science, Information Systems
Rui Zhuang, Jiangping Han, Kaiping Xue, Jian Li, David S. L. Wei, Ruidong Li, Qibin Sun, Jun Lu
Summary: The upgrade of network devices to be equipped with multiple network interfaces allows for the improvement of network throughput performance through multipath transmission protocols, especially MPTCP. However, the current mostly used MPTCP protocols have a common limitation of being rigid and conservative, leading to poor performance in realistic scenarios due to the dynamic nature of networks. In this paper, a lightweight multipath congestion control algorithm called MP-OL is proposed, which models congestion control as a multi-armed bandit problem and adjusts the sending rate of each subflow flexibly and adaptively through online learning. Experimental results have shown that MP-OL achieves significant improvements in fairness, link utilization, and resilience to non-congestion loss, making it suitable for various network scenarios and unstable network conditions.
IEEE TRANSACTIONS ON NETWORK AND SERVICE MANAGEMENT
(2023)
Article
Computer Science, Hardware & Architecture
Yitao Xing, Kaiping Xue, Yuan Zhang, Jiangping Han, Jian Li, David S. L. Wei
Summary: Multipath TCP (MPTCP) aims to utilize multiple network paths for improved throughput and robustness, particularly in mobile networks. However, the challenge lies in effectively distributing packets over unstable and heterogeneous paths to devices with limited buffers. Existing packet scheduling algorithms have not achieved desired performance in dynamic scenarios, such as mobile networks. In this paper, an Online-Learning Assisted Packet Scheduler (OLAPS) is proposed to address this problem by modeling it as a multi-armed bandit problem. OLAPS adaptsively learns from network conditions and provides the highest possible throughput in a dynamic environment. The evaluation of OLAPS shows improved throughput performance compared to other in-kernel schedulers.
IEEE-ACM TRANSACTIONS ON NETWORKING
(2023)
Article
Computer Science, Hardware & Architecture
Mhd Saria Allahham, Amr Mohamed, Aiman Erbad, Mohsen Guizani
Summary: Mobile edge learning (MEL) is a learning paradigm that enables distributed training of machine learning models over heterogeneous edge devices. This study proposes an incentive mechanism to motivate the participation of edge devices in the training process and evaluates its performance through numerical experiments.
IEEE CANADIAN JOURNAL OF ELECTRICAL AND COMPUTER ENGINEERING
(2023)