Article
Mathematics
Tariq Ahamed Ahanger, Abdulaziz Aldaej, Mohammed Atiquzzaman, Imdad Ullah, Muhammad Yousufudin
Summary: The Internet of Things (IoT) technology has enabled more than 10 billion physical items to connect to the internet and conduct activities independently. However, these IoT networks are also vulnerable to attacks from malicious hackers. Machine learning (ML)-assisted methods have been proposed to enhance IoT security, but the centralized storage of data raises concerns about user privacy. The proposed Federated Learning (FL)-based anomaly detection technique utilizes on-device data and decentralized training cycles to identify IoT network intrusions, showing improved performance in protecting user data.
Article
Computer Science, Information Systems
Wenji He, Yifeng Liu, Haipeng Yao, Tianle Mai, Ni Zhang, F. Richard Yu
Summary: The Internet of Things (IoT) has been widely applied in our daily lives in recent years, but also poses challenges in network security, particularly in addressing DDoS attacks. Current DDoS defense mechanisms face limitations, so designing a machine learning-based in-network DDoS detection framework is necessary for addressing these challenges.
IEEE INTERNET OF THINGS JOURNAL
(2021)
Review
Computer Science, Information Systems
Syeda M. Muzammal, Raja Kumar Murugesan, N. Z. Jhanjhi
Summary: Internet of Things (IoT) is a network of interconnected objects via Internet for data collection and exchange. Security issues and requirements in IoT networks and RPL routing protocol necessitate mitigation methods and trust models for ensuring network security. Trust-based approaches have gained significant interest in embedding security in IoT networks and routing protocols.
IEEE INTERNET OF THINGS JOURNAL
(2021)
Article
Computer Science, Information Systems
Nagaraj Balakrishnan, Arunkumar Rajendran, Danilo Pelusi, Vijayakumar Ponnusamy
Summary: The Internet of Things (IoT) is a new technology that aims to connect all objects everywhere for intelligent applications in healthcare, safety, and industry. However, the diverse applications of IoT also bring higher risks of unauthorized access.
INTERNET OF THINGS
(2021)
Article
Engineering, Electrical & Electronic
Rambabu Kalathiripi, N. Venkatram
Summary: The Internet of Things (IoT) is vulnerable to DDoS attacks, and this article introduces a novel method called Regression Coefficient of Traffic Flow Metric (RCTFM) for predictive analysis and detection of DDoS attacks in IoT networks, showing scalability and significance compared to existing methods.
INTERNATIONAL JOURNAL OF COMMUNICATION SYSTEMS
(2021)
Article
Computer Science, Information Systems
Yuming Feng, Weizhe Zhang, Shujun Yin, Hao Tang, Yang Xiang, Yu Zhang
Summary: This article proposes a novel reinforcement learning-based collaborative DDoS detection method and utilizes a lightweight unsupervised classifier for network traffic analysis. The dynamic changes in the IoT environment are handled using the soft actor-critic model and a collaborative aggregation module, ensuring excellent detection performance for different types of IoT devices.
IEEE INTERNET OF THINGS JOURNAL
(2023)
Review
Computer Science, Information Systems
Arash Heidari, Mohammad Ali Jabraeil Jamali
Summary: The security of IoT involves not only network and data security but also human health and life attacks. The integration of Intrusion Detection System (IDS) with IoT systems is important for protecting system security.
CLUSTER COMPUTING-THE JOURNAL OF NETWORKS SOFTWARE TOOLS AND APPLICATIONS
(2023)
Article
Computer Science, Information Systems
Yang Xu, Jia Liu, Yulong Shen, Jun Liu, Xiaohong Jiang, Tarik Taleb
Summary: This article introduces a secure routing scheme based on incentive jamming to enhance the security of data transmission in the IoT. The scheme involves theoretical modeling, incentive mechanism design, and two-stage game framework to determine optimal routing with source rewards and jamming power. The proposed scheme is proven to be individually rational, stable, distributed, and computationally efficient, with simulation and numerical results demonstrating its performance.
IEEE INTERNET OF THINGS JOURNAL
(2021)
Article
Mathematics
Mahmoud Ragab, Sultanah M. Alshammari, Louai A. Maghrabi, Dheyaaldin Alsalman, Turki Althaqafi, Abdullah AL-Malaise AL-Ghamdi
Summary: The Internet of Things (IoT) is a network of interconnected physical devices that exchange and collect information. While IoT devices offer numerous advantages, they also pose security risks. Distributed Denial of Service (DDoS) attacks, in particular, exploit IoT devices to disrupt services. Therefore, there is a need for robust detection systems using artificial intelligence (AI) to identify these attacks.
Article
Engineering, Multidisciplinary
Surya Pavan Kumar Gudla, Sourav Kumar Bhoi, Soumya Ranjan Nayak, Amit Verma
Summary: Fog computing is essential for IoT systems but faces security challenges. This paper proposes a deep learning-based scheme for DDoS attack detection, selecting the best model through performance comparison and achieving high accuracy through simulation.
MATHEMATICAL PROBLEMS IN ENGINEERING
(2022)
Review
Computer Science, Information Systems
Euclides Carlos Pinto Neto, Sajjad Dadkhah, Somayeh Sadeghi, Heather Molyneaux, Ali A. Ghorbani
Summary: The Internet of Things (IoT) has the potential to revolutionize medical treatment in healthcare, but it also faces security threats. Advanced analytics can enhance IoT security, but generating realistic datasets is complex. This research conducts a review of Machine Learning (ML) solutions for IoT security in healthcare, focusing on existing datasets, resources, applications, and challenges, to highlight the current landscape and future requirements.
COMPUTER COMMUNICATIONS
(2024)
Review
Computer Science, Information Systems
Komal Bansal, Anita Singhrova
Summary: The popularity of IoT has led to its implementation in both home automation systems and industrial applications. However, this has also resulted in security challenges that can be addressed through the use of Intrusion Detection Systems (IDS).
MULTIMEDIA TOOLS AND APPLICATIONS
(2023)
Article
Computer Science, Information Systems
Tariq Ahamed Ahanger, Abdulaziz Aldaej, Mohammed Atiquzzaman, Imdad Ullah, Mohammed Yousuf Uddin
Summary: This research proposes a unique attack identification technique based on deep learning for detecting botnet attacks in user-oriented IoT environments. The presented technique outperforms the state-of-the-art deep learning techniques in terms of accuracy, specificity, and sensitivity.
CMC-COMPUTERS MATERIALS & CONTINUA
(2022)
Article
Computer Science, Information Systems
Yinghui Zhang, Qin Ren, Kun Song, Yang Liu, Tiankui Zhang, Yi Qian
Summary: This article proposes an energy-efficient multilevel secure routing protocol in IoT networks, which utilizes clustering and optimized intercluster routing to enhance network performance, and adopts multiple trust levels to defend against different attacks.
IEEE INTERNET OF THINGS JOURNAL
(2022)
Review
Chemistry, Analytical
Muhammad Almas Khan, Muazzam A. Khan, Sana Ullah Jan, Jawad Ahmad, Sajjad Shaukat Jamal, Awais Aziz Shah, Nikolaos Pitropakis, William J. Buchanan
Summary: This paper proposed a Deep Neural Network (DNN) for intrusion detection in MQTT-based protocol and compared its performance with traditional machine learning algorithms. Results showed that the DNN model achieved high accuracy in both binary and multi-label classification on different datasets.
Article
Automation & Control Systems
Bin Jiang, Jianqiang Li, Huihui Wang, Houbing Song
Summary: With the improvement of hardware computing power, edge computing of industrial data has been widely used in the past decade, greatly improving production efficiency. Compared to cloud computing, edge computing saves bandwidth consumption and ensures terminal data security to some extent. However, new attack types require better privacy protection in industrial edge computing. This article proposes a federated edge learning framework based on hybrid differential privacy and adaptive compression to protect the privacy of industrial data.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2023)
Article
Engineering, Multidisciplinary
Aurora Gonzalez-Vidal, Jose Mendoza-Bernal, Shuteng Niu, Antonio F. Skarmeta, Houbing Song
Summary: In this study, a transfer learning-based framework for smart buildings is proposed to address energy-related problems. The framework includes network creation and transferable predictive model components. A novel clustering algorithm for mixed data and clustering of image-based time series representation are evaluated to create networks of buildings with similar characteristics. A combination of long short term memory and convolutional neural network is trained on the centroids of the clusters for energy consumption prediction. The framework achieves state-of-the-art performance on three datasets, reducing the CVRMSE in energy consumption prediction by 21.6% and in air conditioning usage prediction from 4.18% to 0.28%.
IEEE TRANSACTIONS ON INDUSTRY APPLICATIONS
(2023)
Article
Engineering, Civil
Aamir Akbar, Muhammad Ibrar, Mian Ahmad Jan, Lei Wang, Nadir Shah, Houbing Herbert Song
Summary: Since millions of smart vehicles in Internet-of-Vehicles (IoV) produce and relay data, creating social networks of vehicles in IoV is crucial for the future Intelligent Transportation System (ITS). However, the IoV architecture has been fragmented to meet the needs of different work domains. To address these problems, the concept of Social IoV (SIoV) was introduced. One of the challenges in SIoV is the rapid growth and depletion of social relations between vehicles due to the dynamic and unstable nature of IoV. Therefore, we propose an adaptive clustering technique called SeAC to improve the stability and efficiency of SIoV.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2023)
Editorial Material
Computer Science, Information Systems
Haibin Lv, Enrico Natalizio, Houbing Song, Shehzad Ashraf
IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS
(2023)
Article
Engineering, Electrical & Electronic
Muhammad Adil, Varun G. Menon, Venki Balasubramanian, Sattam Rabia Alotaibi, Houbing Song, Zhanpeng Jin, Ahmed Farouk
Summary: The rapid growth of patient-wearable devices and implantable biosensors in digital healthcare has raised concerns about their security. This article presents a detailed survey of the literature from 2019 to 2022, discussing the security issues of self-empowered wireless sensor networks (SWSNs) and proposing future research directions.
IEEE SENSORS JOURNAL
(2023)
Article
Automation & Control Systems
Zixiao Zhao, Qinghe Du, Houbing Song
Summary: In this article, a learning network is proposed to timely discover intrusion in the fifth generation network for Industrial internet of things (IoT), and can identify two types of intrusion. By extracting traffic load information from the states (success, collision, and idle) of access resources observed at media access control and physical layers, the learning network can effectively capture the number of active devices, provide reasonable prediction using history records, and achieve more accurate detection compared with baseline approaches.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2023)
Editorial Material
Engineering, Civil
Haibin Lv, Jaime Lloret, Houbing Song
Summary: The Internet of Things (IoT) is an important part of new generation information technology, connecting any object to the Internet for information exchange and communication. The Internet of Vehicles (IoV) is the focus of IoT development, allowing for the upgrade of vehicle applications. IoT intelligent infrastructure plays a crucial role in providing high-quality public services, reducing costs, and achieving sustainable development.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2023)
Article
Engineering, Civil
Kefeng Guo, Min Wu, Xingwang Li, Houbing Song, Neeraj Kumar
Summary: In this paper, the co-optimized performance of multi-reconfigurable intelligent surface (RIS)-assisted integrated satellite-unmanned aerial vehicle-terrestrial network (IS-UAV-TN) is discussed, considering the presence of multiple vehicle users. The paper proposes installing RIS on the UAV to reshape the wireless transmission path and adopts non-orthogonal multiple access (NOMA) protocols to address spectrum shortage and enhance connection quality. A multi-objective optimization problem is formulated to maximize the system achievable rate and minimize the UAV energy consumption, and a multi-objective deep deterministic policy gradient (MO-DDPG) algorithm is proposed for online decision making in IS-UAV-TNs.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2023)
Article
Computer Science, Information Systems
Xiaotong Wu, Muhammad Bilal, Xiaolong Xu, Houbing Song
Summary: This paper investigates data inference attacks on multimedia data using artificial intelligence models and proposes a privacy-preserving approach based on Bayesian networks and deep learning. The privacy of the models is guaranteed through conditional probability distribution estimation. The proposed method includes a simple perturbation approach and an improved approach that combines attribute features using a taxonomy tree to enhance the prediction accuracy. Extensive experiments demonstrate that the proposed models outperform existing private decision tree methods.
INFORMATION SCIENCES
(2023)
Article
Engineering, Multidisciplinary
Muhammad Tayyeb, Muhammad Umer, Khaled Alnowaiser, Saima Sadiq, Ala' Abdulmajid Eshmawi, Rizwan Majeed, Abdullah Mohamed, Houbing Song, Imran Ashraf
Summary: Cardiovascular problems have become a leading cause of death globally, with a recent increase in the number of patients. Currently, the analysis of electrocardiogram (ECG) data for cardiac abnormality detection is time-consuming and prone to errors. This study proposes a simple multilayer perceptron (MLP) model for heart disease prediction, achieving better outcomes than existing approaches with a 94.40% accuracy score. The findings suggest that the proposed system has high potential for real-world deployment in practical medical settings.
CMES-COMPUTER MODELING IN ENGINEERING & SCIENCES
(2023)
Article
Computer Science, Information Systems
Waleed Raza, Xuefei Ma, Houbing Song, Amir Ali, Habib Zubairi, Kamal Acharya
Summary: Underwater acoustic wireless communication networks consist of autonomous underwater acoustic vehicles and battery-deployed modems interconnected to the ocean bottom. Orthogonal frequency division multiplexing (OFDM) has become the dominant modulation technique due to its high data transmission and robustness. However, OFDM suffers from a high peak to average power ratio (PAPR), leading to increased power consumption, non-linear distortion, and higher bit error rates (BER). In this study, a machine learning-based underwater acoustic communication system using LSTM-NN is proposed to mitigate the PAPR, reduce non-linear distortion, and improve overall performance.
KSII TRANSACTIONS ON INTERNET AND INFORMATION SYSTEMS
(2023)
Proceedings Paper
Computer Science, Artificial Intelligence
Sang Xing, Thomas Yang, Houbing Song
Summary: Unmanned aerial vehicle (UAV) technology has been significant in both military and civilian applications. Formation control has become an important concept, and this paper explores how to develop more effective UAV management and organizations by optimizing the overall communication performance of a dynamical multi-agent system.
Article
Computer Science, Hardware & Architecture
Yu Zhan, Ying Fu, Liang Huang, Jianmin Guo, Heyuan Shi, Houbing Song, Chao Hu
Summary: This article presents an effective adversarial attack method on video classification systems, which reduces query consumption and achieves high attack success rate through optimal parameter group updating. The proposed attack method is evaluated on UCF101 and JESTER datasets, and achieves significant improvements over various DNN-based video classification systems.
IEEE TRANSACTIONS ON RELIABILITY
(2023)
Article
Engineering, Multidisciplinary
Jun Liu, Geng Yuan, Changdi Yang, Houbing Song, Liang Luo
Summary: The interpretability of deep learning models is a significant area of research in artificial intelligence. Medical imaging requires explanations, but existing solutions for left ventricular segmentation have limited interpretability. In this study, we trained a novel interpretable approach from scratch to autonomously segment the left ventricle with a cardiac MRI. Our enhanced GPU training system used deep learning techniques to simplify tasks and improve interpretability.
CMES-COMPUTER MODELING IN ENGINEERING & SCIENCES
(2023)
Article
Computer Science, Artificial Intelligence
Yingqi Peng, Wei Liu, Anfeng Liu, Tian Wang, Houbing Song, Shaobo Zhang
Summary: This paper proposes a truth-based Three-tier Combinatorial Multi-Armed Bandit (TCMAB) incentive mechanism for selecting each other to maximize their revenues in Mobile Crowd Sensing (MCS). The mechanism optimizes the interaction between the platform and the worker, as well as between the task requestor and the platform, to establish a balanced MCS ecosystem and improve the utilities, data quality, and applications quality of MCS.
EXPERT SYSTEMS WITH APPLICATIONS
(2024)