Article
Engineering, Multidisciplinary
Abdul Rehman Javed, Saif Ur Rehman, Mohib Ullah Khan, Mamoun Alazab, Thippa G. Reddy
Summary: Controller Area Network (CAN) is a widely used communication protocol in vehicles, but vulnerabilities in the security mechanisms may result in intrusion attacks. In this paper, a novel approach named CANintelliIDS is proposed, which combines CNN and GRU models to detect intrusion attacks on the CAN bus, achieving a performance gain of 10.79% over existing methods.
IEEE TRANSACTIONS ON NETWORK SCIENCE AND ENGINEERING
(2021)
Article
Telecommunications
Hongmao Qin, Mengru Yan, Haojie Ji
Summary: Electronization and intelligentization are becoming the fundamental characteristics of modern automobiles. Automotive information security is increasingly highlighted with the deepening of intelligent network integration. An anomaly detection algorithm based on long short-term memory (LSTM) is proposed to detect abnormal behavior of the controller area network (CAN) bus, showing lower false positive rate and higher detection rate.
VEHICULAR COMMUNICATIONS
(2021)
Article
Computer Science, Hardware & Architecture
Hamed Alqahtani, Gulshan Kumar
Summary: Modern vehicles are becoming increasingly connected, raising concerns about security. Conventional security mechanisms are insufficient to protect in-vehicle networks from attacks, necessitating the development of an effective intrusion detection system (IDS). This study presents IDS-IVN, an IDS for in-vehicle networks that utilizes deep learning to extract and classify traffic features for intrusion detection.
COMPUTERS & ELECTRICAL ENGINEERING
(2022)
Article
Computer Science, Information Systems
Stefano Longari, Daniel Humberto Nova Valcarcel, Mattia Zago, Michele Carminati, Stefano Zanero
Summary: Automotive security has improved significantly due to new connectivity features, with researchers showing vulnerabilities in modern vehicles to various attacks. The proposed IDS CANnolo, based on LSTM-autoencoders, outperforms existing models in detecting anomalies in CAN networks, as demonstrated in experiments.
IEEE TRANSACTIONS ON NETWORK AND SERVICE MANAGEMENT
(2021)
Article
Chemistry, Analytical
Damilola Oladimeji, Amar Rasheed, Cihan Varol, Mohamed Baza, Hani Alshahrani, Abdullah Baz
Summary: Current vehicles rely on in-vehicle communication protocols to support electronic features, with the CAN bus being the most widely adopted protocol. However, as vehicles become more sophisticated, there is a rise in attacks against them. In this research, we analyze the security vulnerabilities of the CAN bus protocol and find significant risks, such as spoofing, injection, and Denial of Service. Our analysis also shows the potential for an attacker to take control of the bus and disrupt the vehicle's operations.
Article
Engineering, Civil
Marwa A. Elsayed, Michael Wrana, Ziad Mansour, Karim Lounis, Steven H. H. Ding, Mohammad Zulkernine
Summary: The aerospace and defense industries are highly susceptible to cyber threats due to their sensitive nature, and a security breach can have far-reaching consequences at the national level. This paper introduces a novel adaptive intrusion detection system for the MIL-STD-1553 communication bus in aerospace vehicles, utilizing advanced deep learning techniques to enhance its ability to detect unknown attack patterns.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2022)
Article
Automation & Control Systems
Zhangwei Yu, Yan Liu, Guoqi Xie, Renfa Li, Siming Liu, Laurence T. Yang
Summary: Intelligent connected vehicles are experiencing rapid growth, but this also increases the vulnerability of automotive CAN networks to cyberattacks. Existing intrusion detection technologies for automotive CAN networks are often ineffective against sophisticated attacks. In this study, a novel time interval conditional entropy method is proposed, which shows higher accuracy and ease of deployment compared to existing methods.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2023)
Article
Computer Science, Artificial Intelligence
Deepak Kumar Jain, Weiping Ding, Ketan Kotecha
Summary: This research develops a new fuzzy deep neural network (FDNN) with Honey Bader Algorithm (HBA) for privacy-preserving intrusion detection technique, named FDNN-HBAID for cloud environment. The presented FDNN-HBAID system is based on the design of an intrusion detection approach with a blockchain-enabled privacy-preserving scheme. The experimental validation on benchmark datasets revealed that the FDNN-HBAID approach had shown the potential to achieve security and privacy in the cloud infrastructure.
INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS
(2023)
Review
Computer Science, Artificial Intelligence
Brooke Lampe, Weizhi Meng
Summary: Modern automobiles heavily rely on internal vehicle networks (IVNs) to control various systems, but the security of these networks was not prioritized in the past. With increasing connectivity to the outside world, researchers have explored automotive security enhancements, but implementation challenges and cost are barriers. An intrusion detection system (IDS) is a promising solution that requires minimal adjustment and deep learning techniques can improve its effectiveness. This paper provides a comprehensive overview of deep learning-based IDSs in automotive networks, categorizing different schemes and evaluating their advantages and disadvantages.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Chemistry, Analytical
Bifta Sama Bari, Kumar Yelamarthi, Sheikh Ghafoor
Summary: Electronic Control Units (ECUs) are increasingly used in vehicles to improve driving comfort and safety. However, the Controller Area Network (CAN) protocol used by these ECUs has security vulnerabilities. This paper proposes a machine learning-based intrusion detection system (IDS) using SVM, DT, and KNN and evaluates its effectiveness with real-world datasets.
Article
Engineering, Civil
Kai Wang, Aiheng Zhang, Haoran Sun, Bailing Wang
Summary: This paper investigates the application of deep-learning methods in intrusion detection in in-vehicle networks. Ten representative advanced deep-learning methods are analyzed, and their performance is compared. The study provides directions and suggestions for future research.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2023)
Article
Computer Science, Information Systems
Linxi Zhang, Xuke Yan, Di Ma
Summary: This article proposes a new IDS system using Binarized Neural Network (BNN) to accelerate intrusion detection and reduce memory and energy costs. The experimental results show that the proposed system achieves faster detection and maintains acceptable detection rates compared to full-precision models. Additionally, using FPGA hardware significantly reduces detection latency and power consumption.
Review
Chemistry, Multidisciplinary
Leila Mohammadpour, Teck Chaw Ling, Chee Sun Liew, Alihossein Aryanfar
Summary: With the advancement and widespread use of Internet applications in recent years, the need for securing Internet networks has increased. Intrusion detection systems (IDSs) employing artificial intelligence (AI) methods, particularly deep learning (DL) algorithms such as convolutional neural networks (CNNs), play a vital role in ensuring network security. However, there is a lack of comprehensive surveys on CNN-based IDS schemes.
APPLIED SCIENCES-BASEL
(2022)
Article
Computer Science, Information Systems
Minki Nam, Seungyoung Park, Duk Soo Kim
Summary: The CAN bus protocol is vulnerable to attacks due to lack of security consideration in its design. By learning and detecting the pattern of CAN ID sequences in normal vehicle operation, potential attacks can be identified.
Article
Telecommunications
Mu Han, Pengzhou Cheng, Shidian Ma
Summary: This paper focuses on studying the complex value neural network (CVNN) to detect arbitration field (CAN ID) for protecting CAN network. The constructed IDS in real-time detection shows high accuracy, reaching 98%. The attack experiment indicates that the model makes it difficult for adversaries to infer valuable information.
VEHICULAR COMMUNICATIONS
(2021)
Article
Engineering, Electrical & Electronic
Afia Naeem, Muhammad Rizwan, Shtwai Alsubai, Ahmad Almadhor, Md. Akhtaruzzaman, Shayla Islam, Hameedur Rahman
Summary: In this research, an enhanced cluster-based lifetime protocol (ECBLTR) is proposed to maximize the network stability and average throughput of vehicular ad-hoc networks (VANETs). The Sugeno model fuzzy inference system is used to assess the cluster head (CH) based on input parameters such as residual energy, local distance, node degree, concentration, and distance from the base station. The results show that our enhanced routing protocol improves the link throughput of VANETs and increases the network lifetime by 10%.
IET ELECTRICAL SYSTEMS IN TRANSPORTATION
(2023)
Article
Chemistry, Analytical
Ahmad Almadhor, Gabriel Avelino Sampedro, Mideth Abisado, Sidra Abbas, Ye-Jin Kim, Muhammad Attique Khan, Jamel Baili, Jae-Hyuk Cha
Summary: With recent advancements in wearable technology, continuous stress monitoring through physiological factors has gained attention. Identifying stress early can improve healthcare outcomes by reducing the negative effects. However, privacy concerns limit the availability of data, making it challenging to utilize AI models in the medical industry. This research proposes a Federated Learning approach that utilizes a Deep Neural Network model to classify wearable-based electrodermal activities while ensuring patient data privacy.
Retraction
Computer Science, Artificial Intelligence
Hafiz Tayyab Rauf, Jiechao Gao, Ahmad Almadhor, Muhammad Arif, Md Tabrez Nafis
Article
Computer Science, Information Systems
Gulshan Kumar, Rajkumar Singh Rathore, Kutub Thakur, Ahmad Almadhor, Sardar Asad Ali Biabani, Subhash Chander
Summary: In real-time and mission-critical applications of wireless sensor networks, preserving source location privacy is a challenging task. Various methods have been proposed, but a dynamic routing approach (SLP-DRA) that selects a path and injects fake messages into the network shows promising results in enhancing security without compromising network performance.
Article
Computer Science, Information Systems
Sidra Abbas, Gabriel Avelino Sampedro, Mideth Abisado, Ahmad Almadhor, Iqra Yousaf, Seng-Phil Hong
Summary: The healthcare industry is increasingly interested in the Internet of Things (IoT) and the Internet of Medical Things (IoMT). The IoMT facilitates communication of critical information between medical appliances. The paper proposes a machine-learning and deep-learning-based approach to protect IoMT systems from cyber-attacks.
Article
Public, Environmental & Occupational Health
Abdul Rehman Javed, Habib Ullah Khan, Mohammad Kamel Bader Alomari, Muhammad Usman Sarwar, Muhammad Asim, Ahmad S. Almadhor, Muhammad Zahid Khan
Summary: Explainable artificial intelligence (XAI) plays a crucial role in various domains, such as healthcare, fitness, skill assessment, and personal assistants, by providing an understanding and explanation of AI decision-making process. This study introduces XAI-HAR, a novel XAI-enabled human activity recognition (HAR) approach, which utilizes key features extracted from sensor data collected in a smart home. XAI-HAR utilizes feature selection techniques including physical key features selection (PKFS) and statistical key features selection (SKFS) with a weighted criteria to ensure accurate activity recognition.
FRONTIERS IN PUBLIC HEALTH
(2023)
Article
Mathematics
Mohana Alanazi, Abdulaziz Alanazi, Ahmad Almadhor, Hafiz Tayyab Rauf
Summary: This paper proposes an optimal and multi-objective planning method for a hybrid energy system (HES) with wind turbine and battery storage (WT/Battery). The method aims to reduce power loss, improve voltage profile, enhance customer reliability, and minimize the net present cost of the system. The research uses a novel metaheuristic algorithm called improved Fick's law algorithm (IFLA) to find the optimal installation site and size of the hybrid system. Simulation results show that the multi-objective planning approach improves voltage and reliability, and reduces power loss by effectively managing the reserve power and optimizing power injection into the network.
Article
Environmental Sciences
Zhongguan Huang, Shuainan Chen, Guodao Zhang, Ahmad Almadhor, Rujie Li, Meixuan Li, Mohamed Abbas, Binh Nguyen Le, Jie Zhang, Yideng Huang
Summary: As human activities continue to pose a threat to our environment, including the inner ear, new strategies are needed to combat the problem. Nanocatalyst-loaded cochlear implants provide a promising solution for the targeted treatment of inner ear infections, offering better therapeutic efficacy than traditional methods.
ENVIRONMENTAL RESEARCH
(2023)
Article
Environmental Sciences
Nan Zheng, Zhiang Yao, Shanhui Tao, Ahmad Almadhor, Mohammed S. Alqahtani, Rania M. Ghoniem, Huajun Zhao, Shijun Li
Summary: Breast cancer is the leading cause of death in women aged 35 to 54. Nanotechnology plays a crucial role in tumor treatment and detection. The study utilized convolutional neural networks and adaptive neuro-fuzzy inference system to early detect breast cancer based on nine different indicators.
ENVIRONMENTAL RESEARCH
(2023)
Article
Chemistry, Analytical
Ahmad Almadhor, Gabriel Avelino Sampedro, Mideth Abisado, Sidra Abbas
Summary: This research aimed to detect stress using a stacking model based on machine learning algorithms using chest-based features from the Wearable Stress and Affect Detection (WESAD) dataset. The efficiency of the proposed model was estimated regarding accuracy, precision, recall, and F1-score. The experimental outcome illustrated the efficacy of the proposed stacking technique, achieving 0.99% accuracy, and outperforming traditional methodologies and previous studies.
Article
Engineering, Multidisciplinary
Aysha Bibi, Gabriel Avelino Sampedro, Ahmad Almadhor, Abdul Rehman Javed, Tai-hoon Kim
Summary: Given the increasing frequency of network attacks, there is an urgent need for more effective network security measures. This research paper introduces a deep learning-based approach for network intrusion detection to overcome the challenges faced by AI-driven methods. The proposed approach utilizes various classification algorithms and achieves impressive accuracy rates on multiple datasets.
Article
Computer Science, Artificial Intelligence
Nasir Saleem, Jiechao Gao, Rizwana Irfan, Ahmad Almadhor, Hafiz Tayyab Rauf, Yudong Zhang, Seifedine Kadry
Summary: This article proposes a deep learning-based approach called DeepCNN for speech emotion recognition. By parallelising convolutional neural networks and a convolution layer-based transformer, this method allows for effective feature representation with lower computational cost. Experimental results on the EMO-BD and IEMOCAP datasets demonstrate the superior performance of DeepCNN in emotion recognition accuracy.
CAAI TRANSACTIONS ON INTELLIGENCE TECHNOLOGY
(2023)
Article
Computer Science, Information Systems
Sidra Abbas, Abdullah Al Hejaili, Gabriel Avelino Sampedro, Mideth Abisado, Ahmad S. Almadhor, Tariq Shahzad, Khmaies Ouahada
Summary: The rise of the Internet of Things (IoT) has increased the importance of cybersecurity research. This study proposes a novel approach using federated learning and the CIC_IoT 2023 dataset to identify large attacks on IoT devices, achieving impressive accuracy.
Article
Computer Science, Information Systems
Sidra Abbas, Gabriel Avelino Sampedro, Mideth Abisado, Ahmad S. Almadhor, Tai-Hoon Kim, Monji Mohamed Zaidi
Summary: This paper proposes an ensemble stacking machine learning approach for accurately predicting novel DDI hazard indicators. Experimental results show that the proposed method outperforms traditional machine learning approaches in terms of accuracy and efficiency.