Related references
Note: Only part of the references are listed.
Article
Computer Science, Hardware & Architecture
Abdullah Alsaedi et al.
Summary: This article proposes a framework called UnSupervised Misbehaviour Detection (USMD) that uses a deep neural network and long-short term memory method to monitor and identify attacks on CPSs in real-time. Experimental results show that USMD outperforms six state-of-the-art methods on various datasets.
IEEE TRANSACTIONS ON DEPENDABLE AND SECURE COMPUTING
(2023)
Article
Automation & Control Systems
Pedro Ruzafa-Alcazar et al.
Summary: Federated learning (FL) has gained significant attention for its advantages and applicability, but sharing updated gradients/weights in the training process raises privacy concerns, especially in the context of IoT. Our work comprehensively evaluates differential privacy techniques applied to an FL-enabled intrusion detection system (IDS) for industrial IoT, considering nonindependent and identically distributed data. We compare the accuracy achieved with different privacy requirements and aggregation functions (FedAvg and Fed+), and find that using Fed+ yields similar results even with noise in the federated training process.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2023)
Article
Automation & Control Systems
Sk Tanzir Mehedi et al.
Summary: Security concerns for IoT applications have prompted the need for sophisticated defense solutions. Deep learning and deep transfer learning are potential approaches for network intrusion detection. However, traditional IDS face new challenges in a heterogeneous IoT setup.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2023)
Article
Engineering, Civil
Ayodeji Oseni et al.
Summary: The paper proposes an explainable deep learning-based intrusion detection framework to improve transparency and resiliency of DL-based IDS in IoT networks. The framework employs SHapley Additive exPlanations (SHAP) mechanism to interpret decisions made by deep learning-based IDS and help cybersecurity experts validate the system's effectiveness and develop more cyber-resilient systems. Experimental results show that the proposed framework performs highly in protecting IoV networks against sophisticated cyber-attacks.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
Sheng Feng et al.
Summary: This article proposes a deep learning model for classifying high-dimensional data and aims to achieve optimal evaluation accuracy and robustness using multicriteria decision-making. A novel one-dimensional visual geometry group network (1D_VGGNet) is introduced to overcome the complexity and instability of high-dimensional data. Additionally, a one-dimensional convolutional neural network (1D_CNN) is used to effectively handle one-dimensional multicriteria decision-making.
APPLIED SOFT COMPUTING
(2023)
Article
Computer Science, Artificial Intelligence
Hesamodin Mohammadian et al.
Summary: Intrusion detection systems play a crucial role in defending networks against security threats. Deep neural networks have shown excellent performance in intrusion detection, but they are vulnerable to adversarial attacks. This paper proposes a new approach using Jacobian Saliency Map to generate adversarial examples for deep learning-based malicious network activity classification. The experiments demonstrate that the proposed method achieves better performance with fewer features compared to other attacks.
APPLIED SOFT COMPUTING
(2023)
Review
Computer Science, Artificial Intelligence
Ayoub Si-Ahmed et al.
Summary: The Internet of Medical Things (IoMT) has revolutionized the healthcare industry by enabling physiological data collection using sensors and transmitting them for analysis. It offers benefits like early disease detection and automatic medication, but also presents security risks like patient privacy violations. Therefore, adopting robust security measures is crucial to ensure data integrity and confidentiality.
APPLIED SOFT COMPUTING
(2023)
Article
Computer Science, Hardware & Architecture
Guowen Wu et al.
Summary: Social Internet of Things (SIoT) is a fusion of Internet of Things and social networks, which has attracted attention as a target for hackers to spread viruses and breach data confidentiality. To address these problems, a novel virus spread model (STSIR) based on epidemic theory and game theory is proposed, which considers people behavior and the characteristics of SIoTs. The model STSIR introduces an individual-group game to establish the attack and defense model between infected and susceptible SIoT nodes, and differential equations to represent the model. Simulation results show that the model STSIR is more effective in curbing virus spread compared to traditional SIS and SIR models.
JOURNAL OF NETWORK AND COMPUTER APPLICATIONS
(2023)
Article
Computer Science, Theory & Methods
Guowen Wu et al.
Summary: To meet the computing requirements of industrial production, EIIoT that combines mobile edge computing with IIoT has emerged. An optimization model based on queuing theory is proposed to solve the task offloading problem in EIIoT. The improved MAQDRL algorithm achieves optimal offloading strategy in dynamic and random multiuser offloading environments.
JOURNAL OF PARALLEL AND DISTRIBUTED COMPUTING
(2023)
Article
Computer Science, Information Systems
Chao Wang et al.
Summary: This article proposes a blockchain-enabled resource orchestration scheme for IoT using deep reinforcement learning. The scheme allows the IoT edge server and end user to reach a consensus on network resource allocation based on blockchain theory. By utilizing a policy network, the intelligent agent can perceive changes in the network's state and make dynamic resource allocation decisions. Simulation results demonstrate that the proposed scheme performs better than other security resource allocation algorithms, with average revenue, user request acceptance rate, and profitability increased by 8.5%, 1.8%, and 11.9%, respectively.
IEEE INTERNET OF THINGS JOURNAL
(2023)
Article
Computer Science, Artificial Intelligence
Shigen Shen et al.
Summary: This study proposes a signaling game approach for privacy preservation in edge-computing-based IoT networks. It addresses the issue of malicious IoT nodes requesting private data from an IoT cloud storage system across edge nodes. The optimal privacy preservation strategies for edge nodes are derived and a signaling Q-learning algorithm is designed to achieve convergent equilibrium and game parameters. Simulation results show that the proposed algorithm effectively decreases the optimal probability of malicious requests, enhancing privacy preservation in edge-computing-based IoT cloud storage systems.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Computer Science, Information Systems
Guowen Wu et al.
Summary: In the scenario of Industry 4.0, mobile smart devices face challenges in processing massive amounts of data. To address this issue, a software-defined network-based mobile edge computing system is proposed to offload computation tasks to edge servers, reducing processing latency and energy consumption. A stochastic game-based computation offloading model is established, demonstrating the achievement of Nash Equilibrium. The proposed stochastic game-based resource allocation algorithm with prioritized experience replays (SGRA-PERs) outperforms other algorithms in reducing processing delay and energy consumption, even in large-scale MEC systems.
IEEE INTERNET OF THINGS JOURNAL
(2023)
Article
Telecommunications
Yizhou Shen et al.
Summary: This article presents evolutionary privacy preservation learning strategies for an edge computing-based IoT data sharing scheme, addressing the issue of malicious requests and proposing a new algorithm for optimal learning strategy.
DIGITAL COMMUNICATIONS AND NETWORKS
(2023)
Article
Computer Science, Theory & Methods
Shigen Shen et al.
Summary: This paper proposes a two-layer malware spread-patch model based on IIoT and designs a new algorithm suitable for suppressing the spread of malware. The effectiveness of the model and algorithm is verified through in-depth analysis and numerous comparative experiments.
IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY
(2023)
Article
Computer Science, Information Systems
Shivani Singh et al.
Summary: Edge computing is a technological advancement that connects sensors and provides services at the device end, but security is a major concern. This article explores the security and privacy issues in different layers of the Edge computing architecture and the machine learning algorithms used to address these concerns. It also discusses various types of attacks on the Edge network and introduces intrusion detection systems and machine learning algorithms that overcome these security and privacy challenges.
IEEE INTERNET OF THINGS JOURNAL
(2022)
Article
Computer Science, Cybernetics
Laisen Nie et al.
Summary: The Social Internet of Things has become part of our daily lives and collaborative edge computing is introduced as a new paradigm to address IoT needs. However, the proximity of edge networks to connected devices raises privacy concerns and security issues, prompting the proposal of a deep learning-based intrusion detection algorithm to enhance security.
IEEE TRANSACTIONS ON COMPUTATIONAL SOCIAL SYSTEMS
(2022)
Article
Computer Science, Artificial Intelligence
Earum Mushtaq et al.
Summary: This study proposes a hybrid framework for intrusion detection system using a combination of deep auto-encoder (AE) and long short term memory (LSTM). Experimental results show that the proposed AE-LSTM model achieves higher classification accuracy and detection rate on the NSL-KDD dataset compared to other deep and shallow machine learning techniques, indicating its superior performance.
APPLIED SOFT COMPUTING
(2022)
Article
Computer Science, Information Systems
Segun Popoola et al.
Summary: This article proposes a federated deep learning method for zero-day botnet attack detection in IoT-edge devices. The method generates a global model by coordinating the training of independent models in multiple IoT-edge devices, achieving high-performance classification detection of zero-day botnet attacks and ensuring data privacy and security.
IEEE INTERNET OF THINGS JOURNAL
(2022)
Article
Computer Science, Theory & Methods
Yunseong Lee et al.
Summary: This paper proposes a new user association control method for maximizing system utility in mmWave-based HMEC systems. The proposed method achieves low communication overhead and computation complexity, while significantly improving system throughput, edge throughput, and reducing handover cost.
FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE
(2022)
Article
Engineering, Multidisciplinary
Xiaogang Zhu et al.
Summary: SIoT applications are vulnerable to attacks, and therefore, measures need to be taken to improve their security. This paper proposes a fuzzy testing method called BECFuzz, which instruments specific edges and conducts fuzzy testing based on both edge coverage and path coverage, effectively improving the effectiveness of fuzzy testing.
IEEE TRANSACTIONS ON NETWORK SCIENCE AND ENGINEERING
(2022)
Article
Computer Science, Hardware & Architecture
Youyang Qu et al.
Summary: This article discusses the issues faced by digital twin networks (DTNs), such as centralized processing, data falsification, and privacy leakage, and proposes a novel blockchain-enabled adaptive asynchronous federated learning (FedTwin) paradigm to address these challenges.
Article
Automation & Control Systems
Wei Liang et al.
Summary: In this article, an optimized model is proposed to address intrusion detection in imbalanced datasets and apply microservice architecture in distributed IoT systems. The model improves multiclass classification performance by optimizing the intra/inter-class structure using reconstructed feature embeddings and a nonlinear neural network.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2022)
Article
Computer Science, Information Systems
Peiying Zhang et al.
Summary: Space-air-ground integration is a key trend in the 6G era, and efficient scheduling of multi-dimension network resources is a major challenge. By employing reinforcement learning and a bandwidth-aware virtual network resource allocation algorithm, the proposed approach outperforms conventional algorithms in terms of long-term average reward, acceptance rate, and long-term reward/cost.
IEEE TRANSACTIONS ON NETWORK AND SERVICE MANAGEMENT
(2022)
Article
Computer Science, Hardware & Architecture
Mohanad Sarhan et al.
Summary: This paper proposes a hierarchical blockchain-based federated learning framework for secure and privacy-preserved collaborative IoT intrusion detection. By sharing cyber threat intelligence, the detection capabilities of the model are improved.
COMPUTERS & ELECTRICAL ENGINEERING
(2022)
Article
Automation & Control Systems
Panjun Sun et al.
Summary: This paper constructs a new tripartite game model to enhance trust and cooperation among service participants. By calculating the ideal stable state point, it addresses the trust issues in network edge services, and designs relevant experimental studies to verify and compare the correctness and effectiveness of several factors that affect the convergence stability of the evolutionary games.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2022)
Article
Computer Science, Information Systems
Noora Mohammed Al-Maslamani et al.
Summary: Federated learning is a method that leverages datasets from multiple devices to improve machine learning model performance while preserving privacy. However, FL is susceptible to adversarial attacks. In this article, a reputation-based mechanism is proposed to evaluate the reliability and trustworthiness of workers, and a deep reinforcement learning (DRL) algorithm is used to enhance the accuracy and stability of the FL model.
IEEE INTERNET OF THINGS JOURNAL
(2022)
Article
Computer Science, Information Systems
Omar Abdel Wahab
Summary: Machine learning-based intrusion detection systems in the Internet of Things (IoT) often struggle to maintain performance in dynamic environments due to data drift and concept drift. We propose a drift detection technique using PCA to study variance changes in intrusion detection data streams, as well as an online outlier detection technique. Additionally, our online deep neural network (DNN) adjusts hidden layer sizes dynamically using the Hedge weighting mechanism to adapt to new intrusion data. Experimental results show that our solution stabilizes intrusion detection performance compared to static DNN models.
IEEE INTERNET OF THINGS JOURNAL
(2022)
Article
Telecommunications
Ajay Kumar et al.
Summary: Internet of Things (IoT) security refers to the act of securing IoT devices and networks. This study proposes Intrusion Detection Systems (IDSs) and Network-based Intrusion Prevention Systems (NBIPSs) to protect cloud servers and IoT systems from illegal access. The proposed NBIPS inspects network activity streams to identify and counteract misuse instances, providing an additional layer of investigation to safeguard the network system.
DIGITAL COMMUNICATIONS AND NETWORKS
(2022)
Article
Computer Science, Theory & Methods
Zihao Cheng et al.
Summary: This paper investigates the secure frequency control problem in multi-area hybrid power systems with wind power. The hybrid power system is modeled as a switched system, and the exponential stability of the system under DoS attacks is studied. An active defense scheme is proposed to design the control gains, and the load disturbance attenuant performance is analyzed using the concepts of vulnerability point and resilience point. The estimation methods for vulnerability point and resilience point are given under a certain attack model, and simulations are conducted to verify the theories.
IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY
(2022)
Article
Telecommunications
Ajay Kumar et al.
Summary: The study proposes an intrusion prevention system to create a NBIPS for top to bottom protection. The NBIPS inspects network activity streams to identify and counteract instances of misuse. Generally located behind a firewall, the NBIPS provides a reciprocal layer of investigation to mitigate risks.
DIGITAL COMMUNICATIONS AND NETWORKS
(2022)
Article
Computer Science, Information Systems
Jie Mu et al.
Summary: This paper proposes a textual anomaly detection network that overcomes the limitations of the CVDD method through adversarial training strategy and a textual anomaly detection module constructed with multiple dimensional transformation matrices, achieving better performance on several textual datasets.
COMPUTER COMMUNICATIONS
(2021)
Article
Computer Science, Information Systems
Jusik Yun et al.
Summary: This article proposes a deep network shard-based blockchain scheme that dynamically finds the optimal throughput configuration by analyzing the latency and security-level characteristics of sharded blockchain. Using deep reinforcement learning, the system parameters are optimized to achieve higher TPS and security level by adapting to the network status. Simulation results show that this DQNSB scheme provides a higher TPS compared to existing DRL-enabled blockchain technology while maintaining a high security level.
IEEE INTERNET OF THINGS JOURNAL
(2021)
Article
Computer Science, Information Systems
Xing Liu et al.
Summary: The Industrial Internet of Things (IIoT) improves production efficiency through automation and Internet of Things (IoT) technologies, but also introduces security threats. Deep Reinforcement Learning (DRL) shows potential in automated control of complex IIoT systems, but its vulnerabilities must be considered. Research investigates the impact of simulated attacks on DRL-based IIoT controllers and suggests future research directions for securing machine learning in IIoT systems.
COMPUTER COMMUNICATIONS
(2021)
Article
Computer Science, Information Systems
Xiaohu Liu et al.
Summary: Defense decision-making in cybersecurity has increasingly relied upon stochastic game processes, with the present study addressing the limitations of the MDP approach by using a partially observable MDP and DQN algorithm. This approach enables network defense strategies to gradually approach an optimal defense strategy by leveraging online learning.
COMPUTERS & SECURITY
(2021)
Article
Computer Science, Information Systems
Mohamed Abdel-Basset et al.
Summary: The study introduces a semi-supervised deep learning approach for intrusion detection in IoT networks, utilizing a multiscale residual temporal convolutional module and an improved traffic attention mechanism for network fine-tuning and information concentration. A hierarchical semi-supervised training method is introduced to consider the sequential characteristics of IoT traffic data.
IEEE INTERNET OF THINGS JOURNAL
(2021)
Article
Computer Science, Information Systems
Zhiming Liu et al.
Summary: This article introduces RAFT+, a new leader selection scheme based on the distributed consensus algorithm RAFT, which uses a deep Q-Network to optimize leader selection and improve system performance by reducing disparities between different types of IoT end devices while maintaining system security.
IEEE INTERNET OF THINGS JOURNAL
(2021)
Proceedings Paper
Telecommunications
Anand Mudgerikar et al.
Summary: Reinforcement Learning is an effective technique for building 'smart' SDN controllers, but may pose security risks during exploration. The Jarvis-SDN framework proposed in this paper focuses on learning intelligent policies to maximize functionality while ensuring security.
IEEE INTERNATIONAL CONFERENCE ON COMMUNICATIONS (ICC 2021)
(2021)
Article
Engineering, Electrical & Electronic
Ning Gao et al.
IEEE TRANSACTIONS ON COMMUNICATIONS
(2020)
Article
Computer Science, Information Systems
Hui Xia et al.
IEEE INTERNET OF THINGS JOURNAL
(2020)
Article
Computer Science, Information Systems
Nagarathna Ravi et al.
IEEE INTERNET OF THINGS JOURNAL
(2020)
Review
Computer Science, Information Systems
M. S. Roopa et al.
COMPUTER COMMUNICATIONS
(2019)
Article
Computer Science, Hardware & Architecture
Shigen Shen et al.
JOURNAL OF NETWORK AND COMPUTER APPLICATIONS
(2019)
Article
Computer Science, Information Systems
Nadia Chaabouni et al.
IEEE COMMUNICATIONS SURVEYS AND TUTORIALS
(2019)
Article
Computer Science, Hardware & Architecture
Jinxue Zhang et al.
IEEE TRANSACTIONS ON DEPENDABLE AND SECURE COMPUTING
(2018)
Article
Computer Science, Theory & Methods
Abebe Abeshu Diro et al.
FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE
(2018)
Article
Computer Science, Theory & Methods
Liang Xiao et al.
IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY
(2018)
Article
Computer Science, Information Systems
Shigen Shen et al.
IEEE INTERNET OF THINGS JOURNAL
(2018)
Article
Computer Science, Hardware & Architecture
Kai Yang et al.
IEEE WIRELESS COMMUNICATIONS
(2018)
