IET Cyber-Physical Systems: Theory and Applications最新文献

Efficient learning of uncertainty distributions in coupled multidisciplinary systems through sensory data

IF 1.7

IET Cyber-Physical Systems: Theory and Applications Pub Date : 2025-02-04 DOI: 10.1049/cps2.70000

Negar Asadi, Seyede Fatemeh Ghoreishi

{"title":"Efficient learning of uncertainty distributions in coupled multidisciplinary systems through sensory data","authors":"Negar Asadi, Seyede Fatemeh Ghoreishi","doi":"10.1049/cps2.70000","DOIUrl":"https://doi.org/10.1049/cps2.70000","url":null,"abstract":"Coupled multidisciplinary systems are fundamental to many complex engineering systems, such as those in cyber–physical systems, aerospace engineering, automotive systems, energy networks, and robotics. Accurate analysis, control, and monitoring of these systems depend on effectively inferring their inherent uncertainties. However, the dynamic nature of these systems, along with the interconnectivity of various disciplines, poses significant challenges for uncertainty estimation. This paper presents a framework for learning uncertainty distributions in partially observed coupled multidisciplinary systems. By employing a non-linear/non-Gaussian hidden Markov model (HMM) representation, the authors capture the stochastic nature of system states and observations. The proposed methodology leverages particle filtering techniques and Bayesian optimisation for efficient parameter estimation, accounting for the inherent uncertainties in input statistics. Numerical experiments on a coupled aerodynamics-structures system and a power converter system demonstrate the efficacy of the proposed method in estimating input distribution statistics. The results highlight the critical importance of accounting for non-stationary behaviours in coupled multidisciplinary systems for capturing the true variability of input statistics and showcase the superiority of our method over approaches that assume data derive from the stationary state of the system.","PeriodicalId":36881,"journal":{"name":"IET Cyber-Physical Systems: Theory and Applications","volume":"10 1","pages":""},"PeriodicalIF":1.7,"publicationDate":"2025-02-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1049/cps2.70000","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143111841","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

FL-ADS: Federated learning anomaly detection system for distributed energy resource networks FL-ADS：分布式能源资源网络联合学习异常检测系统

IF 1.7

IET Cyber-Physical Systems: Theory and Applications Pub Date : 2025-01-29 DOI: 10.1049/cps2.70001

Shaurya Purohit, Manimaran Govindarasu, Benjamin Blakely

{"title":"FL-ADS: Federated learning anomaly detection system for distributed energy resource networks","authors":"Shaurya Purohit, Manimaran Govindarasu, Benjamin Blakely","doi":"10.1049/cps2.70001","DOIUrl":"https://doi.org/10.1049/cps2.70001","url":null,"abstract":"With the ongoing development of Distributed Energy Resources (DER) communication networks, the imperative for strong cybersecurity and data privacy safeguards is increasingly evident. DER networks, which rely on protocols such as Distributed Network Protocol 3 and Modbus, are susceptible to cyberattacks such as data integrity breaches and denial of service due to their inherent security vulnerabilities. This paper introduces an innovative Federated Learning (FL)-based anomaly detection system designed to enhance the security of DER networks while preserving data privacy. Our models leverage Vertical and Horizontal Federated Learning to enable collaborative learning while preserving data privacy, exchanging only non-sensitive information, such as model parameters, and maintaining the privacy of DER clients' raw data. The effectiveness of the models is demonstrated through its evaluation on datasets representative of real-world DER scenarios, showcasing significant improvements in accuracy and F1-score across all clients compared to the traditional baseline model. Additionally, this work demonstrates a consistent reduction in loss function over multiple FL rounds, further validating its efficacy and offering a robust solution that balances effective anomaly detection with stringent data privacy needs.","PeriodicalId":36881,"journal":{"name":"IET Cyber-Physical Systems: Theory and Applications","volume":"10 1","pages":""},"PeriodicalIF":1.7,"publicationDate":"2025-01-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1049/cps2.70001","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143120821","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Analysing a multi-stage cyber threat and its impact on the power system

IF 1.7

IET Cyber-Physical Systems: Theory and Applications Pub Date : 2025-01-24 DOI: 10.1049/cps2.12107

Leen Al Homoud, Namrata Barpanda, Vinicius Bobato, Ana Goulart, Kate Davis, Mark Rice

引用次数: 0

Motif-based resiliency assessment for cyber-physical power systems under various hazards

IF 1.7

IET Cyber-Physical Systems: Theory and Applications Pub Date : 2024-12-17 DOI: 10.1049/cps2.12103

Hamed M. Binqadhi, Mohammed M. AlMuhaini, H. Vincent Poor, David Flynn, Hao Huang

{"title":"Motif-based resiliency assessment for cyber-physical power systems under various hazards","authors":"Hamed M. Binqadhi, Mohammed M. AlMuhaini, H. Vincent Poor, David Flynn, Hao Huang","doi":"10.1049/cps2.12103","DOIUrl":"https://doi.org/10.1049/cps2.12103","url":null,"abstract":"Cyber-physical power systems (CPPS) are integral to meeting society's demand for secure, sustainable, affordable and resilient critical networks and services. Given the convergence of decarbonising, heating, cooling, and transportation networks onto cyber-physical power systems (CPPS), this takes on increased significance. This paper introduces an innovative approach to the open challenge of how we evaluate CPPS resilience, presenting the use of network motifs and Monte Carlo simulations. We demonstrate how our methodology enables a comprehensive analysis of CPPS by capturing the interdependence between cyber and physical networks and by accounting for inherent uncertainties in cyber and physical components. Specifically, this method incorporates the dynamic interplay between the physical and cyber networks, presenting a time-dependent motif-based resilience metric. This metric evaluates CPPS performance in maintaining critical loads during and after diverse extreme events in cyber and/or physical layers. The resilience status of the system is determined using the prevalence of 4-node motifs within the system's network, offering valuable redundant paths for critical load supply. The study models a variety of natural events, including earthquakes, windstorms, and tornadoes, along with cyber-attacks while accounting for their inherent uncertainties using Monte Carlo simulation. The proposed approach is demonstrated through two test CPPS, specifically the IEEE 14-bus and IEEE 30-bus test systems, affirming its effectiveness in quantifying CPPS resilience. By comprehensively addressing system dynamics, interdependencies, and uncertainties, the proposed technique advances our understanding of CPPS and supports resilient system design.","PeriodicalId":36881,"journal":{"name":"IET Cyber-Physical Systems: Theory and Applications","volume":"10 1","pages":""},"PeriodicalIF":1.7,"publicationDate":"2024-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1049/cps2.12103","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143362384","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Towards autonomous device protection using behavioural profiling and generative artificial intelligence

IF 1.7

IET Cyber-Physical Systems: Theory and Applications Pub Date : 2024-12-11 DOI: 10.1049/cps2.12102

Sandeep Gupta, Bruno Crispo

{"title":"Towards autonomous device protection using behavioural profiling and generative artificial intelligence","authors":"Sandeep Gupta, Bruno Crispo","doi":"10.1049/cps2.12102","DOIUrl":"https://doi.org/10.1049/cps2.12102","url":null,"abstract":"Demand for autonomous protection in computing devices cannot go unnoticed, considering the rapid proliferation of deployed devices and escalating cyberattacks. Consequently, cybersecurity measures with an improved generalisation that can proactively determine the indicators of compromises to predict 0-day threats or previously unseen malware together with known malware are highly desirable. In this article, the authors present a novel concept of autonomous device protection based on behavioural profiling by continuously monitoring internal resource usage and leveraging generative artificial intelligence (genAI) to distinguish between benign and malicious behaviour. The authors design a proof-of-concept for Windows-based computing devices relying on a built-in event tracing mechanism for log collection that is converted into structured data using a graph data structure. The authors extract graph-level features, that is, graph depth, nodes count, number of leaf nodes, node degree statistics, and events count and node-level features (NLF), that is, process start, file create and registry events details for each graph. Further, the authors investigate the use of genAI exploiting a pre-trained large language network—a simple contrastive sentence embedding framework to extract strong features, that is, dense vectors from event graphs. Finally, the authors train a random forest classifier using both the graph-level features and NLF to obtain classification models that are evaluated on a collected dataset containing one thousand benign and malicious samples achieving accuracy up to 99.25%.","PeriodicalId":36881,"journal":{"name":"IET Cyber-Physical Systems: Theory and Applications","volume":"10 1","pages":""},"PeriodicalIF":1.7,"publicationDate":"2024-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1049/cps2.12102","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143362801","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Winning the battle with cyber risk identification tools in industrial control systems: A review

IF 1.7

IET Cyber-Physical Systems: Theory and Applications Pub Date : 2024-11-17 DOI: 10.1049/cps2.12105

Ayo Rotibi, Neetesh Saxena, Pete Burnap

引用次数: 0

A three-vector model predicting torque control of permanent magnet synchronous motor with a fixed weight coefficient

IF 1.7

IET Cyber-Physical Systems: Theory and Applications Pub Date : 2024-11-14 DOI: 10.1049/cps2.12104

Xingyu Qu, Chengkun Peng, Peng Lu, Bing Ge, Shuang Zhang, Qinghe Wang, Zhenyang Li

{"title":"A three-vector model predicting torque control of permanent magnet synchronous motor with a fixed weight coefficient","authors":"Xingyu Qu, Chengkun Peng, Peng Lu, Bing Ge, Shuang Zhang, Qinghe Wang, Zhenyang Li","doi":"10.1049/cps2.12104","DOIUrl":"https://doi.org/10.1049/cps2.12104","url":null,"abstract":"The difficulty of adjusting the weighting coefficients of the cost function in traditional model predictive torque control is addressed by proposing a fixed weighting coefficient three-vector model predictive torque control (FWC-MPTC) strategy. The strategy applies three voltage vectors in a control period. The first voltage vector is selected by a fixed coefficient cost function, the second and third voltage vectors are determined by a cost function that includes only torque and flux, and the third voltage vector is no longer just a traditional zero vector. In addition, to solve the problem of poor disturbance immunity of the speed loop PI controller, an active disturbance rejection controller (ADRC) is introduced in the speed loop, and the error non-linear function in the controller is rewritten into a smoother new function. The proposed control strategy reduces the torque and speed fluctuation of the traditional three-vector model predictive control (TTV-MPTC), improves the robustness of the system, avoids the difficulty of adjusting the weight coefficient in the traditional cost function, and reduces the computational complexity of the cost function.","PeriodicalId":36881,"journal":{"name":"IET Cyber-Physical Systems: Theory and Applications","volume":"9 4","pages":"509-520"},"PeriodicalIF":1.7,"publicationDate":"2024-11-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1049/cps2.12104","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143252689","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Cloud-mediated self-triggered synchronisation of a general linear multi-agent system over a directed graph

IF 1.7

IET Cyber-Physical Systems: Theory and Applications Pub Date : 2024-07-29 DOI: 10.1049/cps2.12101

Takumi Namba, Kiyotsugu Takaba

{"title":"Cloud-mediated self-triggered synchronisation of a general linear multi-agent system over a directed graph","authors":"Takumi Namba, Kiyotsugu Takaba","doi":"10.1049/cps2.12101","DOIUrl":"https://doi.org/10.1049/cps2.12101","url":null,"abstract":"The authors propose a self-triggered synchronisation control method of a general high-order linear time-invariant multi-agent system through a cloud repository. In the cloud-mediated self-triggered control, each agent asynchronously accesses the cloud repository to obtain past information about its neighbouring agents. Then, the agent predicts future behaviours of its neighbours as well as of its own and locally determines its next access time to the cloud repository. In the case of a general high-order linear agent dynamics, each agent has to estimate exponential evolution of its trajectory characterised by eigenvalues of a system matrix, which is different from single/double integrator or first-order linear agents. The authors’ proposed method deals with exponential behaviours of the agents by tightly evaluating the bounds on matrix exponentials. Based on these bounds, the authors design the self-triggered controller through a cloud that achieves the bounded state synchronization of the closed-loop system without exhibiting any Zeno behaviours. The effectiveness of the proposed method is demonstrated through the numerical simulation.","PeriodicalId":36881,"journal":{"name":"IET Cyber-Physical Systems: Theory and Applications","volume":"9 4","pages":"497-508"},"PeriodicalIF":1.7,"publicationDate":"2024-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1049/cps2.12101","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143253698","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

The threat of zero-dynamics attack on non-linear cyber-physical systems

IF 1.7

IET Cyber-Physical Systems: Theory and Applications Pub Date : 2024-06-27 DOI: 10.1049/cps2.12099

Amir Norouzi Mobarakeh, Mohammad Ataei, Rahmat-Allah Hooshmand

引用次数: 0

Design of an efficient dynamic context-based privacy policy deployment model via dual bioinspired Q learning optimisations

IF 1.7

IET Cyber-Physical Systems: Theory and Applications Pub Date : 2024-06-27 DOI: 10.1049/cps2.12100

Namrata Jiten Patel, Ashish Jadhav

{"title":"Design of an efficient dynamic context-based privacy policy deployment model via dual bioinspired Q learning optimisations","authors":"Namrata Jiten Patel, Ashish Jadhav","doi":"10.1049/cps2.12100","DOIUrl":"https://doi.org/10.1049/cps2.12100","url":null,"abstract":"A novel context-based privacy policy deployment model enhanced with bioinspired Q-learning optimisations is presented. The model addresses the challenge of maintaining privacy while ensuring data integrity and usability in various settings. Leveraging datasets including Adult (Census Income), Yelp, UC Irvine Machine Learning, and Movie Lens, the authors evaluate the model's performance against state-of-the-art techniques, such as GEF AL, Deep Forest, and Robust Continual Learning. The approach employs Firefly Optimiser (FFO) and Ant Lion Optimiser (ALO) algorithms to dynamically adjust privacy parameters and handle large datasets efficiently. Additionally, Q-learning enables intelligent decision-making and rapid adaptation to changing data and network conditions and scenarios. Evaluation results demonstrate that the model consistently outperforms reference techniques across multiple metrics, including privacy levels, scalability, fidelity, and sensitivity management. By reducing reputational harm, minimising delays, and enhancing network quality, the model offers robust privacy protection without sacrificing data utility. Overall, a dynamic context-based privacy policy deployment approach, enhanced with bioinspired Q-learning optimisations, presents a significant advancement in privacy preservation methods. The combination of ALO, FFO, and Q-learning techniques offers a practical solution to evolving data privacy challenges and enhances flexibility in various use case scenarios.","PeriodicalId":36881,"journal":{"name":"IET Cyber-Physical Systems: Theory and Applications","volume":"9 4","pages":"477-496"},"PeriodicalIF":1.7,"publicationDate":"2024-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1049/cps2.12100","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143253351","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0