With the gradual penetration of the internet of things(IoT)into all areas of life,the scale of IoT devices shows an explosive growth trend.The era of internet of everything is coming,and the important position of IoT ...With the gradual penetration of the internet of things(IoT)into all areas of life,the scale of IoT devices shows an explosive growth trend.The era of internet of everything is coming,and the important position of IoT security is becoming increasingly prominent.Due to the large number types of IoT devices,there may be different security vulnerabilities,and unknown attack forms and virus samples are appear.In other words,large number of IoT devices,large data volumes,and various attack forms pose a big challenge of malicious traffic identification.To solve these problems,this paper proposes a concept drift detection and adaptation(CDDA)method for IoT security framework.The AI model performance is evaluated by verifying the effectiveness of IoT traffic for data drift detection,so as to select the best AI model.The experimental test are given to confirm that the feasibility of the framework and the adaptive method in practice,and the effect on the performance of IoT traffic identification is also verified.展开更多
In the last decade,IoT has been widely used in smart cities,autonomous driving and Industry 4.0,which lead to improve efficiency,reliability,security and economic benefits.However,with the rapid development of new tec...In the last decade,IoT has been widely used in smart cities,autonomous driving and Industry 4.0,which lead to improve efficiency,reliability,security and economic benefits.However,with the rapid development of new technologies,such as cognitive communication,cloud computing,quantum computing and big data,the IoT security is being confronted with a series of new threats and challenges.IoT device identification via Radio Frequency Fingerprinting(RFF)extracting from radio signals is a physical-layer method for IoT security.In physical-layer,RFF is a unique characteristic of IoT device themselves,which can difficultly be tampered.Just as people’s unique fingerprinting,different IoT devices exhibit different RFF which can be used for identification and authentication.In this paper,the structure of IoT device identification is proposed,the key technologies such as signal detection,RFF extraction,and classification model is discussed.Especially,based on the random forest and Dempster-Shafer evidence algorithm,a novel ensemble learning algorithm is proposed.Through theoretical modeling and experimental verification,the reliability and differentiability of RFF are extracted and verified,the classification result is shown under the real IoT device environments.展开更多
IoT security is very crucial to IoT applications,and security situational awareness can assess the overall security status of the IoT.Traditional situational awareness methods only consider the unilateral impact of at...IoT security is very crucial to IoT applications,and security situational awareness can assess the overall security status of the IoT.Traditional situational awareness methods only consider the unilateral impact of attack or defense,but lackconsideration of joint actions by both parties.Applying gametheory to security situational awareness can measure the impact of the opposition and interdependence of the offensive and defensive parties.This paper proposes an IoT security situational awareness method based on Q-Learning and Bayesian game.Through Q-Learning update,the long-term benefits of action strategies in specific states were obtained,and static Bayesian game methods were used to solve the Bayesian Nash Equilibrium of participants of different types.The proposed method comprehensively considers offensive and defensive actions,obtains optimal defense decisions in multi-state and multi-type situations,and evaluates security situation.Experimental results prove the effectiveness of this method.展开更多
The rapid expansion of the Internet of Things(IoT)has introduced significant security challenges due to the scale,complexity,and heterogeneity of interconnected devices.The current traditional centralized security mod...The rapid expansion of the Internet of Things(IoT)has introduced significant security challenges due to the scale,complexity,and heterogeneity of interconnected devices.The current traditional centralized security models are deemed irrelevant in dealing with these threats,especially in decentralized applications where the IoT devices may at times operate on minimal resources.The emergence of new technologies,including Artificial Intelligence(AI),blockchain,edge computing,and Zero-Trust-Architecture(ZTA),is offering potential solutions as it helps with additional threat detection,data integrity,and system resilience in real-time.AI offers sophisticated anomaly detection and prediction analytics,and blockchain delivers decentralized and tamper-proof insurance over device communication and exchange of information.Edge computing enables low-latency character processing by distributing and moving the computational workload near the devices.The ZTA enhances security by continuously verifying each device and user on the network,adhering to the“never trust,always verify”ideology.The present research paper is a review of these technologies,finding out how they are used in securing IoT ecosystems,the issues of such integration,and the possibility of developing a multi-layered,adaptive security structure.Major concerns,such as scalability,resource limitations,and interoperability,are identified,and the way to optimize the application of AI,blockchain,and edge computing in zero-trust IoT systems in the future is discussed.展开更多
Internet of Things(IoT)refers to the infrastructures that connect smart devices to the Internet,operating autonomously.This connectivitymakes it possible to harvest vast quantities of data,creating new opportunities f...Internet of Things(IoT)refers to the infrastructures that connect smart devices to the Internet,operating autonomously.This connectivitymakes it possible to harvest vast quantities of data,creating new opportunities for the emergence of unprecedented knowledge.To ensure IoT securit,various approaches have been implemented,such as authentication,encoding,as well as devices to guarantee data integrity and availability.Among these approaches,Intrusion Detection Systems(IDS)is an actual security solution,whose performance can be enhanced by integrating various algorithms,including Machine Learning(ML)and Deep Learning(DL),enabling proactive and accurate detection of threats.This study proposes to optimize the performance of network IDS using an ensemble learning method based on a voting classification algorithm.By combining the strengths of three powerful algorithms,Random Forest(RF),K-Nearest Neighbors(KNN),and Support Vector Machine(SVM)to detect both normal behavior and different categories of attack.Our analysis focuses primarily on the NSL-KDD dataset,while also integrating the recent Edge-IIoT dataset,tailored to industrial IoT environments.Experimental results show significant enhancements on the Edge-IIoT and NSL-KDD datasets,reaching accuracy levels between 72%to 99%,with precision between 87%and 99%,while recall values and F1-scores are also between 72%and 99%,for both normal and attack detection.Despite the promising results of this study,it suffers from certain limitations,notably the use of specific datasets and the lack of evaluations in a variety of environments.Future work could include applying this model to various datasets and evaluating more advanced ensemble strategies,with the aim of further enhancing the effectiveness of IDS.展开更多
Internet of Things(IoT)has become widely used nowadays and tremendous increase in the number of users raises its security requirements as well.The constraints on resources such as low computational capabilities and po...Internet of Things(IoT)has become widely used nowadays and tremendous increase in the number of users raises its security requirements as well.The constraints on resources such as low computational capabilities and power requirements demand lightweight cryptosystems.Conventional algorithms are not applicable in IoT network communications because of the constraints mentioned above.In this work,a novel and efficient scheme for providing security in IoT applications is introduced.The scheme proposes how security can be enhanced in a distributed IoT application by providing multilevel protection and dynamic key generation in the data uploading and transfer phases.Existing works rely on a single key for communication between sensing device and the attached gateway node.In proposed scheme,this session key is updated after each session and this is done by applying principles of cellular automata.The proposed system provides multilevel security by using incomparable benefits of blockchain,dynamic key and random number generation based on cellular automata.The same was implemented and tested with the widely known security protocol verification tool called Automated Validation of Internet Security Protocols and Applications(AVISPA).Results show that the scheme is secure against various attacks.The proposed scheme has been compared with related schemes and the result analysis shows that the new scheme is fast and efficient also.展开更多
The explosive expansion of the Internet of Things(IoT)systems has increased the imperative to have strong and robust solutions to cyber Security,especially to curtail Distributed Denial of Service(DDoS)attacks,which c...The explosive expansion of the Internet of Things(IoT)systems has increased the imperative to have strong and robust solutions to cyber Security,especially to curtail Distributed Denial of Service(DDoS)attacks,which can cripple critical infrastructure.The proposed framework presented in the current paper is a new hybrid scheme that induces deep learning-based traffic classification and blockchain-enabledmitigation tomake intelligent,decentralized,and real-time DDoS countermeasures in an IoT network.The proposed model fuses the extracted deep features with statistical features and trains them by using traditional machine-learning algorithms,which makes them more accurate in detection than statistical features alone,based on the Convolutional Neural Network(CNN)architecture,which can extract deep features.A permissioned blockchain will be included to record the threat cases immutably and automatically execute mitigation measures through smart contracts to provide transparency and resilience.When tested on two test sets,BoT-IoT and IoT-23,the framework obtains a maximum F1-score at 97.5 percent and only a 1.8 percent false positive rate,which compares favorably to other solutions regarding effectiveness and the amount of time required to respond.Our findings support the feasibility of our method as an extensible and secure paradigm of nextgeneration IoT security,which has constrictive utility in mission-critical or resource-constrained settings.The work is a substantial milestone in autonomous and trustful mitigation against DDoS attacks through intelligent learning and decentralized enforcement.展开更多
Attacks are growing more complex and dangerous as network capabilities improve at a rapid pace.Network intrusion detection is usually regarded as an efficient means of dealing with security attacks.Many ways have been...Attacks are growing more complex and dangerous as network capabilities improve at a rapid pace.Network intrusion detection is usually regarded as an efficient means of dealing with security attacks.Many ways have been presented,utilizing various strategies and focusing on different types of visitors.Anomaly-based network intrusion monitoring is an essential area of intrusion detection investigation and development.Despite extensive research on anomaly-based network detection,there is still a lack of comprehensive literature reviews covering current methodologies and datasets.Despite the substantial research into anomaly-based network intrusion detection algorithms,there is a dearth of a research evaluation of new methodologies and datasets.We explore and evaluate 50 highest publications on anomaly-based intrusion detection using an in-depth review of related literature techniques.Our work thoroughly explores the technological environment of the subject in order to help future research in this sector.Our examination is carried out from the relevant angles:application areas,data preprocessing and threat detection approaches,assessment measures,and datasets.We select unresolved research difficulties and underexplored research areas from every viewpoint recommendation of the study.Finally,we outline five potentially increased research areas for the future.展开更多
The increasing deployment of Internet of Things(IoT)devices has introduced significant security chal-lenges,including identity spoofing,unauthorized access,and data integrity breaches.Traditional security mechanisms r...The increasing deployment of Internet of Things(IoT)devices has introduced significant security chal-lenges,including identity spoofing,unauthorized access,and data integrity breaches.Traditional security mechanisms rely on centralized frameworks that suffer from single points of failure,scalability issues,and inefficiencies in real-time security enforcement.To address these limitations,this study proposes the Blockchain-Enhanced Trust and Access Control for IoT Security(BETAC-IoT)model,which integrates blockchain technology,smart contracts,federated learning,and Merkle tree-based integrity verification to enhance IoT security.The proposed model eliminates reliance on centralized authentication by employing decentralized identity management,ensuring tamper-proof data storage,and automating access control through smart contracts.Experimental evaluation using a synthetic IoT dataset shows that the BETAC-IoT model improves access control enforcement accuracy by 92%,reduces device authentication time by 52%(from 2.5 to 1.2 s),and enhances threat detection efficiency by 7%(from 85%to 92%)using federated learning.Additionally,the hybrid blockchain architecture achieves a 300%increase in transaction throughput when comparing private blockchain performance(1200 TPS)to public chains(300 TPS).Access control enforcement accuracy was quantified through confusion matrix analysis,with high precision and minimal false positives observed across access decision categories.Although the model presents advantages in security and scalability,challenges such as computational overhead,blockchain storage constraints,and interoperability with existing IoT systems remain areas for future research.This study contributes to advancing decentralized security frameworks for IoT,providing a resilient and scalable solution for securing connected environments.展开更多
IoT has emerged as a game-changing technology that connects numerous gadgets to networks for communication,processing,and real-time monitoring across diverse applications.Due to their heterogeneous nature and constrai...IoT has emerged as a game-changing technology that connects numerous gadgets to networks for communication,processing,and real-time monitoring across diverse applications.Due to their heterogeneous nature and constrained resources,as well as the growing trend of using smart gadgets,there are privacy and security issues that are not adequately managed by conventional securitymeasures.This review offers a thorough analysis of contemporary AI solutions designed to enhance security within IoT ecosystems.The intersection of AI technologies,including ML,and blockchain,with IoT privacy and security is systematically examined,focusing on their efficacy in addressing core security issues.The methodology involves a detailed exploration of existing literature and research on AI-driven privacy-preserving security mechanisms in IoT.The reviewed solutions are categorized based on their ability to tackle specific security challenges.The review highlights key advancements,evaluates their practical applications,and identifies prevailing research gaps and challenges.The findings indicate that AI solutions,particularly those leveraging ML and blockchain,offerpromising enhancements to IoT privacy and security by improving threat detection capabilities and ensuring data integrity.This paper highlights how AI technologies might strengthen IoT privacy and security and offer suggestions for upcoming studies intended to address enduring problems and improve the robustness of IoT networks.展开更多
The conventional dynamic heterogeneous redundancy(DHR)architecture suffers from the security threats caused by the stability differences and similar vulnerabilities among the executors.To overcome these challenges,we ...The conventional dynamic heterogeneous redundancy(DHR)architecture suffers from the security threats caused by the stability differences and similar vulnerabilities among the executors.To overcome these challenges,we propose an intelligent DHR architecture,which is more feasible by intelligently combining the random distribution based dynamic scheduling algorithm(RD-DS)and information weight and heterogeneity based arbitrament(IWHA)algorithm.In the proposed architecture,the random distribution function and information weight are employed to achieve the optimal selection of executors in the process of RD-DS,which avoids the case that some executors fail to be selected due to their stability difference in the conventional DHR architecture.Then,through introducing the heterogeneity to restrict the information weights in the procedure of the IWHA,the proposed architecture solves the common mode escape issue caused by the existence of multiple identical error output results of similar vulnerabilities.The experimental results characterize that the proposed architecture outperforms in heterogeneity,scheduling times,security,and stability over the conventional DHR architecture under the same conditions.展开更多
Secure data communication is an essential requirement for an Internet of Things(IoT)system.Especially in Industrial Internet of Things(IIoT)and Internet of Medical Things(IoMT)systems,when important data are hacked,it...Secure data communication is an essential requirement for an Internet of Things(IoT)system.Especially in Industrial Internet of Things(IIoT)and Internet of Medical Things(IoMT)systems,when important data are hacked,it may induce property loss or life hazard.Even though many IoTrelated communication protocols are equipped with secure policies,they still have some security weaknesses in their IoT systems.LoRaWAN is one of the low power wide-area network protocols,and it adopts Advanced Encryption Standard(AES)to provide message integrity and confidentiality.However,LoRaWAN’s encryption key update scheme can be further improved.In this paper,a Two-stage High-efficiency LoRaWAN encryption key Update Scheme(THUS for short)is proposed to update LoRaWAN’s root keys and session keys in a secure and efficient way.The THUS consists of two stages,i.e.,the Root Key Update(RKU)stage and the Session Key Update(SKU)stage,and with different update frequencies,the RKU and SKU provide higher security level than the normal LoRaWAN specification does.A modified AES encryption/decryption process is also utilized in the THUS for enhancing the security of the THUS.The security analyses demonstrate that the THUS not only protects important parameter during key update stages,but also satisfies confidentiality,integrity,and mutual authentication.Moreover,The THUS can further resist replay and eavesdropping attacks.展开更多
Industrial internet of things (IIoT) is the usage of internet of things(IoT) devices and applications for the purpose of sensing, processing andcommunicating real-time events in the industrial system to reduce the unn...Industrial internet of things (IIoT) is the usage of internet of things(IoT) devices and applications for the purpose of sensing, processing andcommunicating real-time events in the industrial system to reduce the unnecessary operational cost and enhance manufacturing and other industrial-relatedprocesses to attain more profits. However, such IoT based smart industriesneed internet connectivity and interoperability which makes them susceptibleto numerous cyber-attacks due to the scarcity of computational resourcesof IoT devices and communication over insecure wireless channels. Therefore, this necessitates the design of an efficient security mechanism for IIoTenvironment. In this paper, we propose a hyperelliptic curve cryptography(HECC) based IIoT Certificateless Signcryption (IIoT-CS) scheme, with theaim of improving security while lowering computational and communicationoverhead in IIoT environment. HECC with 80-bit smaller key and parameterssizes offers similar security as elliptic curve cryptography (ECC) with 160-bitlong key and parameters sizes. We assessed the IIoT-CS scheme security byapplying formal and informal security evaluation techniques. We used Realor Random (RoR) model and the widely used automated validation of internet security protocols and applications (AVISPA) simulation tool for formalsecurity analysis and proved that the IIoT-CS scheme provides resistance tovarious attacks. Our proposed IIoT-CS scheme is relatively less expensivecompared to the current state-of-the-art in terms of computational cost andcommunication overhead. Furthermore, the IIoT-CS scheme is 31.25% and 51.31% more efficient in computational cost and communication overhead,respectively, compared to the most recent protocol.展开更多
In this paper,an advanced and optimized Light Gradient Boosting Machine(LGBM)technique is proposed to identify the intrusive activities in the Internet of Things(IoT)network.The followings are the major contributions:...In this paper,an advanced and optimized Light Gradient Boosting Machine(LGBM)technique is proposed to identify the intrusive activities in the Internet of Things(IoT)network.The followings are the major contributions:i)An optimized LGBM model has been developed for the identification of malicious IoT activities in the IoT network;ii)An efficient evolutionary optimization approach has been adopted for finding the optimal set of hyper-parameters of LGBM for the projected problem.Here,a Genetic Algorithm(GA)with k-way tournament selection and uniform crossover operation is used for efficient exploration of hyper-parameter search space;iii)Finally,the performance of the proposed model is evaluated using state-of-the-art ensemble learning and machine learning-based model to achieve overall generalized performance and efficiency.Simulation outcomes reveal that the proposed approach is superior to other considered methods and proves to be a robust approach to intrusion detection in an IoT environment.展开更多
In recent times,technology has advanced significantly and is currently being integrated into educational environments to facilitate distance learning and interaction between learners.Integrating the Internet of Things...In recent times,technology has advanced significantly and is currently being integrated into educational environments to facilitate distance learning and interaction between learners.Integrating the Internet of Things(IoT)into education can facilitate the teaching and learning process and expand the context in which students learn.Nevertheless,learning data is very sensitive and must be protected when transmitted over the network or stored in data centers.Moreover,the identity and the authenticity of interacting students,instructors,and staff need to be verified to mitigate the impact of attacks.However,most of the current security and authentication schemes are centralized,relying on trusted third-party cloud servers,to facilitate continuous secure communication.In addition,most of these schemes are resourceintensive;thus,security and efficiency issues arise when heterogeneous and resource-limited IoT devices are being used.In this paper,we propose a blockchain-based architecture that accurately identifies and authenticates learners and their IoT devices in a decentralized manner and prevents the unauthorized modification of stored learning records in a distributed university network.It allows students and instructors to easily migrate to and join multiple universities within the network using their identity without the need for user re-authentication.The proposed architecture was tested using a simulation tool,and measured to evaluate its performance.The simulation results demonstrate the ability of the proposed architecture to significantly increase the throughput of learning transactions(40%),reduce the communication overhead and response time(26%),improve authentication efficiency(27%),and reduce the IoT power consumption(35%)compared to the centralized authentication mechanisms.In addition,the security analysis proves the effectiveness of the proposed architecture in resisting various attacks and ensuring the security requirements of learning data in the university network.展开更多
The speech recognition technology has been increasingly common in our lives.Recently,a number of commercial smart speakers containing the personal assistant system using speech recognition came out.While the smart spe...The speech recognition technology has been increasingly common in our lives.Recently,a number of commercial smart speakers containing the personal assistant system using speech recognition came out.While the smart speaker vendors have been concerned about the intelligence and the convenience of their assistants,but there have been little mentions of the smart speakers in security aspects.As the smart speakers are becoming the hub for home automation,its security vulnerabilities can cause critical problems.In this paper,we categorize attack vectors and classify them into hardware-based,network-based,and software-based.With the attack vectors,we describe the detail attack scenarios and show the result of tests on several commercial smart speakers.In addition,we suggest guidelines to mitigate various attacks against smart speaker ecosystem.展开更多
The lightweight encryption algorithm based on Add-Rotation-XOR(ARX)operation has attracted much attention due to its high software affinity and fast operation speed.However,lacking an effective defense scheme for phys...The lightweight encryption algorithm based on Add-Rotation-XOR(ARX)operation has attracted much attention due to its high software affinity and fast operation speed.However,lacking an effective defense scheme for physical attacks limits the applications of the ARX algorithm.The critical challenge is how to weaken the direct dependence between the physical information and the secret key of the algorithm at a low cost.This study attempts to explore how to improve its physical security in practical application scenarios by analyzing the masking countermeasures of ARX algorithms and the leakage causes.Firstly,we specify a hierarchical security framework by quantitatively evaluating the indicators based on side-channel attacks.Then,optimize the masking algorithm to achieve a trade-off balance by leveraging the software-based local masking strategies and non-full-round masking strategies.Finally,refactor the assembly instruction to improve the leaks by exploring the leakage cause at assembly instruction.To illustrate the feasibility of the proposed scheme,we further conducted a case study by designing a software-based masking method for Chaskey.The experimental results show that the proposed method can effectively weaken the impact of physical attacks.展开更多
A lightweight malware detection and family classification system for the Internet of Things (IoT) was designed to solve the difficulty of deploying defense models caused by the limited computing and storage resources ...A lightweight malware detection and family classification system for the Internet of Things (IoT) was designed to solve the difficulty of deploying defense models caused by the limited computing and storage resources of IoT devices. By training complex models with IoT software gray-scale images and utilizing the gradient-weighted class-activated mapping technique, the system can identify key codes that influence model decisions. This allows for the reconstruction of gray-scale images to train a lightweight model called LMDNet for malware detection. Additionally, the multi-teacher knowledge distillation method is employed to train KD-LMDNet, which focuses on classifying malware families. The results indicate that the model’s identification speed surpasses that of traditional methods by 23.68%. Moreover, the accuracy achieved on the Malimg dataset for family classification is an impressive 99.07%. Furthermore, with a model size of only 0.45M, it appears to be well-suited for the IoT environment. By training complex models using IoT software gray-scale images and utilizing the gradient-weighted class-activated mapping technique, the system can identify key codes that influence model decisions. This allows for the reconstruction of gray-scale images to train a lightweight model called LMDNet for malware detection. Thus, the presented approach can address the challenges associated with malware detection and family classification in IoT devices.展开更多
The proliferation of Internet of Things(IoT)devices has established edge computing as a critical paradigm for real-time data analysis and low-latency processing.Nevertheless,the distributed nature of edge computing pr...The proliferation of Internet of Things(IoT)devices has established edge computing as a critical paradigm for real-time data analysis and low-latency processing.Nevertheless,the distributed nature of edge computing presents substantial security challenges,rendering it a prominent target for sophisticated malware attacks.Existing signature-based and behavior-based detection methods are ineffective against the swiftly evolving nature of malware threats and are constrained by the availability of resources.This paper suggests the Genetic Encoding for Novel Optimization of Malware Evaluation(GENOME)framework,a novel solution that is intended to improve the performance of malware detection and classification in peripheral computing environments.GENOME optimizes data storage and computa-tional efficiency by converting malware artifacts into compact,structured sequences through a Deoxyribonucleic Acid(DNA)encoding mechanism.The framework employs two DNA encoding algorithms,standard and compressed,which substantially reduce data size while preserving high detection accuracy.The Edge-IIoTset dataset was used to conduct experiments that showed that GENOME was able to achieve high classification performance using models such as Random Forest and Logistic Regression,resulting in a reduction of data size by up to 42%.Further evaluations with the CIC-IoT-23 dataset and Deep Learning models confirmed GENOME’s scalability and adaptability across diverse datasets and algorithms.The potential of GENOME to address critical challenges,such as the rapid mutation of malware,real-time processing demands,and resource limitations,is emphasized in this study.GENOME offers comprehensive protection for peripheral computing environments by offering a security solution that is both efficient and scalable.展开更多
The Internet of Things(IoT)integrates more than billions of intelligent devices over the globe with the capabilityof communicating with other connected devices with little to no human intervention.IoT enables data agg...The Internet of Things(IoT)integrates more than billions of intelligent devices over the globe with the capabilityof communicating with other connected devices with little to no human intervention.IoT enables data aggregationand analysis on a large scale to improve life quality in many domains.In particular,data collected by IoT containa tremendous amount of information for anomaly detection.The heterogeneous nature of IoT is both a challengeand an opportunity for cybersecurity.Traditional approaches in cybersecurity monitoring often require different kindsof data pre-processing and handling for various data types,which might be problematic for datasets that contain heterogeneousfeatures.However,heterogeneous types of network devices can often capture a more diverse set of signalsthan a single type of device readings,which is particularly useful for anomaly detection.In this paper,we presenta comprehensive study on using ensemble machine learning methods for enhancing IoT cybersecurity via anomalydetection.Rather than using one single machine learning model,ensemble learning combines the predictive powerfrom multiple models,enhancing their predictive accuracy in heterogeneous datasets rather than using one singlemachine learning model.We propose a unified framework with ensemble learning that utilises Bayesian hyperparameteroptimisation to adapt to a network environment that contains multiple IoT sensor readings.Experimentally,weillustrate their high predictive power when compared to traditional methods.展开更多
基金supported by 2023 Teaching Research Project of the Education Department of Anhui Province:Exploration of Optimizing Teaching Strategies for Embedded Courses in the Context of“New Engineering”(Project No.2023jyxm0460)2024 High-quality Course on Ideological and Political Education Integrated into Curriculum at Anhui University of Engineering:“Data Structures and Algorithms”(Project No.2024szyzk40)Industry-University-Research Cooperation Project of Anhui University of Engineering:“Online detection of surface quality defects in high-speed wire rod”(Project No.HX-2024-11-003).
文摘With the gradual penetration of the internet of things(IoT)into all areas of life,the scale of IoT devices shows an explosive growth trend.The era of internet of everything is coming,and the important position of IoT security is becoming increasingly prominent.Due to the large number types of IoT devices,there may be different security vulnerabilities,and unknown attack forms and virus samples are appear.In other words,large number of IoT devices,large data volumes,and various attack forms pose a big challenge of malicious traffic identification.To solve these problems,this paper proposes a concept drift detection and adaptation(CDDA)method for IoT security framework.The AI model performance is evaluated by verifying the effectiveness of IoT traffic for data drift detection,so as to select the best AI model.The experimental test are given to confirm that the feasibility of the framework and the adaptive method in practice,and the effect on the performance of IoT traffic identification is also verified.
文摘In the last decade,IoT has been widely used in smart cities,autonomous driving and Industry 4.0,which lead to improve efficiency,reliability,security and economic benefits.However,with the rapid development of new technologies,such as cognitive communication,cloud computing,quantum computing and big data,the IoT security is being confronted with a series of new threats and challenges.IoT device identification via Radio Frequency Fingerprinting(RFF)extracting from radio signals is a physical-layer method for IoT security.In physical-layer,RFF is a unique characteristic of IoT device themselves,which can difficultly be tampered.Just as people’s unique fingerprinting,different IoT devices exhibit different RFF which can be used for identification and authentication.In this paper,the structure of IoT device identification is proposed,the key technologies such as signal detection,RFF extraction,and classification model is discussed.Especially,based on the random forest and Dempster-Shafer evidence algorithm,a novel ensemble learning algorithm is proposed.Through theoretical modeling and experimental verification,the reliability and differentiability of RFF are extracted and verified,the classification result is shown under the real IoT device environments.
基金the National Key Research and Development Program of China(No.2017YFB1400700).
文摘IoT security is very crucial to IoT applications,and security situational awareness can assess the overall security status of the IoT.Traditional situational awareness methods only consider the unilateral impact of attack or defense,but lackconsideration of joint actions by both parties.Applying gametheory to security situational awareness can measure the impact of the opposition and interdependence of the offensive and defensive parties.This paper proposes an IoT security situational awareness method based on Q-Learning and Bayesian game.Through Q-Learning update,the long-term benefits of action strategies in specific states were obtained,and static Bayesian game methods were used to solve the Bayesian Nash Equilibrium of participants of different types.The proposed method comprehensively considers offensive and defensive actions,obtains optimal defense decisions in multi-state and multi-type situations,and evaluates security situation.Experimental results prove the effectiveness of this method.
基金the Deanship of Graduate Studies and Scientific Research at Qassim University for financial support(QU-APC-2025).
文摘The rapid expansion of the Internet of Things(IoT)has introduced significant security challenges due to the scale,complexity,and heterogeneity of interconnected devices.The current traditional centralized security models are deemed irrelevant in dealing with these threats,especially in decentralized applications where the IoT devices may at times operate on minimal resources.The emergence of new technologies,including Artificial Intelligence(AI),blockchain,edge computing,and Zero-Trust-Architecture(ZTA),is offering potential solutions as it helps with additional threat detection,data integrity,and system resilience in real-time.AI offers sophisticated anomaly detection and prediction analytics,and blockchain delivers decentralized and tamper-proof insurance over device communication and exchange of information.Edge computing enables low-latency character processing by distributing and moving the computational workload near the devices.The ZTA enhances security by continuously verifying each device and user on the network,adhering to the“never trust,always verify”ideology.The present research paper is a review of these technologies,finding out how they are used in securing IoT ecosystems,the issues of such integration,and the possibility of developing a multi-layered,adaptive security structure.Major concerns,such as scalability,resource limitations,and interoperability,are identified,and the way to optimize the application of AI,blockchain,and edge computing in zero-trust IoT systems in the future is discussed.
文摘Internet of Things(IoT)refers to the infrastructures that connect smart devices to the Internet,operating autonomously.This connectivitymakes it possible to harvest vast quantities of data,creating new opportunities for the emergence of unprecedented knowledge.To ensure IoT securit,various approaches have been implemented,such as authentication,encoding,as well as devices to guarantee data integrity and availability.Among these approaches,Intrusion Detection Systems(IDS)is an actual security solution,whose performance can be enhanced by integrating various algorithms,including Machine Learning(ML)and Deep Learning(DL),enabling proactive and accurate detection of threats.This study proposes to optimize the performance of network IDS using an ensemble learning method based on a voting classification algorithm.By combining the strengths of three powerful algorithms,Random Forest(RF),K-Nearest Neighbors(KNN),and Support Vector Machine(SVM)to detect both normal behavior and different categories of attack.Our analysis focuses primarily on the NSL-KDD dataset,while also integrating the recent Edge-IIoT dataset,tailored to industrial IoT environments.Experimental results show significant enhancements on the Edge-IIoT and NSL-KDD datasets,reaching accuracy levels between 72%to 99%,with precision between 87%and 99%,while recall values and F1-scores are also between 72%and 99%,for both normal and attack detection.Despite the promising results of this study,it suffers from certain limitations,notably the use of specific datasets and the lack of evaluations in a variety of environments.Future work could include applying this model to various datasets and evaluating more advanced ensemble strategies,with the aim of further enhancing the effectiveness of IDS.
文摘Internet of Things(IoT)has become widely used nowadays and tremendous increase in the number of users raises its security requirements as well.The constraints on resources such as low computational capabilities and power requirements demand lightweight cryptosystems.Conventional algorithms are not applicable in IoT network communications because of the constraints mentioned above.In this work,a novel and efficient scheme for providing security in IoT applications is introduced.The scheme proposes how security can be enhanced in a distributed IoT application by providing multilevel protection and dynamic key generation in the data uploading and transfer phases.Existing works rely on a single key for communication between sensing device and the attached gateway node.In proposed scheme,this session key is updated after each session and this is done by applying principles of cellular automata.The proposed system provides multilevel security by using incomparable benefits of blockchain,dynamic key and random number generation based on cellular automata.The same was implemented and tested with the widely known security protocol verification tool called Automated Validation of Internet Security Protocols and Applications(AVISPA).Results show that the scheme is secure against various attacks.The proposed scheme has been compared with related schemes and the result analysis shows that the new scheme is fast and efficient also.
文摘The explosive expansion of the Internet of Things(IoT)systems has increased the imperative to have strong and robust solutions to cyber Security,especially to curtail Distributed Denial of Service(DDoS)attacks,which can cripple critical infrastructure.The proposed framework presented in the current paper is a new hybrid scheme that induces deep learning-based traffic classification and blockchain-enabledmitigation tomake intelligent,decentralized,and real-time DDoS countermeasures in an IoT network.The proposed model fuses the extracted deep features with statistical features and trains them by using traditional machine-learning algorithms,which makes them more accurate in detection than statistical features alone,based on the Convolutional Neural Network(CNN)architecture,which can extract deep features.A permissioned blockchain will be included to record the threat cases immutably and automatically execute mitigation measures through smart contracts to provide transparency and resilience.When tested on two test sets,BoT-IoT and IoT-23,the framework obtains a maximum F1-score at 97.5 percent and only a 1.8 percent false positive rate,which compares favorably to other solutions regarding effectiveness and the amount of time required to respond.Our findings support the feasibility of our method as an extensible and secure paradigm of nextgeneration IoT security,which has constrictive utility in mission-critical or resource-constrained settings.The work is a substantial milestone in autonomous and trustful mitigation against DDoS attacks through intelligent learning and decentralized enforcement.
文摘Attacks are growing more complex and dangerous as network capabilities improve at a rapid pace.Network intrusion detection is usually regarded as an efficient means of dealing with security attacks.Many ways have been presented,utilizing various strategies and focusing on different types of visitors.Anomaly-based network intrusion monitoring is an essential area of intrusion detection investigation and development.Despite extensive research on anomaly-based network detection,there is still a lack of comprehensive literature reviews covering current methodologies and datasets.Despite the substantial research into anomaly-based network intrusion detection algorithms,there is a dearth of a research evaluation of new methodologies and datasets.We explore and evaluate 50 highest publications on anomaly-based intrusion detection using an in-depth review of related literature techniques.Our work thoroughly explores the technological environment of the subject in order to help future research in this sector.Our examination is carried out from the relevant angles:application areas,data preprocessing and threat detection approaches,assessment measures,and datasets.We select unresolved research difficulties and underexplored research areas from every viewpoint recommendation of the study.Finally,we outline five potentially increased research areas for the future.
文摘The increasing deployment of Internet of Things(IoT)devices has introduced significant security chal-lenges,including identity spoofing,unauthorized access,and data integrity breaches.Traditional security mechanisms rely on centralized frameworks that suffer from single points of failure,scalability issues,and inefficiencies in real-time security enforcement.To address these limitations,this study proposes the Blockchain-Enhanced Trust and Access Control for IoT Security(BETAC-IoT)model,which integrates blockchain technology,smart contracts,federated learning,and Merkle tree-based integrity verification to enhance IoT security.The proposed model eliminates reliance on centralized authentication by employing decentralized identity management,ensuring tamper-proof data storage,and automating access control through smart contracts.Experimental evaluation using a synthetic IoT dataset shows that the BETAC-IoT model improves access control enforcement accuracy by 92%,reduces device authentication time by 52%(from 2.5 to 1.2 s),and enhances threat detection efficiency by 7%(from 85%to 92%)using federated learning.Additionally,the hybrid blockchain architecture achieves a 300%increase in transaction throughput when comparing private blockchain performance(1200 TPS)to public chains(300 TPS).Access control enforcement accuracy was quantified through confusion matrix analysis,with high precision and minimal false positives observed across access decision categories.Although the model presents advantages in security and scalability,challenges such as computational overhead,blockchain storage constraints,and interoperability with existing IoT systems remain areas for future research.This study contributes to advancing decentralized security frameworks for IoT,providing a resilient and scalable solution for securing connected environments.
基金The author Dr.Arshiya Sajid Ansari extends the appreciation to the Deanship of Postgraduate Studies and Scientific Research at Majmaah University for funding this research work through the project number(R-2025-1706).
文摘IoT has emerged as a game-changing technology that connects numerous gadgets to networks for communication,processing,and real-time monitoring across diverse applications.Due to their heterogeneous nature and constrained resources,as well as the growing trend of using smart gadgets,there are privacy and security issues that are not adequately managed by conventional securitymeasures.This review offers a thorough analysis of contemporary AI solutions designed to enhance security within IoT ecosystems.The intersection of AI technologies,including ML,and blockchain,with IoT privacy and security is systematically examined,focusing on their efficacy in addressing core security issues.The methodology involves a detailed exploration of existing literature and research on AI-driven privacy-preserving security mechanisms in IoT.The reviewed solutions are categorized based on their ability to tackle specific security challenges.The review highlights key advancements,evaluates their practical applications,and identifies prevailing research gaps and challenges.The findings indicate that AI solutions,particularly those leveraging ML and blockchain,offerpromising enhancements to IoT privacy and security by improving threat detection capabilities and ensuring data integrity.This paper highlights how AI technologies might strengthen IoT privacy and security and offer suggestions for upcoming studies intended to address enduring problems and improve the robustness of IoT networks.
基金supported by the National Key Research and Development Program of China(2020YFE0200600)the National Natural Science Foundation of China(U22B2026)。
文摘The conventional dynamic heterogeneous redundancy(DHR)architecture suffers from the security threats caused by the stability differences and similar vulnerabilities among the executors.To overcome these challenges,we propose an intelligent DHR architecture,which is more feasible by intelligently combining the random distribution based dynamic scheduling algorithm(RD-DS)and information weight and heterogeneity based arbitrament(IWHA)algorithm.In the proposed architecture,the random distribution function and information weight are employed to achieve the optimal selection of executors in the process of RD-DS,which avoids the case that some executors fail to be selected due to their stability difference in the conventional DHR architecture.Then,through introducing the heterogeneity to restrict the information weights in the procedure of the IWHA,the proposed architecture solves the common mode escape issue caused by the existence of multiple identical error output results of similar vulnerabilities.The experimental results characterize that the proposed architecture outperforms in heterogeneity,scheduling times,security,and stability over the conventional DHR architecture under the same conditions.
文摘Secure data communication is an essential requirement for an Internet of Things(IoT)system.Especially in Industrial Internet of Things(IIoT)and Internet of Medical Things(IoMT)systems,when important data are hacked,it may induce property loss or life hazard.Even though many IoTrelated communication protocols are equipped with secure policies,they still have some security weaknesses in their IoT systems.LoRaWAN is one of the low power wide-area network protocols,and it adopts Advanced Encryption Standard(AES)to provide message integrity and confidentiality.However,LoRaWAN’s encryption key update scheme can be further improved.In this paper,a Two-stage High-efficiency LoRaWAN encryption key Update Scheme(THUS for short)is proposed to update LoRaWAN’s root keys and session keys in a secure and efficient way.The THUS consists of two stages,i.e.,the Root Key Update(RKU)stage and the Session Key Update(SKU)stage,and with different update frequencies,the RKU and SKU provide higher security level than the normal LoRaWAN specification does.A modified AES encryption/decryption process is also utilized in the THUS for enhancing the security of the THUS.The security analyses demonstrate that the THUS not only protects important parameter during key update stages,but also satisfies confidentiality,integrity,and mutual authentication.Moreover,The THUS can further resist replay and eavesdropping attacks.
基金This work is supported by the University of Malaya IIRG Grant(IIRG008A-19IISSN),Ministry of Education FRGS Grant(FP055-2019A)This work was also supported by Grant System of University of Zilina No.1/2020.(Project No.7962)partially supported by the Slovak Grant Agency for Science(VEGA)under Grant Number 1/0157/21.The authors are grateful to the Taif University Researchers Supporting Project(Number TURSP-2020/36),Taif University,Taif,Saudi Arabia.
文摘Industrial internet of things (IIoT) is the usage of internet of things(IoT) devices and applications for the purpose of sensing, processing andcommunicating real-time events in the industrial system to reduce the unnecessary operational cost and enhance manufacturing and other industrial-relatedprocesses to attain more profits. However, such IoT based smart industriesneed internet connectivity and interoperability which makes them susceptibleto numerous cyber-attacks due to the scarcity of computational resourcesof IoT devices and communication over insecure wireless channels. Therefore, this necessitates the design of an efficient security mechanism for IIoTenvironment. In this paper, we propose a hyperelliptic curve cryptography(HECC) based IIoT Certificateless Signcryption (IIoT-CS) scheme, with theaim of improving security while lowering computational and communicationoverhead in IIoT environment. HECC with 80-bit smaller key and parameterssizes offers similar security as elliptic curve cryptography (ECC) with 160-bitlong key and parameters sizes. We assessed the IIoT-CS scheme security byapplying formal and informal security evaluation techniques. We used Realor Random (RoR) model and the widely used automated validation of internet security protocols and applications (AVISPA) simulation tool for formalsecurity analysis and proved that the IIoT-CS scheme provides resistance tovarious attacks. Our proposed IIoT-CS scheme is relatively less expensivecompared to the current state-of-the-art in terms of computational cost andcommunication overhead. Furthermore, the IIoT-CS scheme is 31.25% and 51.31% more efficient in computational cost and communication overhead,respectively, compared to the most recent protocol.
文摘In this paper,an advanced and optimized Light Gradient Boosting Machine(LGBM)technique is proposed to identify the intrusive activities in the Internet of Things(IoT)network.The followings are the major contributions:i)An optimized LGBM model has been developed for the identification of malicious IoT activities in the IoT network;ii)An efficient evolutionary optimization approach has been adopted for finding the optimal set of hyper-parameters of LGBM for the projected problem.Here,a Genetic Algorithm(GA)with k-way tournament selection and uniform crossover operation is used for efficient exploration of hyper-parameter search space;iii)Finally,the performance of the proposed model is evaluated using state-of-the-art ensemble learning and machine learning-based model to achieve overall generalized performance and efficiency.Simulation outcomes reveal that the proposed approach is superior to other considered methods and proves to be a robust approach to intrusion detection in an IoT environment.
文摘In recent times,technology has advanced significantly and is currently being integrated into educational environments to facilitate distance learning and interaction between learners.Integrating the Internet of Things(IoT)into education can facilitate the teaching and learning process and expand the context in which students learn.Nevertheless,learning data is very sensitive and must be protected when transmitted over the network or stored in data centers.Moreover,the identity and the authenticity of interacting students,instructors,and staff need to be verified to mitigate the impact of attacks.However,most of the current security and authentication schemes are centralized,relying on trusted third-party cloud servers,to facilitate continuous secure communication.In addition,most of these schemes are resourceintensive;thus,security and efficiency issues arise when heterogeneous and resource-limited IoT devices are being used.In this paper,we propose a blockchain-based architecture that accurately identifies and authenticates learners and their IoT devices in a decentralized manner and prevents the unauthorized modification of stored learning records in a distributed university network.It allows students and instructors to easily migrate to and join multiple universities within the network using their identity without the need for user re-authentication.The proposed architecture was tested using a simulation tool,and measured to evaluate its performance.The simulation results demonstrate the ability of the proposed architecture to significantly increase the throughput of learning transactions(40%),reduce the communication overhead and response time(26%),improve authentication efficiency(27%),and reduce the IoT power consumption(35%)compared to the centralized authentication mechanisms.In addition,the security analysis proves the effectiveness of the proposed architecture in resisting various attacks and ensuring the security requirements of learning data in the university network.
基金This work was supported by Institute of Information&communications Technology Planning&Evaluation(IITP)grant funded by the Korea government(MSIT)(No.2019-0-00231,Development of artificial intelligence based video security technology and systems for public infrastructure safety)。
文摘The speech recognition technology has been increasingly common in our lives.Recently,a number of commercial smart speakers containing the personal assistant system using speech recognition came out.While the smart speaker vendors have been concerned about the intelligence and the convenience of their assistants,but there have been little mentions of the smart speakers in security aspects.As the smart speakers are becoming the hub for home automation,its security vulnerabilities can cause critical problems.In this paper,we categorize attack vectors and classify them into hardware-based,network-based,and software-based.With the attack vectors,we describe the detail attack scenarios and show the result of tests on several commercial smart speakers.In addition,we suggest guidelines to mitigate various attacks against smart speaker ecosystem.
基金This work was partially supported by the Natural Science Foundation of Jiangsu Province under Grant No.BK20201462partially supported by the Scientific Research Support Project of Jiangsu Normal University under Grant No.21XSRX001.
文摘The lightweight encryption algorithm based on Add-Rotation-XOR(ARX)operation has attracted much attention due to its high software affinity and fast operation speed.However,lacking an effective defense scheme for physical attacks limits the applications of the ARX algorithm.The critical challenge is how to weaken the direct dependence between the physical information and the secret key of the algorithm at a low cost.This study attempts to explore how to improve its physical security in practical application scenarios by analyzing the masking countermeasures of ARX algorithms and the leakage causes.Firstly,we specify a hierarchical security framework by quantitatively evaluating the indicators based on side-channel attacks.Then,optimize the masking algorithm to achieve a trade-off balance by leveraging the software-based local masking strategies and non-full-round masking strategies.Finally,refactor the assembly instruction to improve the leaks by exploring the leakage cause at assembly instruction.To illustrate the feasibility of the proposed scheme,we further conducted a case study by designing a software-based masking method for Chaskey.The experimental results show that the proposed method can effectively weaken the impact of physical attacks.
文摘A lightweight malware detection and family classification system for the Internet of Things (IoT) was designed to solve the difficulty of deploying defense models caused by the limited computing and storage resources of IoT devices. By training complex models with IoT software gray-scale images and utilizing the gradient-weighted class-activated mapping technique, the system can identify key codes that influence model decisions. This allows for the reconstruction of gray-scale images to train a lightweight model called LMDNet for malware detection. Additionally, the multi-teacher knowledge distillation method is employed to train KD-LMDNet, which focuses on classifying malware families. The results indicate that the model’s identification speed surpasses that of traditional methods by 23.68%. Moreover, the accuracy achieved on the Malimg dataset for family classification is an impressive 99.07%. Furthermore, with a model size of only 0.45M, it appears to be well-suited for the IoT environment. By training complex models using IoT software gray-scale images and utilizing the gradient-weighted class-activated mapping technique, the system can identify key codes that influence model decisions. This allows for the reconstruction of gray-scale images to train a lightweight model called LMDNet for malware detection. Thus, the presented approach can address the challenges associated with malware detection and family classification in IoT devices.
基金supported by the Institute of Information&Communications Technology Planning&Evaluation(IITP)(Project Nos.RS-2024-00438551,30%,2022-11220701,30%,2021-0-01816,30%)the National Research Foundation of Korea(NRF)grant funded by the Korean Government(Project No.RS2023-00208460,10%).
文摘The proliferation of Internet of Things(IoT)devices has established edge computing as a critical paradigm for real-time data analysis and low-latency processing.Nevertheless,the distributed nature of edge computing presents substantial security challenges,rendering it a prominent target for sophisticated malware attacks.Existing signature-based and behavior-based detection methods are ineffective against the swiftly evolving nature of malware threats and are constrained by the availability of resources.This paper suggests the Genetic Encoding for Novel Optimization of Malware Evaluation(GENOME)framework,a novel solution that is intended to improve the performance of malware detection and classification in peripheral computing environments.GENOME optimizes data storage and computa-tional efficiency by converting malware artifacts into compact,structured sequences through a Deoxyribonucleic Acid(DNA)encoding mechanism.The framework employs two DNA encoding algorithms,standard and compressed,which substantially reduce data size while preserving high detection accuracy.The Edge-IIoTset dataset was used to conduct experiments that showed that GENOME was able to achieve high classification performance using models such as Random Forest and Logistic Regression,resulting in a reduction of data size by up to 42%.Further evaluations with the CIC-IoT-23 dataset and Deep Learning models confirmed GENOME’s scalability and adaptability across diverse datasets and algorithms.The potential of GENOME to address critical challenges,such as the rapid mutation of malware,real-time processing demands,and resource limitations,is emphasized in this study.GENOME offers comprehensive protection for peripheral computing environments by offering a security solution that is both efficient and scalable.
文摘The Internet of Things(IoT)integrates more than billions of intelligent devices over the globe with the capabilityof communicating with other connected devices with little to no human intervention.IoT enables data aggregationand analysis on a large scale to improve life quality in many domains.In particular,data collected by IoT containa tremendous amount of information for anomaly detection.The heterogeneous nature of IoT is both a challengeand an opportunity for cybersecurity.Traditional approaches in cybersecurity monitoring often require different kindsof data pre-processing and handling for various data types,which might be problematic for datasets that contain heterogeneousfeatures.However,heterogeneous types of network devices can often capture a more diverse set of signalsthan a single type of device readings,which is particularly useful for anomaly detection.In this paper,we presenta comprehensive study on using ensemble machine learning methods for enhancing IoT cybersecurity via anomalydetection.Rather than using one single machine learning model,ensemble learning combines the predictive powerfrom multiple models,enhancing their predictive accuracy in heterogeneous datasets rather than using one singlemachine learning model.We propose a unified framework with ensemble learning that utilises Bayesian hyperparameteroptimisation to adapt to a network environment that contains multiple IoT sensor readings.Experimentally,weillustrate their high predictive power when compared to traditional methods.
