检索结果-内蒙古大学图书馆

Disruptive Technologies (ICDT), international conference on

作者： Rajneesh Kumar Gaurav Gulati Bhupesh Gupta Mohit Chhabra Department of Computer Science & Engineering Maharishi Markandeshwar Engineering College MMDU Mullana Haryana India Department of Computer Science& Engineering IMS Engineering College Ghaziabad UP India

ISBN: (数字)9798331519582

ISBN: (纸本)9798331519599

With technological advancement, distributed Denial of Service (DDoS) attacks are gaining momentum in IoT networks. DDoS attacks are widely spreading on IoT devices since they have limited resources (memory) and no efficient security models. Different security measures are available to protect IoT devices from attacks. Some of these are firewalls, Intrusion detection systems, etc. Recently, researchers have utilized Artificial Intelligence for early detection of attacks due to its capability of detecting menaced attacks and, hence, boosting security. In this paper, a rigorous survey of different AI-enabled state-of-the-art models for detecting DDoS Attacks was done, and the future direction and scope of improvement for early Detection of DDoS attacks on IoT devices were highlighted.

关键词： Surveys Analytical models Firewalls (computing) Memory management Intrusion detection Denial-of-service attack Internet of Things security Artificial intelligence Disruptive technologies

来源：评论

学校读者我要写书评

暂无评论

TruChain: A Blockchain-based Access Control to Improve the security of Smart Water Grid systems

TruChain: A Blockchain-based Access Control to Improve the S...

引用

international Communication systems and networks and Workshops, COMSNETS

作者： Susmita Mondal Suchetana Chakraborty Department of Computer Science and Engineering Indian Institute of Technology Jodhpur

ISBN: (数字)9798331531195

ISBN: (纸本)9798331531201

Water is a significant resource in day-to-day life, and it usually requires technological association for comprehensive management. Smart Water Grids (SWG) typically use cyberphysical systems (CPS) to monitor several parameters associated with water quality and distribution, leveraging the possibility of performing remote operations. For robust architecture, remote operations rely on application-specific sensors, communication networks, edge control, and cloud computation. Needless to say, the centralized control of edge and cloud infrastructure is prone to attacks and failures, such as unauthorized access or single-point-of-failure. We propose TruChain, a Blockchain-based access control mechanism to eliminate the probability of access takeover and aggregate quorum-based validation on sensory data for transparent provenance reliability. We also provide access revocation to strengthen security by restricting access to sensitive data stored in a privately distributed cloud. We believe our solution has empirical decentralization and a verifiable authorization method by maintaining a tamper-evident, auditable trail of interactive events, building trust without third-party intervention.

关键词： Cloud computing Smart contracts systems architecture Water quality Throughput Reliability Sustainable development Water resources Intelligent sensors Monitoring

来源：评论

学校读者我要写书评

暂无评论

On-Device AI security Solutions: A Study on Lightweight Ensemble Learning Technique

On-Device AI Security Solutions: A Study on Lightweight Ense...

引用

international Communication systems and networks and Workshops, COMSNETS

作者： Huiyao Dong Igor Kotenko Faculty of Information Technology and Security ITMO University Saint Petersburg Russia Laboratory of Computer Security Problems St. Petersburg Federal Research Center of the RAS Saint Petersburg Russia

ISBN: (数字)9798331531195

ISBN: (纸本)9798331531201

IoT security poses a significant challenge due to the presence of extensive confidential data and vulnerable devices. Artificial intelligence (AI) is increasingly viewed as pivotal in cybersecurity, enhancing the efficacy of security measures including login mechanisms with fingerprinting, real-time phishing detection, and multi-stage attack identification. However, centralized AI models face issues such as high variance and over-fitting, as well as resource inefficiencies. This study explores the deployment of on-device AI security models in a distributed manner with lightweight yet effective ensemble deep learning techniques. The proposed methods involve lightweight ensemble techniques such as learnable weighted average voting (WAVGVoting) and concatenation-based stacking, integrated with three base learners with distinct structures. The experiments on Edge-IIoT, utilizing 5-fold cross-validation, show that our approaches are effective even in dynamic data and diverse settings. Specifically, the stacking model achieved an average accuracy of 99.8441% with a recall of 99.7762%, while WAVGVoting showed an average precision of 99.9116% and a false alarm rate of 0.0883%, certainly indicating its applicability.

关键词： Accuracy Phishing Stacking Intrusion detection Fingerprint recognition Real-time systems Internet of Things Ensemble learning Artificial intelligence Faces

来源：评论

学校读者我要写书评

暂无评论

Enhancing Peer-to-Peer Network security using 3D Convolutional Autoencoder based Anomaly Detection

Enhancing Peer-to-Peer Network Security using 3D Convolution...

引用

Intelligent systems and Computational networks (ICISCN), international conference on

作者： Rana Veer Samara Sihman Bharattej R Zaid Ajznblasm E. G. Satish Adlin Sylvia A M. Devi Department of Computer Science Saint Leo University FL USA Department of Computers Techniques Engineering College of Technical Engineering The Islamic University of Al Diwaniyah Al Diwaniyah Iraq Department of Computer Science and Engineering Nitte Meenakshi Institute of Technology Bengaluru India Department of Computer Science and Engineering Dhanalakshmi Srinivasan College of Engineering and Technology India Department of Electrical and Electronics Engineering New Prince Shri Bhavani College of Engineering and Technology Chennai India

ISBN: (数字)9798331529246

ISBN: (纸本)9798331529253

In this era, Peer-to-Peer (P2P) networks have developed as a revolutionized network for data distribution and alternate to traditional client-server network. The features of P2P networks allow a distributed group of users to stake resources in the form of digital content or information. However, P2P networks lack in controlling access and it has limited security. In this research, Three Dimensional-Convolutional Autoencoder (3D-CA) is proposed to improve the security in P2P network. Initially, the data is obtained from University of New South Wales Network Behavior 2015 (UNSW-NB15) dataset and then preprocessed with data cleaning to ensure data quality. After that, the P2P autoencoder architecture is employed to learn the normal patterns which employs the detection in P2P network. Finally, the proposed 3D-CA is trained to detect the anomalies based on reconstruction error between input node and reconstructed pattern. From the results, the proposed 3D-CA model attained better outcomes compared to existing K-means algorithm in terms of accuracy, precision as well as F1-score by achieving 0.764, 0.90 and 0.80 respectively.

关键词： Accuracy Three-dimensional displays Scalability Autoencoders Telecommunication traffic Reinforcement learning Probabilistic logic Cleaning Peer-to-peer computing Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

DR3DH: A DoS resistant extended triple Diffie–Hellman for mobile edge networks

引用

computer networks 2025年 265卷

作者： Altaweel, Ala Bouridane, Ahmed Department of Computer Engineering College of Computing and Informatics University of Sharjah Sharjah United Arab Emirates

Mobile Edge networks (MENs) are wireless networks that establish "close-to-end-users-clouds" to provide storage, computation, and communication services. MENs employ the Extended Triple Diffie–Hellman (X3DH) protocol to establish secret keys that provide end-to-end encryption among their nodes. X3DH relies on a cloud server that stores the public keys of the nodes to address the asynchronous scenarios when they operate offline. The cloud server in X3DH protocol represents a single point of failure (SPoF), as the exchange of secure keys is disrupted if the server fails or is compromised. Moreover, a malicious attacker, Eve, can launch various DoS attacks against the MEN nodes (e.g., packet dropping or packet modification) and wireless links (e.g., jamming) to disrupt the execution of X3DH during secure key exchange. This paper proposes the DoS-Resistant-X3DH (DR3DH) protocol to resolve the SPoF of the cloud server in X3DH and to address packet dropping, packet modification, and jamming DoS attacks. DR3DH employs Reed–Solomon Erasure Coding to encode the X3DH public keys into fragments that are distributed into a set of storage nodes. These storage nodes, which are determined by an Integer Linear Programming (ILP) solver, are optimum. That is, they have lowest probabilities to launch packet dropping/modification attacks and lowest probabilities that the wireless links toward them are jammed. The authors evaluated DR3DH through trace-driven simulations in MATLAB using two mobility traces and a proof-of-concept implementation in Java. The authors also compared DR3DH with two approaches that employ Random and Greedy policies when selecting the storage nodes for keys fragments. The results demonstrate the resistance of DR3DH to DoS attacks, achieving a high success rate that outperforms the Random and Greedy approaches by between 13.6% and 83.0%. Additionally, the results confirm the feasibility of DR3DH under different mobility models and node speeds, as demonstrated by

关键词： Packet loss

来源：评论

学校读者我要写书评

暂无评论

Anomaly Detection in Microservices Architecture Using Graph Neural networks

Anomaly Detection in Microservices Architecture Using Graph ...

引用

Euromicro conference on Parallel, distributed and Network-Based Processing

作者： Matthias Osswald Timothy Schönenberger Gokcan Cantali Wissem Soussi Gürkan Gür Zurich University of Applied Sciences (ZHAW) InIT Winterthur Switzerland Communication Systems Group CSG University of Zürich UZH Zürich Switzerland

ISBN: (数字)9798331524937

ISBN: (纸本)9798331524944

The rise of cloud computing has transformed application development and deployment, with Kubernetes emerging as a key platform for managing containerized applications. This paper explores the use of Graph Neural networks (GNNs) to detect anomalies in Kubernetes clusters and proposes GNN-based Anomaly Detection in Kubernetes (GATAKU), which is instrumental in maintaining security and performance. Our work involves integrating Cilium for detailed network monitoring and data collection, setting up a Kubernetes cluster with k3s and Traefik, and simulating attack scenarios to generate realistic data. Data preprocessing and feature engineering prepare this data for the GNN training. We present the GATAKU model’s performance, highlighting metrics such as accuracy, precision, recall, and F 1 -score and compare it to baseline ML models, namely Support Vector Machine (SVM) and Random Forest (RF). Moreover, we discuss these findings and emerging challenges, including handling high-dimensional data, and explore practical implications for cybersecurity.

关键词： Support vector machines Training Cloud computing Analytical models Accuracy computer architecture Graph neural networks computer security Anomaly detection Tuning

来源：评论

学校读者我要写书评

暂无评论

Enhancing DDoS Attack Detection in SDN with a Stacked Model Framework Utilizing Deep Neural networks

Enhancing DDoS Attack Detection in SDN with a Stacked Model ...

引用

IEEE international conference on Consumer Electronics (ICCE)

作者： Aishita Sharma Sunil K. Singh Sudhakar Kumar Shin Hung Pan Brij B. Gupta Kwok Tai Chui Department of CSE Chandigarh College of Engineering and Technology Chandigarh India Department of Information Management Asia University Taiwan Department of Computer Science and Information Engineering Asia University Taiwan University of Economics and Human Sciences in Warsaw Poland Hong Kong Metropolitan University Hong Kong

ISBN: (数字)9798331521165

ISBN: (纸本)9798331521172

Software Defined Networking enhances network management and security through centralized control, vital for the growth of consumer electronics. With the rise of smart devices and IoT systems, the demand for scalable network management has intensified. While SDN streamlines network operations and supports essential technologies, it remains vulnerable to DDoS attacks that can disrupt these services. However, SDN environments are vulnerable to distributed Denial of Service (DDoS) attacks, posing significant risks to operational integrity. This paper analyzes the performance of various machine learning models at the individual level, providing insights into their effectiveness in detecting DDoS attacks. Based on these findings, a hybrid model is introduced, utilizing stacking techniques with a Deep Neural Network (DNN) as the meta-learner. The hybrid approach achieves a remarkable accuracy of 99.09%. The results underscore the crucial role of machine learning, particularly deep learning methodologies, in safeguarding SDN networks against cyber threats. As reliance on complex networked systems in consumer electronics increases, enhancing the security of SDN environments becomes essential for maintaining seamless operations.

关键词： Deep learning Stacking Artificial neural networks Denial-of-service attack security computer crime Software defined networking Smart devices Consumer electronics Centralized control

来源：评论

学校读者我要写书评

暂无评论

Machine Learning based Portable Executable Malware and DDoS Attacks Detection in IoT networks

Machine Learning based Portable Executable Malware and DDoS ...

引用

international conference on ent Computing and Control systems (ICICCS)

作者： S. Balakrishnan S. Leelavathy Sunil Kumar RM S. Simonthomas Department of Computer Science and Engineering Aarupadai Veedu Institute of Technology Vinayaka Mission’s Research Foundation(DU) Chennai Tamil Nadu India Department of AI&DS Panimalar Engineering College Chennai Department of CSE RL Jalappa Institute of Technology Bangalore Rural District Department of Computer Science and Engineering Aarupadai Veedu Institute of Technology VMRF-DU Chennai Tamil Nadu India

ISBN: (数字)9798331512088

ISBN: (纸本)9798331512095

As the Internet of Things digital systems have been becoming increasingly complex, so are the cybersecurity issues, which, in turn, have been heightened by the malicious activities of Portable Executable (PE) malware and distributed Denial of Service (DDoS) attacks. These kinds of threats constitute a significant challenge to the integrity, confidentiality, and availability of connected systems; hence, an immediate need has been identified to design effective detection mechanisms. The development of IoT-based devices has moved at a galloping speed, which was accompanied by enormous security issues of these networks with respect to potential cyber threats caused by PE malware or DDoS. The PE malware exploits vulnerabilities in executable files to breach IoT devices, which most of the time leads to unauthorized access and system compromise. However, DDoS attacks target IoT networks by causing a flood of malicious traffic against them, thereby resulting in service interruptions and great damage. The proposed system uses Multivariate Correlation Analysis (MCA) to evaluate network flow based on the extraction and analysis of spatial relationships among traffic attributes. MCA can prove to be an effective anomaly-based detection mechanism in the case of malicious behavior. The proposed system ensures scalability and real-time capability in terms of detection offered by it by using lightweight machine learning models and combining them with MCA. This strategy intends to enhance IoT environment security through a reliable framework for identifying PE malware and counteracting DDoS attacks.

关键词： Correlation Accuracy Scalability Telecommunication traffic Denial-of-service attack Malware Real-time systems Internet of Things Reliability computer crime

来源：评论

学校读者我要写书评

暂无评论

Data-as-a-Product to enable data-driven value networks in Industries 4.0 & 5.0: The Swiss Smart Factory experiment 16

Data-as-a-Product to enable data-driven value networks in In...

引用

16th international conference on Ambient systems, networks and Technologies networks, ANT 2025 / 8th international conference on Emerging Data and Industry 4.0, EDI40 2025

作者： Nizamis, Alexandros Julian, Matilde Valero, Clara I. Foti, Magda Drigkopoulou, Ioanna Esbrí, Miguel Ángel Costa, Ruben Yortholt, Alexandre Ioannidis, Dimosthenis Gkonis, Panagiotis Trakadas, Panagiotis Tzovaras, Dimitrios Palau, Carlos E. Department of Digital Industry Technologies National and Kapodistrian University of Athens NKUA Euboea Dirfes Messapies 34400 Greece Information Technologies Institute Center for Research and Technology Hellas 6th km Charilaou-Thermi Thessaloniki 57001 Greece Communications Department Universitat Politècnica de València Valencia 46022 Spain Netcompany-Intrasoft S.A 2b rue Nicolas Bové Luxembourg 1253 Luxembourg Eviden Albarracín 25 Madrid 28037 Spain CTS-UNINOVA School of Science and Technology NOVA University of Lisbon Caparica 2829-516 Portugal Department of Port Management and Shipping National and Kapodistrian University of Athens NKUA Euboea Dirfies Messapies 34400 Greece Switzerland Innovation Park Biel/Bienne Ltd Aarbergstrasse 46 Biel/Bienne 2503 Switzerland

Over the years, the economic and strategic potential of data has been identified by companies, and nowadays, data has emerged as a valuable digital asset for them. Data can be offered as a product by combining it with a series of services related to data quality, security, trust, communication, and monetization. In this paper, an implementation of Data-as-a-Product (DaaP) developed in Horizon Europe project RE4DY for its use in industrial environments is presented. DaaP is a core concept to enable distributed data management solutions and collaboration among industrial stakeholders. The architecture of the proposed solution consists of core services to enable data abstraction, interoperability, quality, security, and traceability. In addition to them, Data Space components are considered to provide data sovereignty and trust alongside with a Marketplace to promote the discovery of the shared resources. This implementation has been tested in a use case where data from the Swiss Smart Factory was shared with an analytics service provider. The goals of this experiment were to validate the implemented DaaP solution and to perform an initial evaluation of the potential benefits of this concept. The proposed DaaP implementation provides an easy-to-use environment that simplifies the entire workflow for collecting, pre-processing, and sharing data to create data-driven services, and enhances data quality while saving time and reducing costs. © 2025 Elsevier B.V.. All rights reserved.

关键词： Data security Data Space Data Transformation Data-as-a-Product Factory Experiment

来源：评论

学校读者我要写书评

暂无评论

Exploring blockchain solutions: Integrating cryptocurrency with IoT for enhanced security

Exploring blockchain solutions: Integrating cryptocurrency w...

引用

Pervasive Computational Technologies (ICPCT), international conference on

作者： M Shravan Shital Kakad Umar M Mulani Geeti Sharma Mohit Tiwari Mary Shiba C School of Business SR University Warangal Telangana India Artificial Intelligence and Data Science Vishwakarma Institute of Technology Pune Maharashtra KJ College of Engineering and Management Research Pune Faculty of Management Studies (CMS Business School) Jain Deemed to be University Department of Computer Science and Engineering Bharati Vidyapeeth’s College of Engineering Delhi Delhi Department of Computer Science and Business Systems R.M.K Engineering College Thiruvallur

ISBN: (数字)9798331508685

ISBN: (纸本)9798331519476

Blockchain, initially developed as the underlying technology for Bitcoin, has garnered significant attention for its applications beyond cryptocurrency, particularly in complex non-monetary domains. Utilizing cryptographic methods like hashing and asymmetric encryption, combined with a distributed consensus model, Blockchain-based ledgers achieve high levels of security and immutability, effectively removing the need for third-party intermediaries. Meanwhile, the rapid growth in Internet of Things (IoT) devices being connected to networks raises substantial concerns around security and privacy. Addressing these security challenges is essential for the expanding IoT landscape. This paper explores the blockchain solution by integrating cryptocurrency with IoT for enhanced security, reviewing recent studies and applications to evaluate Blockchain's role in IoT security, pinpoint challenges, and propose Blockchain-driven solutions to improve security in the IoT ecosystem.

关键词： Privacy Ecosystems Focusing Bitcoin Reliability engineering Hardware Blockchains Safety Internet of Things security

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：