检索结果-内蒙古大学图书馆

Generative Adversarial Networks-Driven Cyber threat Intelligence Detection Framework for Securing internet of things 19

Generative Adversarial Networks-Driven Cyber Threat Intellig...

引用

19th Annual international conference on distributed computing in Smart Systems and the internet of things, DCOSS-IoT 2023

作者： Ferrag, Mohamed Amine Hamouda, Djallel Debbah, Merouane Maglaras, Leandros Lakas, Abderrahmane Technology Innovation Institute Abu Dhabi Masdar City9639 United Arab Emirates Guelma University Labstic Laboratory Guelma24000 Algeria Edinburgh Napier University Blockpass Id Lab EdinburghEH10 5DT United Kingdom College of Information Technology United Arab Emirates University Al-Ain United Arab Emirates

ISBN: (纸本)9798350346497

While the benefits of 6G-enabled internet of things (IoT) are numerous, providing high-speed, low-latency communication that brings new opportunities for innovation and forms the foundation for continued growth in the IoT industry, it is also important to consider the security challenges and risks associated with the technology. In this paper, we propose a two-stage intrusion detection framework for securing IoTs, which is based on two detectors. In the first stage, we propose an adversarial training approach using generative adversarial networks (GAN) to help the first detector train on robust features by supplying it with adversarial examples as validation sets. Consequently, the classifier would perform very well against adversarial attacks. then, we propose a deep learning (DL) model for the second detector to identify intrusions. We evaluated the proposed approach's efficiency in terms of detection accuracy and robustness against adversarial attacks. Experiment results with a new cyber security dataset demonstrate the effectiveness of the proposed methodology in detecting both intrusions and persistent adversarial examples with a weighted avg of 96%, 95%, 95 %, and 95% for precision, recall, f-score, and accuracy, respectively. © 2023 IEEE.

关键词： internet of things

来源：评论

学校读者我要写书评

暂无评论

Management of Life Cycle of computing Agents with Non-deterministic Lifetime in a Kubernetes Cluster 6

Management of Life Cycle of Computing Agents with Non-determ...

引用

6th IEEE international conference on Information and Telecommunication Technologies and Radio Electronics, UkrMiCo 2023

作者： Alieksieiev, Mykola Smahliuk, Volodymyr Igor Sikorsky Kyiv Polytechnic Institute Kyiv Ukraine

ISBN: (纸本)9798350348484

the work is devoted to the topical issue of effective use of computing resources in systems with a dynamic distributed architecture, that use personal or public computing devices for the needs of distributed computing, in particular the paper is dedicated to the task of effective life cycle management of containerized applications. Unlike the known existing solutions, systems considered in the work have a relatively short-term and non-deterministic lifetime of their computing agents and therefore must have specialized functionality for automatically joining and detaching computing agents from the cluster as far as this process may take time and requires a certain qualification and permissions. So, the problem is to provide a transparent interface for the user and automate cluster operator tasks. the approach proposed in the work is based on the organization of the process of managing working nodes in form of Server Discovery in the Kubernetes cluster environment. the advantage of the proposed approach is a flexible and simple interface for managing working nodes with a non-deterministic life cycle based on developed software that performs operations of checking the user's operating environment, installing the required software to join the cluster, or uninstalling components and disabling the agent on user demand. the paper also describes the experimental environment, conducts a study of the system's operation in possible user behavior scenarios and proves the effectiveness of the approach. © 2023 IEEE.

关键词： Life cycle

来源：评论

学校读者我要写书评

暂无评论

BFT-Metronome: A Novel Byzantine Fault-Tolerant Clock Synchronization Algorithm 6

BFT-Metronome: A Novel Byzantine Fault-Tolerant Clock Synchr...

引用

6th international conference on Blockchain computing and Applications, BCCA 2024

作者： Fulford, Conner Medury, Sai Altarawneh, Amani Skjellum, Anthony Department of Computer Science Engineering University of Tennessee at Chattanooga ChattanoogaTN United States The Advanced Computing Center for Research and Education Vanderbilt University NashvilleTN United States Department of Computer Science Tennessee Tech University CookevilleTN United States

ISBN: (纸本)9798350351538

distributed systems and blockchain consensus protocols rely on a clock synchronization algorithm to resolve any conflicts related to the state of data or resources. Faulty and adversarial peers make it challenging to achieve clock synchronization in a peer-to-peer distributed system. Clock-synchronization protocols such as the Network Time Protocol (NTP) and the Precision Time Protocol (PTP) are effective but only in a partially or fully trusted network. they fail to synchronize clocks in the presence of misbehaving peers who try to rewind or fast-forward time or introduce deadlocks purposely. this paper introduces BFT-Metronome, a Byzantine fault-tolerant clock synchronization algorithm for peer-to-peer distributed systems. the novel BFT-Metronome algorithm combines a sensor-fusion algorithm with a statistical outlier detection algorithm to enable participating peers to determine the most likely skew based on broadcast timestamps. the algorithm is designed to withstand up to N3 − 1 misbehaving participants in a network of N total participants, and the independently calculated offset is observed to be within 10 ms of precision vs. 40-100 ms in peer-to-peer distributed systems. the BFT-Metronome clock synchronization algorithm can also be applied to blockchain consensus protocols (such as Proof-of-Stake) that rely on weakly synchronized clocks. this is shown by integrating BFT-Metronome with the Lightweight Mining Algorithm to achieve consensus-round synchronization and timeouts. then, generalization to other protocols is argued qualitatively. It can also be applied to large distributed systems to secure against insider threats during clock synchronization. © 2024 IEEE.

关键词： Synchronization

来源：评论

学校读者我要写书评

暂无评论

An Edge computing Architecture for internet Measurement Network to Measure and Analyze Protocol Data

引用

SN Computer Science 2023年第6期4卷 822页

作者： Raje, Anand Agrawal, Anupam Santhosh, T. De, Indrajit Sinha, Sushanta Haq, Joherul Sachan, Subodh Nayak, Manjit AIORI India Internet Foundation (IIFON) 7/83 Shahid nagar West Bengal Kolkata 700078 India MeitY Government of India New Delhi India STPI Government of India New Delhi India STPI Government of India West Bengal Kolkata India Professor IEM and UEM West Bengal Kolkata India

this paper presents the high-level architecture, task execution methods, and scheduling algorithms behind community internet measurement network (IMN), named AIORI-IMN (Raje A, et al. the internet Measurement Network (AIORI-IMN). In: 2023 4th international conference on computing and Communication Systems (I3CS) 1–8, 2023). AIORI-IMN is researched and developed as part of the project “Advanced internet Operations Research in India” (AIORI) funded by MeitY, Govt. of India (internet Governance | Ministry of Electronics and Information technology, Government of India. URL https://***/content/internet-proliferation-governance). AIORI-IMN is designed to collect, analyze, collaborate and share protocol measurement metrics using distributed Remote Endpoints (RE). the underlying architecture supports the measurement platform to be plug-and-play, secured, scalable, interoperable and resilient. the core architecture is based on distributed edge computing paradigm. It has been designed to be layered with defined interfaces, helping each layer to be interoperable and flexible to adopt new changes with minimal or no impact on other layers. the distributed communication is handled using the Publish-Subscribe messaging pattern. the architecture, design and algorithms have been tested with a reference implementation. the implementation is live now having 100+ Remote Endpoints (RE). the portal https://*** facilitates stakeholders to execute, analyze and visualize measurement tasks in REs. the underlying distributed edge architecture is having three layers (Worker, Controller, UI Management & Analytics). All the layers are interoperable and communicate through APIs and messages. the task execution and scheduling algorithms keep track of optimal resource utilization. A novel approach to internet Measurement has been researched. It needs continuous evolution so that it remains relevant for future internet architecture. © 2023, the Author(s), under exclusive licence to

关键词： Computer networks distributed computing Edge computing Future internet architecture internet measurement

来源：评论

学校读者我要写书评

暂无评论

TSCH Meets BLE: Routed Mesh Communication Over BLE 19

TSCH Meets BLE: Routed Mesh Communication Over BLE

引用

19th Annual international conference on distributed computing in Smart Systems and the internet of things, DCOSS-IoT 2023

作者： Harms, Laura Landsiedel, Olaf Kiel University Germany Chalmers University of Technology Sweden

ISBN: (纸本)9798350346497

Bluetooth Low Energy (BLE) is the prevalent communication protocol for the internet of things. However, for time-critical applications requiring time-synchronized multi-hop networks with often multiple node exchanging data at the same time slot, BLE lacks a solution. Instead, we commonly see IEEE 802.15.4 being used with its Time-Slotted Channel Hopping (TSCH) MAC layer. In this work, we build TBLE, which brings the established TSCH protocol to BLE, enabling BLE to be used for time-synchronized routed mesh communication. We show that in experimental testbed deployments, TBLE achieves similar performance to TSCH, with the possibility for lower average latencies of up to 20%. Moreover, due to the higher spectral efficiency of BLE compared with IEEE 802.15.4 (40 vs. 16 channels), more parallel routed communications are possible with TBLE, further reducing latency and increasing throughput. © 2023 IEEE.

关键词： internet of things

来源：评论

学校读者我要写书评

暂无评论

FedVPS: Federated Learning for Privacy and Security of internet of Vehicles on Non-IID Data 12

FedVPS: Federated Learning for Privacy and Security of Inter...

引用

IEEE 12th Data Driven Control and Learning Systems conference (DDCLS)

作者： Kuang Hangdong Mi Bo Huang Darong Deng Zhaoyang Chongqing Jiaotong Univ Coll Informat Sci & Engn Chongqing 400074 Peoples R China Anhui Univ Sch Artificial Intelligence Hefei 230039 Anhui Peoples R China

ISBN: (纸本)9798350321050

the 6th generation of mobile networks (6G) offers many advantages, including fast transmission rates, low delays, and ultra-dense networks. these benefits can solve the communication problems in the internet of Vehicles (IoV). However, automobiles as IoV terminals generate Non-Independent Identically distributed (Non-IID) data while driving, making it necessary to introduce distributed machine learning into the IoV as a network that integrates intelligent computing and vehicle networking. To address the Non-IID of local data and the heterogeneity of local models, we propose a heterogeneous Federated Learning scheme in this paper. Based on the distributed architecture (Terminal - Edge device - Cloud) in the IoV, we designed a privacy protection scheme using Secure Multi-Party Computation (SMPC). this ensures that the terminals participating in Federated Learning get accurate calculation results without revealing useful information, thus preserving the privacy of local datasets. the privacy and security of the IoV based on Federated Learning (FedVPS) not only protect the privacy of the terminals but also improve communication efficiency, enabling accurate and efficient distributed machine learning. the aggregation method of Federated Learning is a prototype-based scheme that utilizes the effective information stored in local datasets. In the BIT-Vehicle dataset, FedVPS is not only more robust but also has excellent prediction accuracy. Compared to FedAvg, FedVPS has advantages in communication efficiency and model prediction accuracy.

关键词： internet of Vehicles Non-IID SMPC FedVPS

来源：评论

学校读者我要写书评

暂无评论

Harmonia: Accurate Federated Learning with All-Inclusive Dataset 17

Harmonia: Accurate Federated Learning with All-Inclusive Dat...

引用

IEEE 17th international conference on Cloud computing (IEEE CLOUD)

作者： Choi, Wonmi Ahn, Juyoung Yoo, Yeonho Yoo, Chuck Yang, Gyeongsik Korea Univ Dept Comp Sci & Engn Seoul South Korea

ISBN: (纸本)9798350368543;9798350368536

Federated learning (FL) is an appealing model training technique that utilizes heterogeneous datasets and user devices, ensuring user data privacy. Existing FL research proposed device selection schemes to balance the computing speeds of devices. However, we observe that these schemes compromise prediction accuracy by similar to 57.7%. To solve this problem, we present Harmonia that enhances prediction accuracy, while also balancing the diverse computing speeds of devices. Our evaluation shows that Harmonia improves prediction accuracy by similar to 1.7x over existing schemes.

关键词： Federated Learning Data Privacy distributed Machine Learning Collaborative Learning Client Selection

来源：评论

学校读者我要写书评

暂无评论

Evaluating Indicator Weights for Satellite internet Security Assessment: an Approach to Combining Rough Set with Fuzzy Hierarchical Analysis 21

Evaluating Indicator Weights for Satellite Internet Security...

引用

21st IEEE international Symposium on Parallel and distributed Processing with Applications, 13th IEEE international conference on Big Data and Cloud computing, 16th IEEE international conference on Social computing and Networking and 13th international conference on Sustainable computing and Communications, ISPA/BDCloud/SocialCom/SustainCom 2023

作者： Lu, Yuming Li, Fenghua Wen, Yitong Fang, Liang Guo, Shoukun Li, Zifu Institute of Information Engineering Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences School of Cyber Security Beijing China

ISBN: (纸本)9798350329223

In order to reduce the impact of increasingly sophisticated cyberattacks on the satellite internet security, it is necessary to assess the satellite internet security. Most of existing assessment schemes for network security risk mainly rely on expert knowledge to subjectively weight assessment indicator and quantify security risks, thus leading to results of assessment which are not objective. To address this problem, combining rough set with fuzzy hierarchy analysis, we propose a combination scheme to evaluate the indicator weights for assessing the satellite internet security. First, from the perspective of IPDR model, we propose IPDR-based evaluation indicator system, and fuzzy hierarchy analysis is designed to fuse the indicator scores of more than one experts into one final value and obtain the subjective weight. Second, rough set theory is adopted to reduce indicators and correct the subjective weight obtained in the first step, thus obtaining the comprehensive weight. Finally, a series of experiments are carried out to validate our scheme. © 2023 IEEE.

关键词： Rough set theory

来源：评论

学校读者我要写书评

暂无评论

Research on the Application of 3D Scanning Measurement in the Information Integration System of Building Construction in the internet Era 6

Research on the Application of 3D Scanning Measurement in th...

引用

6th international conference on Intelligent computing and Control Systems, ICICCS 2022

作者： Liu, Xiahong Shanghai Jiguang Polytechnic Colleget Shanghai China

ISBN: (纸本)9781665410359

Aiming at the problem of how to effectively improve the quality management of the prefabricated building in the construction phase, a dynamic management system for information integration in the prefabricated building construction phase based on 3D scanning measurement technology is proposed. 3D scanning measurement and BIM technology principle, combined with two application modes of data comparison and reverse modeling, analysis of its application in construction installation and quality monitoring, deformation monitoring of foundation pits, slopes, tunnels, dams, etc., BIM technology and 3D scanning integrated dynamic management It is feasible for the system to provide decision-making analysis for the information management of the prefabricated building construction stage. © 2022 IEEE.

关键词： Scanning

来源：评论

学校读者我要写书评

暂无评论

A decentralized algorithm for the resource allocation in the mobile edge system of the internet of Vehicles 6

A decentralized algorithm for the resource allocation in the...

引用

2023 IEEE 6th international conference on Information Systems and Computer Aided Education, ICISCAE 2023

作者： Sun, Jiayi Xu, Zhaoyang Wang, Rundong Zhang, Renwen China University of Geosciences Wuhan China

ISBN: (纸本)9798350313444

the internet of Vehicles (Iov) enables the sensing information collected by vehicles to be processed in a variety of ways, such as processed inside the vehicle or transmitted to roadside devices and cloud servers. that is a task computing and offloading problem in a mobile edge computing (MEC) system. this paper mainly studies the problem of competitive allocation of limited resources for multi-vehicle information processing and also studies the relationship between the total cost of the vehicles and some parameters such as the number of roadside devices. Based on real scenarios, we establish a multilevel vehicle internet sensor information service network composed of cloud servers, roadside devices, and in-vehicle devices. At the same time, we define a weighted cost model consisting of transmission delay and energy consumption. Combining the two models, the problem of competitive allocation of communication resources and computing resources is proposed, and the problem is transformed into a Multi-Individual Information Processing Game (MIIP-Game). through the theory of game potential, we prove that there exists at least one NASH balanced solution in the MIIP game, and design a Total Cost Minimum Solving (TCMS) algorithm to find the best allocation method. Finally, the simulation experiments compare the strategy of TCMS with other strategies to verify the validity of the TCMS algorithm, and also investigate several ways to reduce the total cost. © 2023 IEEE.

关键词： Competitive Allocation Game Model Mobile Edge computing System NASH balance Task Offloading

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：