检索结果-内蒙古大学图书馆

International Conference on Power Energy, Environment and Intelligent Control (PEEIC)

作者： Vineet Kumar Adlin Jebakumari S Mansingh Meena Department of Computer Science and Engineering (Cyber Security) Noida Institute of Engineering & Technology Greater Noida Uttar Pradesh India Computer Science Engineering Department Jain (Deemed to be University) Bangalore India Department of Electrical Engineering Vivekananda Global University Jaipur India

The integration of power electronic converters into electrical grids is essential for the interconnection of microgrids, electric cars, energy storage systems, renewable energy sources, and high-voltage DC cables for transmission. The increasing use of these inverters in modern grids has increased interest in tracking and managing their functioning to improve grid support from a practical and research standpoint. Current industry standards currently require grid-tied converters to have a defined set of control parameters, which may be changed remotely over a communication network. Although the ability to manage them remotely adds new features, it also leaves these converters vulnerable to possible cyberattacks. The purpose of this essay is to shed light on the vulnerabilities of power convert control systems to cyberattacks. It offers a summary of common cyberattacks while taking into account the various uses for grid-tied converters. The paper also looks at how different cyberattacks affect these converters' grid support capabilities. Finally, a summary and suggestions for more study are provided.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Position-Aware Transformer for Image Captioning

引用

computers, Materials & Continua 2022年第1期70卷 2065-2081页

作者： Zelin Deng Bo Zhou Pei He Jianfeng Huang Osama Alfarraj Amr Tolba School of Computer and Communication Engineering Changsha University of Science and TechnologyChangsha410114China School of Computer Science and Cyber Engineering Guangzhou UniversityGuangzhou510006China Advanced Forming Research Centre University of StrathclydeRenfrewshirePA49LJGlasgowUnited Kingdom Department of Computer Science Community CollegeKing Saud UniversityRiyadh11437Saudi Arabia Department of Mathematics and Computer Science Faculty of ScienceMenoufia UniversityEgypt

Image captioning aims to generate a corresponding description of an *** recent years,neural encoder-decodermodels have been the dominant approaches,in which the Convolutional Neural Network(CNN)and Long Short TermMemory(LSTM)are used to translate an image into a natural language *** these approaches,the visual attention mechanisms are widely used to enable deeper image understanding through fine-grained analysis and even multiple steps of ***,most conventional visual attention mechanisms are based on high-level image features,ignoring the effects of other image features,and giving insufficient consideration to the relative positions between image *** this work,we propose a Position-Aware Transformer model with image-feature attention and position-aware attention mechanisms for the above *** image-feature attention firstly extracts multi-level features by using Feature Pyramid Network(FPN),then utilizes the scaled-dot-product to fuse these features,which enables our model to detect objects of different scales in the image more effectivelywithout increasing *** the position-aware attentionmechanism,the relative positions between image features are obtained at first,afterwards the relative positions are incorporated into the original image features to generate captions more *** are carried out on the MSCOCO dataset and our approach achieves competitive BLEU-4,METEOR,ROUGE-L,CIDEr scores compared with some state-of-the-art approaches,demonstrating the effectiveness of our approach.

关键词： Deep learning image captioning transformer attention position-aware

来源：评论

学校读者我要写书评

暂无评论

A Stealthy Wrongdoer: Feature-Oriented Reconstruction Attack Against Split Learning

A Stealthy Wrongdoer: Feature-Oriented Reconstruction Attack...

引用

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Xiaoyang Xu Mengda Yang Wenzhe Yi Ziang Li Juan Wang Hongxin Hu Yong Zhuang Yaxin Liu Key Laboratory of Aerospace Information Security and Trusted Computing Ministry of Education School of Cyber Science and Engineering Wuhan University Department of Computer Science and Engineering University at Buffalo SUNY

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

Split Learning (SL) is a distributed learning framework renowned for its privacy-preserving features and minimal computational requirements. Previous research consistently highlights the potential privacy breaches in SL systems by server adversaries reconstructing training data. However, these studies often rely on strong assumptions or compromise system utility to enhance attack performance. This paper introduces a new semi-honest Data Reconstruction Attack on SL, named Feature-Oriented Reconstruction Attack (FORA). In contrast to prior works, FORA relies on limited prior knowledge, specifically that the server utilizes auxiliary samples from the public without knowing any client's private information. This allows FORA to conduct the attack stealthily and achieve robust performance. The key vulnerability exploited by FORA is the revelation of the model representation preference in the smashed data output by victim client. FORA constructs a substitute client through feature-level transfer learning, aiming to closely mimic the victim client's representation preference. Leveraging this substitute client, the server trains the attack model to effectively reconstruct private data. Extensive experiments showcase FORA's superior performance compared to state-of-the-art methods. Furthermore, the paper systematically evaluates the proposed method's applicability across diverse settings and advanced defense strategies.

关键词： computer vision computer aided instruction Distance learning Transfer learning Training data Privacy breach Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Distributed Secure Storage Scheme Based on Sharding Blockchain

引用

computers, Materials & Continua 2022年第3期70卷 4485-4502页

作者： Jin Wang Chenchen Han Xiaofeng Yu Yongjun Ren R.Simon Sherratt School of Computer Science and Mathematics Fujian University of TechnologyFuzhou350118China School of Computer&Communication Engineering Changsha University of Science&TechnologyChangsha410004China School of Business Nanjing UniversityNanjing210093China School of Computer School of SoftwareSchool of Cyberspace SecurityEngineering Research Center of Digital ForensicsMinistry of EducationNanjing University of Information Science&TechnologyNanjing210044China Department of Biomedical Engineering University of ReadingRG66AYUK

Distributed storage can store data in multiple devices or servers to improve data ***,in today’s explosive growth of network data,traditional distributed storage scheme is faced with some severe challenges such as insufficient performance,data tampering,and data lose.A distributed storage scheme based on blockchain has been proposed to improve security and efficiency of traditional distributed *** this scheme,the following improvements have been made in this *** paper first analyzes the problems faced by distributed *** proposed to build a new distributed storage blockchain scheme with sharding *** proposed scheme realizes the partitioning of the network and nodes by means of blockchain sharding technology,which can improve the efficiency of data verification between *** addition,this paper uses polynomial commitment to construct a new verifiable secret share scheme called *** new scheme is one of the foundations for building our improved distributed storage blockchain *** with the previous scheme,our new scheme does not require a trusted third party and has some new features such as homomorphic and batch *** security of VSS can be further *** comparisons show that the proposed scheme significantly reduces storage and communication costs.

关键词： Blockchain distributed storage verifiable secret share polynomial commitment

来源：评论

学校读者我要写书评

暂无评论

An Enhanced Authentication Protocol for IoT-AmI Environment

An Enhanced Authentication Protocol for IoT-AmI Environment

引用

International Wireless Communications and Mobile Computing Conference, IWCMC

作者： Shree Chand Khichar Awaneesh Kumar Yadav Manoj Misra Brij B. Gupta Dept. of Computer Science and Engineering Indian Institute of Technology Roorkee Uttarakhand India International Center for AI and Cyber Security Research and Innovations Asia University Taichung

ISBN: (数字)9798350361261

ISBN: (纸本)9798350361278

The rapid proliferation of the Internet of Things (IoT) in recent years has fostered the swift development of various applications, enabling seamless connections between consumers and everyday utilities. One sector that has seen significant transformation is healthcare, thanks to the adoption of IoT and Ambient Intelligence (AmI). However, this growing utilization of IoT-AmI systems has raised substantial concerns about privacy and security, particularly in user authentication. Numerous authentication techniques have been established for IoT-AmI systems. Nevertheless, the current state-of-the-art reveals that these methods are vulnerable to various severe attacks, such as impersonation, Man-in-the-middle (MITM), traceability, replay, privacy and violation of perfect forward secrecy. Considering the above, this paper aims to propose a secure authentication protocol for IoT-AmI systems. The security of the proposed protocol for IoT-AmI is verified using the formal analysis tool Scyther. Furthermore, the performance of the designed protocol is assessed to show that it has lower computational and communication costs compared to existing protocols.

关键词： Wireless communication Privacy Protocols Costs Authentication Medical services Ambient intelligence

来源：评论

学校读者我要写书评

暂无评论

Evaluating The Mixing Performance in A Planar Passive Micromixer With T-shape and SAR Mixing Chambers: Comparative Study 2

Evaluating The Mixing Performance in A Planar Passive Microm...

引用

2nd International engineering Conference on Electrical, Energy, and Artificial Intelligence, EICEEAI 2023

作者： Ababneh, Jafar Deif, Mohanad A. Solyman, Ahmad Zekry, Rahma S. Hafez, Mohamed Sharfo, Samer M. Cyber Security Zarqa University The Faculty of Information Technology Zarqa Jordan College of Engineering University of Business and Technology Jeddah Saudi Arabia Department of Artificial Intelligence 12566 Egypt School of Computing Engineering and Built Environment Glasgow Caledonian University Glasgow United Kingdom University Department of Bioelectronics Cairo Egypt INTI-IU-University Faculty of Engineering Feqs Nilai Malaysia

ISBN: (纸本)9798350373363

In Microfluidic devices have gained significant interest in various fields, including biomedical diagnostics, environmental preservation, animal epidemic avoidance, and food safety regulation. Micromixing phenomena are crucial for these devices' functionality, as they accurately and efficiently manipulate fluids within microchannels. The process aims to blend samples accurately and swiftly within these scaled-down devices, governed by the promotion of dispersion among distinct fluid species or particles. Advancements in passive and active micromixers have led to innovative designs incorporating diverse processes to enhance mixing efficiency. Examples include two-dimensional impediments, controlled imbalanced collisions, and complex configurations like spiral and convergence-divergence structures. Active micromixers use external cues to initiate and regulate mixing processes, including thermal, magnetic, sound, pressure, and electrical fields. The trajectory of micromixing technologies is significantly influenced by current developments in microfluidics. One notable advancement is the incorporation of micromixers into 3D printing methodologies, facilitating the development of adaptable microfluidic systems. Additionally, the incorporation of microfluidic principles into paper-based channels creates opportunities for the development of cost-effective and portable diagnostic devices. The process of micro-mixing is critical in boosting the functionalities of these devices. © 2023 IEEE.

关键词： Microfluidics

来源：评论

学校读者我要写书评

暂无评论

Side-Channel-Driven Intrusion Detection System for Mission Critical Unmanned Aerial Vehicles

Side-Channel-Driven Intrusion Detection System for Mission C...

引用

IEEE International Symposium on Quality Electronic Design

作者： Alejandro Almeida Muneeba Asif Md Tauhidur Rahman Mohammad Ashiqur Rahman Department of Electrical and Computer Engineering Analytics for Cyber Defense (ACyD) Lab Florida International University USA Department of Electrical and Computer Engineering Security Reliability Low-power and Privacy (SeRLoP) Lab Florida International University USA

ISBN: (数字)9798350309270

ISBN: (纸本)9798350309287

Hardware Trojans (HTs) are gradually becoming a growing threat in the IoT landscape. This type of attack can result in catastrophic incidents for unmanned aerial vehicles (UAVs). Examples of these incidents could be information leakage, drone malfunction, which leads to crashes, and data integrity issues in information gathered by the sensors. Other papers have tried to resolve this issue by focusing on enhancing encryption and hardening the physical properties of the device to restrict information leakage. However, this research aims to demonstrate the efficacy of a side channel-based intrusion detection technique. This technique uses machine learning to detect HTs. We test this by constructing a PWM-inverting HT and implementing it into a UAV with a Pixhawk flight controller. By doing so, we demonstrate how this Intrusion Detection System (IDS) technique effectively detects incidents related to HT implementation on UAVs, analyzing discrepancies in the system’s impedance. Our proposed IDS yields ROC and accuracy scores up to 99.5% and 98%, respectively, in detecting HTs.

关键词： Resistance Mission critical systems Intrusion detection Machine learning Autonomous aerial vehicles Information leakage Sensors

来源：评论

学校读者我要写书评

暂无评论

Design and Implementation of a 5G security Testbed Based on Zero Trust Architecture 15

Design and Implementation of a 5G Security Testbed Based on ...

引用

15th International Conference on Information and Communication technology Convergence, ICTC 2024

作者： Yoon, Mahnsuk Seo, Jihun Lee, Jonghoon Cho, Keuchul Gumi Korea Republic of Center for Connected & Automated Driving Research Korea Transport Institute Department of The Fourth Industrial Revolution & Transport Sejong Korea Republic of Cyber Security Research Division Daejeon Korea Republic of School of Computer Secience and Engineering Software Education Center Kyungpook National University Daegu Korea Republic of

ISBN: (纸本)9798350364637

This paper presents the design and implementation of a 5G security testbed based on Zero Trust Architecture (ZTA). As 5G networks offer ultra-high speeds, low latency, and massive connectivity, ensuring their security has become a critical challenge, especially with the distributed nature and numerous connected devices. Traditional perimeter-based security models are no longer sufficient. Therefore, Zero Trust Architecture, which continuously verifies and monitors all resources and users regardless of their location, has been proposed as a solution. In this study, we propose a comprehensive security management system by integrating ZTA into a 5G testbed, focusing on real-time monitoring and dynamic policy enforcement using data collected from the Access and Mobility Management Function (AMF) and User Plane Function (UPF). The testbed's effectiveness is demonstrated through the deployment of Nokia's network equipment, allowing the collection and analysis of high-resolution traffic data, which aids in early threat detection and response. The proposed system enhances 5G network security and offers significant potential for application across various industries. © 2024 IEEE.

关键词： 5G mobile communication systems

来源：评论

学校读者我要写书评

暂无评论

A Novel Approach for Anomaly Detection using Snort Integrated with Machine Learning

A Novel Approach for Anomaly Detection using Snort Integrate...

引用

International Conference on Computing for Sustainable Global Development (INDIACom)

作者： T. Preethi Ponnuru Rakshitha Reddy Lekkala Likhitha Pendyala Pavan Kumar Abhinav Kamani Department of CSE – Cyber Security Data Science and Artificial Intelligence & Data Science VNR Vignana Jyothi Institute of Engineering and Technology Hyderabad India

In today’s digital world, it is crucial to keep a company’s information safe from cyber threats. With new and more sophisticated network attacks emerging all the time, better security measures and ways to monitor our networks are needed. Intrusion Detection Systems (IDS) can act as digital guards to help protect our networks from these malicious threats. Snort is a widely used open-source IDS, but it can struggle with the ever-changing nature of these threats. Our research focuses on enhancing Snort’s capabilities by integrating it with ML algorithms such as Random Forest, Decision Tree, Support Vector Machine (SVM), K-Nearest Neighbours (KNN), and Naive Bayes. We also conducted subset testing using the NSL-KDD dataset. Our results indicate that combining these ML algorithms with Snort can improve our ability to detect and stop malicious network activities. This research can be helpful for anyone interested in developing smarter and more effective intrusion detection systems.

关键词：

来源：评论

学校读者我要写书评

暂无评论

CAViaR Secretary Bird Optimization Algorithm Enabled Transfer Learning for Melanoma Classification

CAViaR Secretary Bird Optimization Algorithm Enabled Transfe...

引用

8th IEEE-EMBS Conference on Biomedical engineering and Sciences, IECBES 2024

作者： Vijaya, P. Kumar, Basant Mani, Joseph Chander, Satish Fernandes, Roshan Jassim, Hothefa Singvi, Dilip Kumar Modern College of Business and Science Department of Mathematics and Computer Science Bowshar Oman Birla Institute of Technology Mesra Department of Computer Science and Engineering Ranchi India NMAMIT Department of Cyber Security Karnataka Karkala India Burjeel Hospital Department of Internal Medicine Oman

ISBN: (纸本)9798350383409

Melanoma is one amongst aggressive diseases with some ordinary treatment choices. The fatality rates and their occurrence vary expansively around the world relying upon access to earlier identification and basic medical care. The significant demerits of the existing classification models are a lack of predictive significance and a small relationship with treatment results. Here, CAViaR Secretary Bird Optimization Algorithm enabled Transfer Learning (CSBOA-TL) is introduced for melanoma classification. Firstly, an Adaptive Kalman Filter (AKF) is utilized to pre-process input skin images. After pre-processing, skin lesion segmentation is conducted employing Deep Fuzzy Clustering (DFC). Thereafter, statistical features, Oriented FAST Rotated and BRIEF (ORB) and Haralick features are extracted. Lastly, melanoma classification is conducted by Convolutional Neural Network (CNN) based TL, where CNN is utilized with fetched hyperparameters from EfficientNet. The CNN-based TL is trained utilizing the CAViaR Secretary Bird Optimization Algorithm (CSBOA), which is presented by incorporating Conditional Autoregressive Value at Risk (CAViaR) with Secretary Bird Optimization Algorithm (SBOA). Additionally, CSBOA-TL achieved a maximal accuracy of 91.852%, a True Negative Rate (TNR) of 92.788% and a True Positive Rate (TPR) of 90.715%. © 2024 IEEE.

关键词： Oncology

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：