检索结果-内蒙古大学图书馆

International Mining Software Repositories, MSR

作者： George Lake Minhaz F. Zibran Department of Computer Science Idaho State University Pocatello ID USA

ISBN: (数字)9798331501839

ISBN: (纸本)9798331501846

We present a cluster analysis of the Maven Central Repository’s dependency structure to identify and assess vulnerability risks using the Goblin framework. Through analysis of over 15 million artifacts using the Leiden community detection algorithm, we identified approximately 67 thousand distinct clusters with a high modularity score. Our risk assessment framework combines CVE metrics, freshness scores, and inter-cluster connectivity patterns to evaluate cluster risk levels and potential vulnerability propagation paths. The analysis reveals that while individual clusters typically show low to moderate risk scores, the repository’s highly connected structure creates critical paths for vulnerability propagation through hub clusters, some containing over 1.5 million nodes. We provide recommendations for dependency risk monitoring, including tracking of bridge nodes and prioritizing high-connectivity clusters. Our systematic approach provides a framework to identify systemic dependency risks across the repository through targeted inspections at critical points in the dependency network.

关键词： Bridges Target tracking Systematics Software algorithms Software Risk management Security detection algorithms Monitoring Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

Computer Vision Based Recognition Algorithm for Sea Buckthorn Harvesting Robot

Computer Vision Based Recognition Algorithm for Sea Buckthor...

引用

International Scientific Conference on Power and Electrical Engineering of Riga Technical University (RTUCON)

作者： Jurijs Timofejevs Mikhail Gorobetz Andrejs Potapovs Riga Technical University Riga Latvia

ISBN: (数字)9798350365771

ISBN: (纸本)9798350365788

Sea buckthorn harvesting presents challenges in labour requirements and costs, urging the need for technological advancements. This paper discusses the applicability of adaptive systems, computer vision, and robotics in agricultural tasks, focusing on the development of an autonomous computer vision-based sea buckthorn harvesting robot. The paper outlines the overall architecture of the robot and presents results demonstrating its detecting ability. Additionally, a branch direction detection algorithm is described. The research shows satisfactory precision levels for detection on known samples, although precision for new samples requires improvement in future research steps. The outlined conclusions highlight the achieved milestones in the development of the sea buckthorn harvesting robot and emphasize areas for further refinement and enhancement.

关键词： Training Electrical engineering Computer vision Image recognition Costs Adaptive systems Computational modeling Focusing Computer architecture detection algorithms

来源：评论

学校读者我要写书评

暂无评论

Graph-based low complexity detection algorithms in multiple-input-multiple-out systems: an edge selection approach

引用

IET COMMUNICATIONS 2013年第12期7卷 1202-1210页

作者： Lv, Tiejun Long, Feichi Beijing Univ Posts & Telecommun Sch Informat & Commun Engn Beijing 100876 Peoples R China

In this study, the problem of low complexity multiple-input-multiple-out signal detection based on belief propagation (BP) is addressed. The authors propose an edge selection approach that works on factor graph model to cut down the number of circles and high complexity of standard BP algorithm. The message passing from factor nodes to variable nodes is updated by only partial edges, and the mean feedback method is designed to compensate the information loss brought by the edge selection. Both binary and high-order modulations are considered, and the scheme of mapping between bit soft output and modulation symbols when computing the feedback information is discussed. In addition, a minimum mean-square error filter initialised algorithm is proposed, in which the initial message of BP detection is exploited. Both binary and high-order modulations are discussed as well when the authors design this initial message. Simulation results along with convergence and complexity analyses verify that the proposed edge selection approach can achieve good performance with low complexity, and significantly outperform the existing methods with comparative complexity. Moreover, our approach has asymptotic optimality and is a self-adapting scheme, which can achieve the trade-off between performance and complexity by varying the number of selected edges.

关键词： Circles information loss Complexity Edge of a figure or solid signal acquisition High order modulation feedback information detection algorithms

来源：评论

学校读者我要写书评

暂无评论

Efficient Compressed Sensing for Real-Time Electrocardiogram Acquisition on Low-Power Medical Devices

Efficient Compressed Sensing for Real-Time Electrocardiogram...

引用

IEEE EMBS International Conference on Information Technology Applications in Biomedicine (ITAB)

作者： Mitchell Terrell Jon Weissman Dept. of Computer Science and Engineering University of Minnesota Minneapolis Minnesota

ISBN: (数字)9798350351552

ISBN: (纸本)9798350351569

Low cost wearable and implantable cardiac monitoring devices (WCM & ICM), combined with increasingly accurate disease and arrhythmia detection algorithms have proven effective to help slow the impact of cardiovascular disease, the worlds leading cause of death in 2022 [1]. Improvements to server-side detection algorithms along with hardware limitations of these devices such as slow processor speeds and minimal battery life has led to a desire to offload data from the devices for later analysis. Paired with limited storage capacity, this has led to a push to decrease the necessary storage for electrocardiogram (EKG) signals without sacrificing disease detection accuracy and device longevity. A promising recent innovation in EKG compression has come from Compressed Sensing (CS), which exposes inherent sparseness in the signal to selectively sample for eventual server-side reconstruction. Many CS approaches have been implemented on WCM devices which demonstrate a high compression ratio (CR) and accurate signal reconstruction, but quickly become impractical for the stricter hardware constraints of ICM devices due to the increased computation on the device and slow reconstruction time. In this paper we propose a CS approach known as Tailored Sensing (TS) which combines on-device prior knowledge, a custom transform basis, and optimal sense location selection to achieve improved CR and reconstruction accuracy while eliminating on-device computational burden and slow reconstruction time. Our approach offers equivalent or better signal reconstruction at previously unfathomable CRs due to our novel signal segmentation scheme. Additionally, our approach boasts a zero overhead on-device sensing strategy and a 93 % reduction in signal reconstruction time.

关键词： Technological innovation Accuracy Medical devices Transforms Electrocardiography Signal reconstruction Hardware Sensors detection algorithms Compressed sensing

来源：评论

学校读者我要写书评

暂无评论

Identification of Unknown Malicious Flow Based on Adaptive Annotation and Deep Neural Networks

Identification of Unknown Malicious Flow Based on Adaptive A...

引用

International Conference on Big Data and Information Analytics (BigDIA)

作者： Zhaoyun Ding Yi Wang Wangqun Lin National Key Laboratory of Information Systems Engineering National University of Defense Technology Changsha Academy of Military Sciences Beijing

ISBN: (数字)9798350354621

ISBN: (纸本)9798350354638

With the explosive growth of Internet flow, the problems of network security are becoming more and more prominent. The identification and detection of malicious flow in the network have become important topics. Most of the existing classification models are based on closed-world data sets, and can only classify the sampled flow data. In this case, unknown flow, especially the hidden malicious flow, cannot be effectively identified. In order to solve this problem, this paper proposes a recognition framework based on deep neural network to identify unknown flow and detect malicious flow, which can automatically expand the known data set to enhance the classification and detection ability of the model. Firstly, the framework constructs a classification model that can effectively identify the network flow based on the convolutional neural network. Based on this model, the unknown flow data with potential security risks are distinguished and clustered. Then, the unknown flow is maliciously detected according to the clustering results, and the model is updated with the newly discovered flow data.

关键词： Adaptation models Annotations Impurities Manuals Network security Data models Real-time systems Explosives Internet detection algorithms

来源：评论

学校读者我要写书评

暂无评论

Malicious Request Identification Based on a Hybrid Model of BP Neural Network

Malicious Request Identification Based on a Hybrid Model of ...

引用

Electronic Information Engineering and Computer Technology (EIECT), International Conference on

作者： Zhiqiang Zhang Jiaji Zhang Jiaqi Guo Siying Chen Jingxi Wang Yongzheng Li Department of Network Security Shanxi Police College Taiyuan Shanxi China Science and Technology Communication Detachment Taiyuan Public Security Bureau Taiyuan Shanxi China

ISBN: (数字)9798331528850

ISBN: (纸本)9798331528867

Malicious request identification is a key issue in the field of cybersecurity. Existing methods for identifying malicious requests often face limitations when dealing with unknown malicious requests. To address the problem of current malicious request identification methods being ineffective in recognizing unknown malicious requests, this paper employs N-gram for data preprocessing, uses TD-IDF and logistic regression for feature selection, and extracts key features related to malicious requests to enhance the input information of the model. A hybrid model based on BP neural networks is trained to improve the accuracy of malicious request analysis. Experimental results validate the effectiveness and practicality of this model in identifying unknown malicious requests. This research provides new ideas and methods for the identification of malicious requests, holding significant practical importance for cybersecurity protection.

关键词： Deep learning Logistic regression Accuracy Face recognition Neural networks Feature extraction Data models Computer security Protection detection algorithms

来源：评论

学校读者我要写书评

暂无评论

A Review of Automatic Speaker Verification Systems with Feature Extractions and Spoofing Attacks

A Review of Automatic Speaker Verification Systems with Feat...

引用

Electronics and Sustainable Communication Systems (ICESC), 2020 International Conference on

作者： Krithikaa Venket VS Safia Naveed Dept. of Information Technology KCG College of Technology Chennai India

ISBN: (数字)9798350379945

ISBN: (纸本)9798350379952

Automatic Speaker Verification (ASV) technology is gaining traction in various applications due to its reliance on a unique and natural biometric identifier: a person's voice. This review provides a comprehensive analysis of ASV systems, exploring their core functionalities, underlying principles, and potential benefits. It examines the enrollment and verification processes, where speaker voiceprints are created and compared for user authentication. The review then delves into feature extraction techniques, crucial for differentiating genuine and spoofed voices. Common spoofing attacks like replay attacks and voice mimicry are discussed, along with feature analysis methods for spoof detection. Achieving high accuracy, precision, reliability and security in Automatic Speaker Verification (ASV) systems, particularly in the presence of spoofing attacks, involves a combination of robust feature extraction techniques, advanced machine learning models, and effective anti-spoofing strategies ASVSpoof dataset is used for this research. The study concludes by highlighting ongoing challenges and future directions in ASV research, emphasizing the importance of security, fairness, and continuous advancements in this evolving field.

关键词： Biometrics Deep learning Reviews Communication systems Authentication Feature extraction User experience Robustness detection algorithms Spectrogram

来源：评论

学校读者我要写书评

暂无评论

Automating Security in Blockchain: ML-Driven Smart Contract Vulnerability Analysis

Automating Security in Blockchain: ML-Driven Smart Contract ...

引用

Disruptive Technologies (ICDT), International Conference on

作者： Sumithra V Shahsidhara R Akansha Singh School of Computer Science Engineering and Technology Bennett University Greater Noida India OnDevice AI Samsung Research Institute Bangalore Maratahalli Bangalore India

ISBN: (数字)9798331519582

ISBN: (纸本)9798331519599

As with the increasing usage of blockchain especially in decentralized systems, the need for solid security measures increases to stop vulnerabilities in smart contracts. Our method is an ML-based solution to automate the detection of smart contract vulnerabilities and improves the blockchain security. In this paper, we propose a comprehensive vulnerability detection algorithm that employs a hybrid detection mechanism that analyzes transaction patterns and uses ML models to detect suspicious activities on the fly. The algorithm detects as well as flags smart contract vulnerabilities and malicious transactions by analyzing transaction amounts, user behavior, and frequency. The developed framework not only lessens manual effort but also automates validation so as to improve mitigation process in case of unforeseen risks. This essentially shows the capability of using ML-driven analysis to secure the blockchain environment as an adaptable approach for the detection of smart contract vulnerabilities.

关键词： Analytical models Prevention and mitigation Smart contracts Manuals Machine learning Solids Blockchains Security Disruptive technologies detection algorithms

来源：评论

学校读者我要写书评

暂无评论

Image Transformation-Based Defense Against Adversarial Perturbation on Deep Learning Models

引用

IEEE TRANSACTIONS ON DEPENDABLE AND SECURE COMPUTING 2021年第5期18卷 2106-2121页

作者： Agarwal, Akshay Singh, Richa Vatsa, Mayank Ratha, Nalini K. IIIT Delhi Dept Comp Sci & Engn Delhi 110020 India IIT Jodhpur Dept Comp Sci & Engn Karwar 342037 Rajasthan India SUNY Buffalo Buffalo NY 14260 USA

Deep learning algorithms provide state-of-the-art results on a multitude of applications. However, it is also well established that they are highly vulnerable to adversarial perturbations. It is often believed that the solution to this vulnerability of deep learning systems must come from deep networks only. Contrary to this common understanding, in this article, we propose a non-deep learning approach that searches over a set of well-known image transforms such as Discrete Wavelet Transform and Discrete Sine Transform, and classifying the features with a support vector machine-based classifier. Existing deep networks-based defense have been proven ineffective against sophisticated adversaries, whereas image transformation-based solution makes a strong defense because of the non-differential nature, multiscale, and orientation filtering. The proposed approach, which combines the outputs of two transforms, efficiently generalizes across databases as well as different unseen attacks and combinations of both (i.e., cross-database and unseen noise generation CNN model). The proposed algorithm is evaluated on large scale databases, including object database (validation set of ImageNet) and face recognition (MBGC) database. The proposed detection algorithm yields at-least 84.2% and 80.1% detection accuracy under seen and unseen database test settings, respectively. Besides, we also show how the impact of the adversarial perturbation can be neutralized using a wavelet decomposition-based filtering method of denoising. The mitigation results with different perturbation methods on several image databases demonstrate the effectiveness of the proposed method.

关键词： Perturbation methods Databases Machine learning Transforms detection algorithms Integrated circuits Machine learning algorithms Adversarial attack detection mitigation image transformations deep learning

来源：评论

学校读者我要写书评

暂无评论

Eigenvalues-Based Universal Spectrum Sensing Algorithm in Cognitive Radio Networks

引用

IEEE SYSTEMS JOURNAL 2021年第3期15卷 3391-3402页

作者： Zhao, Wenjing Li, He Jin, Minglu Liu, Yang Yoo, Sang-Jo Dalian Univ Technol Sch Informat & Commun Engn Dalian 116024 Peoples R China Inner Mongolia Univ Coll Elect Informat Engn Hohhot 010021 Peoples R China INHA Univ Dept Informat & Commun Engn Incheon 402751 South Korea

The eigenvalues of the sample covariance matrix can capture signal correlations and noise characteristics well, which are widely used for spectrum sensing in cognitive radio networks. Some totally blind spectrum sensing algorithms were proposed, such as maximum eigenvalue-to-arithmetic mean (ME-AM), maximum eigenvalue-to-geometric mean (ME-GM), and arithmetic-to-geometric mean of eigenvalues (AGM) methods. This article makes full use of the advantages of these algorithms and proposes a universal spectrum sensing algorithm based on maximum eigenvalue, arithmetic mean, and geometric mean of eigenvalues. The proposed algorithm takes the weighted geometric mean of the test statistics of the ME-AM and AGM algorithms as new test statistic and includes the ME-AM, ME-GM, and AGM algorithms as special cases. Following the random matrix theory framework, in a similar vein to the ME-AM and ME-GM algorithms, we derive the analytical expressions of false alarm probability, threshold, and detection probability of the proposed method using the Tracy-Widom distribution of maximum eigenvalue. In addition, we discuss the problem of designing the optimal weighting factor through theoretical analysis and simulation experiments. Finally, simulation results verify that the universal algorithm can effectively improve the detection performance.

关键词： Eigenvalues and eigenfunctions Sensors detection algorithms Covariance matrices Cognitive radio Signal to noise ratio Fading channels Cognitive radio (CR) eigenvalues multiantenna systems spectrum sensing

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：