检索结果-内蒙古大学图书馆

IEEE Conference on Communications and Network Security (CNS)

作者： Andrea Corsini Shanchieh Jay Yang Department of Science and Methods for Engineering University of Modena and Reggio Emilia Modena Italy Department of Computer Engineering Rochester Institute of Technology Rochester USA

Machine learning (ML) has become increasingly popular in network intrusion detection. However, ML-based solutions always respond regardless of whether the input data reflects known patterns, a common issue across safety-critical applications. While several proposals exist for detecting Out-Of-Distribution (OOD) in other fields, it remains unclear whether these approaches can effectively identify new forms of intrusions for network security. New attacks, not necessarily affecting overall distributions, are not guaranteed to be clearly OOD as instead, images depicting new classes are in computer vision. In this work, we investigate whether existing OOD detectors from other fields allow the identification of unknown malicious traffic. We also explore whether more discriminative and semantically richer embedding spaces within models, such as those created with contrastive learning and multi-class tasks, benefit detection. Our investigation covers a set of six OOD techniques that employ different detection strategies. These techniques are applied to models trained in various ways and subsequently exposed to unknown malicious traffic from the same and different datasets (network environments). Our findings suggest that existing detectors can identify a consistent portion of new malicious traffic, and that improved embedding spaces enhance detection. We also demonstrate that simple combinations of certain detectors can identify almost 100% of malicious traffic in our tested scenarios.

关键词：

来源：评论

学校读者我要写书评

暂无评论

It's a Match - Enhancing the Fit between Users and Phishing Training through Personalisation 25

It's a Match - Enhancing the Fit between Users and Phishing ...

引用

2025 CHI Conference on Human Factors in Computing Systems, CHI 2025

作者： Schöni, Lorin Roch, Neele Sievers, Hannah Strohmeier, Martin Mayer, Peter Zimmermann, Verena Security Privacy & Society Eth Zurich Zurich Switzerland Armasuisse Thun Switzerland Department of Mathematics and Computer Science University of Southern Denmark Odense Denmark Institute of Applied Informatics and Formal Description Methods Karlsruhe Institute of Technology Karlsruhe Germany Department of Humanities Social and Political Sciences Eth Zürich Zürich Switzerland

ISBN: (纸本)9798400713941

Effective training is essential for enhancing users' ability to detect phishing attempts. Personalised training offers huge potential to more closely align training content with individuals' needs and skill levels. In an online study, we assigned N=342 participants to personalised training or a random training variant to compare their effectiveness. The personalisation was based on a phishing proficiency score calculated from factors such as detection ability, knowledge, and security attitude. After training, the participants demonstrated greater proficiency, with an increased ability to detect phishing emails and higher security attitudes. These effects were most pronounced in the personalised condition, demonstrating the potential of personalisation to improve training outcomes. Overall, personalised training levelled the playing field, efficiently bringing all groups, regardless of their initial proficiency, to a comparable and desired post-training phishing proficiency level. Finally, we derived recommendations for designing personalised phishing training content and assigning users to suitable training programmes. © 2025 Copyright held by the owner/author(s).

关键词： Driver training

来源：评论

学校读者我要写书评

暂无评论

Verification of Genuineness of Educational Internet Resources Using Machine Learning methods

Verification of Genuineness of Educational Internet Resource...

引用

Technology Enhanced Learning in Higher Education (TELE), International Conference on

作者： Aleksandr N. Privalov Vadim A. Smirnov Institute of Advanced Information Technologies Tula State Lev Tolstoy Pedagogical University Tula Russia Department of mathematics computer science and teaching methods Ivanovo State University Shuya Russia

ISBN: (数字)9798350353532

ISBN: (纸本)9798350353549

The analysis of various sources has been carried out, confirming the demand for protective solutions against information threats from fake websites of organizations. The relevance of the research topic is confirmed by the presence of addresses similar in spelling to popular educational Internet resources in the list of domain names of the RU zone registered over the past year. When developing security solutions, it is proposed to use a site verifying the genuineness method based on the use of machine learning algorithms. A review of research by various authors has been conducted in order to determine the most frequently used features for verifying the genuineness of Internet resources in the machine learning models. The authors propose their own verifying the genuineness features that can be used in a situation where data about an Internet resource is extracted from the domain name registry. The proposed features differ from the known ones in that they contain signs of micro-markup on the site and storage of site settings files for search engines on servers. The developed features were tested using a naive Bayesian classifier as a machine learning algorithm. The proposed features can be used in the implementation of a software tool to counteraction threats from fake educational sites.

关键词： Machine learning algorithms Reviews Machine learning Organizations Search engines Feature extraction Internet

来源：评论

学校读者我要写书评

暂无评论

Learning Superconductivity from Ordered and Disordered Material Structures 38

Learning Superconductivity from Ordered and Disordered Mater...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Chen, Pin Peng, Luoxuan Jiao, Rui Mo, Qing Wang, Zhen Huang, Wenbing Liu, Yang Lu, Yutong National Supercomputer Center in Guangzhou School of Computer Science and Engineering Sun Yat-sen University China Dept. of Comp. Sci. & Tech. Institute for AI BNRist Center Tsinghua University China Institute for AIR Tsinghua University China Gaoling School of Artificial Intelligence Renmin University of China China Beijing Key Laboratory of Big Data Management and Analysis Methods Beijing China

Superconductivity is a fascinating phenomenon observed in certain materials under certain conditions. However, some critical aspects of it, such as the relationship between superconductivity and materials' chemical/structural features, still need to be understood. Recent successes of data-driven approaches in material science strongly inspire researchers to study this relationship with them, but a corresponding dataset is still lacking. Hence, we present a new dataset for data-driven approaches, namely SuperCon3D, containing both 3D crystal structures and experimental superconducting transition temperature (Tc) for the first time. Based on SuperCon3D, we propose two deep learning methods for designing high Tc superconductors. The first is SODNet, a novel equivariant graph attention model for screening known structures, which differs from existing models in incorporating both ordered and disordered geometric content. The second is a diffusion generative model DiffCSP-SC for creating new structures, which enables high Tc-targeted generation. Extensive experiments demonstrate that both our proposed dataset and models are advantageous for designing new high Tc superconducting candidates. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

WatE: A Wasserstein t-distributed Embedding Method for Information-enriched Graph Visualization 39

WatE: A Wasserstein t-distributed Embedding Method for Infor...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Cheng, Minjie Luo, Dixin Xu, Hongteng Gaoling School of Artifcial Intelligence Renmin University of China China School of Computer Science and Technology Beijing Institute of Technology China Beijing Key Laboratory of Big Data Management and Analysis Methods China

ISBN: (纸本)157735897X

As a fundamental problem of graph analysis, graph visualization aims to embed a set of graphs in a low-dimensional (e.g., 2D) space and provide insights into their distribution and clustering structure. Focusing on this problem, we propose a novel Wasserstein t-distributed embedding (WatE) method, leading to an information-enriched graph visualization paradigm. Our method learns a graph neural network to represent each graph as the mean and covariance of its node embedding distribution. Accordingly, our method can visualize each graph as an ellipse (determined by the mean and the covariance) rather than a single point. The positions of different ellipses reveal the relations among different graphs as traditional visualization methods do, while the size and shape of an ellipse preserve the node-level structural information of the corresponding graph. We propose a regularized t-distributed stochastic neighbor embedding (Rt-SNE) framework to learn the visualization model, deriving a Wasserstein distance-based Student’s t-distribution of graph pairs and fitting the distribution to the data distribution under regularization. Both subjective and objective evaluations demonstrate that WatE achieves encouraging performance in various graph visualization and clustering tasks. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Flow visualization

来源：评论

学校读者我要写书评

暂无评论

Heuristic Algorithm for Solving Travelling Salesman Problem: Adding the Endpoints of the Longest Edges

Heuristic Algorithm for Solving Travelling Salesman Problem:...

引用

International Conference on Problems of Cybernetics and Informatics (PCI)

作者： Fidan Nuriyeva Department of Computer Science Dokuz Eylul University Izmir Turkey Laboratory of Recognition Identification and Methods of Optimal Solutions Institute of Control Systems Baku Azerbaijan

This study proposes, a new heuristic algorithm based on insertion heuristic to solve the symmetric Travelling Salesman Problem. In the proposed algorithm, firstly the two longest edges are selected and the starting tour passing through their endpoints is constructed, then the endpoints of the next longest edges are added to this tour and the solution passing through all the vertices is found. This problem is known to be NP-Hard. The proposed method was successfully tested on different-sized problems. The experimental results show that the proposed algorithm outperforms many existing methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Are Existing Out-Of-Distribution Techniques Suitable for Network Intrusion Detection?

arXiv

引用

arXiv 2023年

作者： Corsini, Andrea Yang, Shanchieh Jay Department of Science and Methods for Engineering University of Modena and Reggio Emilia Modena Italy Department of Computer Engineering Rochester Institute of Technology Rochester United States

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Exploring the Impact of Random Distribution Choices on Particle Swarm Optimization: An Initial Analysis 27

Exploring the Impact of Random Distribution Choices on Parti...

引用

27th International Conference on Knowledge Based and Intelligent Information and Engineering Sytems, KES 2023

作者： Kolodziejczyk, Joanna Tarasenko, Yuliia Sulikowski, Piotr Research Team on Intelligent Decision Support Systems Department of Artificial Intelligence Methods and Applied Mathematics Faculty of Computer Science and Information Technology West Pomeranian University of Technology in Szczecin ul. Zolnierska 49 Szczecin71-210 Poland National Institute of Telecommunications ul. Szachowa 1 Warsaw04-894 Poland Department of Information Systems Engineering Faculty of Computer Science and Information Technology West Pomeranian University of Technology in Szczecin ul. Zolnierska 49 Szczecin71-210 Poland

Particle Swarm Optimization (PSO) is a robust stochastic optimization algorithm for solving complex and constrained optimization problems. This paper aims to systematically investigate the influence of diverse random number distributions on the learning parameters of PSO and evaluate the algorithm's sensitivity based on these parameters. To this end, several exhaustive numerical experiments were conducted on several test functions, including asymmetric Sphere, Easom, and Csendes. Initially, appropriate random distributions were identified for the learning parameters and proceeded to compare these distributions using all potential combinations. The sensitivity of PSO to these parameters was evaluated using the mean best score, the relative proximity of the best particle to the theoretical optimum, and the average objective function evaluations. The most significant contribution of this research lies in the insights derived from the experimental data. The discovery was that highly skewed and long-tailed distributions such as Chi, Chi-square, Lomax, and Exponential often underperform. On the other hand, distributions that are bounded proportionally to the problem domain consistently surpass the performance of the standard uniform distribution. These findings significantly enhance the understanding of PSO algorithms and provide valuable guidelines for their practical deployment. © 2023 The Authors. Published by Elsevier B.V. This is an open access article under the CC BY-NC-ND license (https://***/licenses/by-nc-nd/4.0)

关键词： Particle Swarm Optimization random number distribution stochastic optimization

来源：评论

学校读者我要写书评

暂无评论

System Methodology of Data Analysis and Preprocessing for Solving Classification Problems

System Methodology of Data Analysis and Preprocessing for So...

引用

International computer sciences and Information Technologies (CSIT)

作者： Irina Kalinina Aleksandr Gozhyj Victoria Vysotska Eugene Malakhov Victor Gozhyj Iryna Tregubova Intelligent Information Systems Department Petro Mohyla Black Sea National University Mykolayiv Ukraine Department of Information Systems and Networks Institute of Computer Science and Information Technologies National University “Lviv Polytechnic” Lviv Ukraine Department of Mathematical Methods of Computer Systems of Odessa National Mechnikov University Odesa Ukraine Department of Computer Science State University of Intelligent Technologies and Telecommunications Odesa Ukraine

ISBN: (数字)9798331542634

ISBN: (纸本)9798331542641

The article describes and investigates the systematic methodology of data analysis and preprocessing for solving classification problems. The methodology combines the following groups of methods on the basis of a systemic approach: methods of processing data gaps, methods of processing anomalous values, methods of feature generation, methods of identifying nonlinearities and non-stationarity, and normalization methods. methods of character generation were studied. methods of feature selection and generation are divided into three main groups: filtering methods, wrapping methods, and embedded methods. Since feature selection plays a crucial role in machine learning, increasing model performance and reducing computational costs, the paper proposes a combined feature selection method that includes the step-by-step use of both filtering and wrapping methods. The method consists of five steps to efficiently select the most relevant features of a data set. It offers a better approach to feature selection. This results in improved model performance with fewer features and reduced computational cost. The creation of a red wine classification system was considered for the experimental verification of the system methodology of analysis and pre-processing of data. The Red Wine Quality dataset was used. The purpose of the classification is to identify factors associated with the risk of untimely delivery of previous orders to customers and information about recipients of goods. To solve the task of wine quality classification, simulations were carried out using various algorithms. The effectiveness of the system approach to solving problems of analysis and preprocessing of data to solve problems of classification was proved.

关键词： Data analysis Systematics Filtering Computational modeling Machine learning Feature extraction Computational efficiency Classification algorithms Wrapping Information technology

来源：评论

学校读者我要写书评

暂无评论

Contrastive Hierarchical Clustering

arXiv

引用

arXiv 2023年

作者： Znalezniak, Michal Rola, Przemyslaw Kaszuba, Patryk Tabor, Jacek Śmieja, Marek Advanced Micro Devices Inc. United States Institute of Quantitative Methods in Social Sciences Cracow University of Economics Poland Faculty of Mathematics and Computer Science Adam Mickiewicz University Poland Faculty of Mathematics and Computer Science Jagiellonian University Kraków Poland

Deep clustering has been dominated by flat models, which split a dataset into a predefined number of groups. Although recent methods achieve an extremely high similarity with the ground truth on popular benchmarks, the information contained in the flat partition is limited. In this paper, we introduce CoHiClust, a Contrastive Hierarchical Clustering model based on deep neural networks, which can be applied to typical image data. By employing a self-supervised learning approach, CoHiClust distills the base network into a binary tree without access to any labeled data. The hierarchical clustering structure can be used to analyze the relationship between clusters, as well as to measure the similarity between data points. Experiments demonstrate that CoHiClust generates a reasonable structure of clusters, which is consistent with our intuition and image semantics. Moreover, it obtains superior clustering accuracy on most of the image datasets compared to the state-of-the-art flat clustering models. Our implementation is available at https://github. com/MichalZnalezniak/Contrastive-Hierarchical-Clustering. Copyright © 2023, The Authors. All rights reserved.

关键词： Cluster analysis

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：