检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Guo, Mingyu Ward, Max Neumann, Aneta Neumann, Frank Nguyen, Hung School of Computer Science University of Adelaide Australia School of Physics Maths and Computing Computer Science and Software Engineering University of Western Australia Australia Department of Molecular and Cellular Biology Harvard University CambridgeMA United States

Active Directory (AD) is the default security management system for Windows domain networks. An AD environment naturally describes an attack graph where nodes represent computers/accounts/security groups, and edges represent existing accesses/known exploits that allow the attacker to gain access from one node to another. Motivated by practical AD use cases, we study a Stackelberg game between one attacker and one defender. There are multiple entry nodes for the attacker to choose from and there is a single target (Domain Admin). Every edge has a failure rate. The attacker chooses the attack path with the maximum success rate. The defender can block a limited number of edges (i.e., revoke accesses) from a set of blockable edges, limited by budget. The defender’s aim is to minimize the attacker’s success rate. We exploit the tree-likeness of practical AD graphs to design scalable algorithms. We propose two novel methods that combine theoretical fixed parameter analysis and practical optimisation techniques. For graphs with small tree widths, we propose a tree decomposition based dynamic program. We then propose a general method for converting tree decomposition based dynamic programs to reinforcement learning environments, which leads to an anytime algorithm that scales better, but loses the optimality guarantee. For graphs with small numbers of non-splitting paths (a parameter we invent specifically for AD graphs), we propose a kernelization technique that significantly downsizes the model, which is then solved via mixed-integer programming. Experimentally, our algorithms scale to handle synthetic AD graphs with tens of thousands of nodes. Copyright © 2022, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Symmetrical Supervision with Transformer for Few-shot Medical Image Segmentation

Symmetrical Supervision with Transformer for Few-shot Medica...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Yao Niu Zhiming Luo Sheng Lian Lei Li Shaozi Li Haixin Song Department of Artificial Intelligence Xiamen University Fujian China College of Computer and Data Science Fuzhou University Fujian China Department of Software Engineering Xiamen University Fujian China

ISBN: (数字)9781665468190

ISBN: (纸本)9781665468206

Few-shot learning can potentially learn the target knowledge in extremely few data regimes. Existing few-shot medical image segmentation methods fail to consider the global anatomy correlation between the support and query sets. They generally adopt a weak one-way information transmission that can not fully explore the knowledge to segment query data. To address this problem, we propose a novel Symmetrical Supervision network based on traditional two-branch methods. We raise two main contributions: (1) The Symmetrical Supervision Mechanism is leveraged to strengthen the supervision of network training; (2) A transformer-based Global Feature Alignment module is introduced to increase the global consistency between the two branches. Experimental results on two challenging datasets (abdominal segmentation dataset CHAOS and cardiac segmentation dataset MS-CMRSeg) show a remarkable performance compared to other comparing methods.

关键词： Training Chaos Image segmentation Correlation Biological system modeling Information processing Transformers

来源：评论

学校读者我要写书评

暂无评论

Transformers for 1D signals in Parkinson's disease detection from gait

arXiv

引用

arXiv 2022年

作者： Nguyen, Duc Minh Dimitri Miah, Mehdi Bilodeau, Guillaume-Alexandre Bouachir, Wassim Litiv Laboratory Dept. of Computer Engineering and Software Engineering Polytechnique Montréal Montréal Canada Téluq University Department of Science and Technology Montréal Canada

This paper focuses on the detection of Parkinson's disease based on the analysis of a patient's gait. The growing popularity and success of Transformer networks in natural language processing and image recognition motivated us to develop a novel method for this problem based on an automatic features extraction via Transformers. The use of Transformers in 1D signal is not really widespread yet, but we show in this paper that they are effective in extracting relevant features from 1D signals. As Transformers require a lot of memory, we decoupled temporal and spatial information to make the model smaller. Our architecture used temporal Transformers, dimension reduction layers to reduce the dimension of the data, a spatial Transformer, two fully connected layers and an output layer for the final prediction. Our model outperforms the current state-of-the-art algorithm with 95.2% accuracy in distinguishing a Parkinsonian patient from a healthy one on the Physionet dataset. A key learning from this work is that Transformers allow for greater stability in results. The source code and pre-trained models are released in https://***/DucMinhDimitriNguyen. Copyright © 2022, The Authors. All rights reserved.

关键词： Image recognition

来源：评论

学校读者我要写书评

暂无评论

Effects of term weighting approach with and without stop words removing on Arabic text classification

Effects of term weighting approach with and without stop wor...

引用

International Conference on Optimization and Applications (ICOA)

作者： Esra’a Alhenawi Ruba Abu Khurma Pedro A. Castillo Maribel G. Arenas Ayat Mahmoud Al-Hinawi Department of Software Engineering Faculty of Information Technology Al-Ahliyya Amman University Amman Jordan Department of Computer Science MEU Research Unit Faculty of Information Technology Middle East University Amman Jordan University of Granada Granada Spain Department of Allied Engineering Sciences Hashemite University Zarqa Jordan

Text classification is a technique for grouping articles into pre-defined categories. Prior to categorization, text documents have to be set up and organised in a form that is compatible with the data mining techniques. That has produced many term weighting techniques have been developed in the literature to improve the functionality of text categorization systems. This paper compares techniques for text classification based on when stop words are eliminated from the documents once and when they are not. We used an Arabic data set of 322 papers grouped into six subjects (health, politics, science, education, agriculture and finance) to research which is the influence of prior weighting of features approaches on classification outcomes with regard to accuracy, recall, precision, and F-measure values. Each document subset includes 50 documents, except the health one that includes 61. We carried out four experiments and checked results getting that only for precision, the term frequency feature weighting approach with stop word removal are more or less the same than for binary method. Moreover the conclusion for accuracy, recall and F-measure is that Feature weighting approach with stop word outperforms the Binary one. Additionally, if the phrase for weighting is the same for both methods, to remove stop word increases classification accuracy for all the experiments.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multi-block-Single-probe Variance Reduced Estimator for Coupled Compositional Optimization

arXiv

引用

arXiv 2022年

作者： Jiang, Wei Li, Gang Wang, Yibo Zhang, Lijun Yang, Tianbao National Key Laboratory for Novel Software Technology Nanjing University Nanjing China Department of Computer Science the University of Iowa Iowa City United States Department of Computer Science and Engineering Texas A&M University College Station United States

Variance reduction techniques such as SPIDER/SARAH/STORM have been extensively studied to improve the convergence rates of stochastic non-convex optimization, which usually maintain and update a sequence of estimators for a single function across iterations. What if we need to track multiple functional mappings across iterations but only with access to stochastic samples of O(1) functional mappings at each iteration? There is an important application in solving an emerging family of coupled compositional optimization problems in the form of Pmi=1 fi(gi(w)), where gi is accessible through a stochastic oracle. The key issue is to track and estimate a sequence of g(w) = (g1(w), . . ., gm(w)) across iterations, where g(w) has m blocks and it is only allowed to probe O(1) blocks to attain their stochastic values and Jacobians. To improve the complexity for solving these problems, we propose a novel stochastic method named Multi-block-Single-probe Variance Reduced (MSVR) estimator to track the sequence of g(w). It is inspired by STORM but introduces a customized error correction term to alleviate the noise not only in stochastic samples for the selected blocks but also in those blocks that are not sampled. With the help of the MSVR estimator, we develop several algorithms for solving the aforementioned compositional problems with improved complexities across a spectrum of settings with non-convex/convex/strongly convex/Polyak-Lojasiewicz (PL) objectives. Our results improve upon prior ones in several aspects, including the order of sample complexities and dependence on the strong convexity parameter. Empirical studies on multi-task deep AUC maximization demonstrate the better performance of using the new estimator. Copyright © 2022, The Authors. All rights reserved.

关键词： Error correction

来源：评论

学校读者我要写书评

暂无评论

Exploring Issues of Story-Based Effort Estimation in Agile software Development

SSRN

引用

SSRN 2023年

作者： Iqbal, Muhammad Ijaz, Muhammad Mazhar, Tehseen Shahzad, Tariq Abbas, Qamar Ghadi, Yazeed Yasin Ahmed, Waseem Hamam, Habib Institute of Computing and Information Technology Gomal University Dera Ismail Khan KP Pakistan Department of Computer Science Virtual University of Pakistan Lahore55150 Pakistan Department of Computer Sciences COMSATS University Islamabad Sahiwal Campus Sahiwal57000 Pakistan Department of Computer Science FCIT International Islamic University Islamabad Pakistan Department of computer science and software engineering Al Ain University Abu Dhabi15322 United Arab Emirates Department of Computer Science and Information Technology University of Malakand Pakistan Faculty of Engineering University of de Moncton MonctonNBE1A3E9 Canada Commune d'Akanda B.P. Libreville1989 Gabon School of Electrical Engineering Department of Electrical and Electronic Engineering. Science University of Johannesburg Johannesburg2006 South Africa Spectrum of Knowledge Production & Skills Development Sfax3027 Tunisia

Objctives This research delves into the domain of user story-based effort estimation in agile software development, aiming to explore the issues arising from inaccurate estimations. The primary goal is to uncover these issues comprehensively and propose potential solutions, thus enhancing the efficacy. Methods To achieve the research objectives, a systematic literature review (SLR) is conducted, surveying a wide range of sources to gather insights into issues surrounding user story-based effort estimation. Results The SLR reveals a spectrum of issues undermining the accuracy of user story-based effort estimation. It identifies internal factors like communication, team expertise, and composition. © 2023, The Authors. All rights reserved.

关键词： software design

来源：评论

学校读者我要写书评

暂无评论

On the Privacy of Mental Health Apps: An Empirical Investigation and its Implications for Apps Development

arXiv

引用

arXiv 2022年

作者： Iwaya, Leonardo Horn Ali Babar, M. Rashid, Awais Wijayarathna, Chamila Centre for Research on Engineering Software Technologies The University of Adelaide AdelaideSA5005 Australia Australia Department of Mathematics and Computer Science Karlstad University Karlstad Sweden Bristol Cyber Security Group Department of Computer Science University of Bristol United Kingdom

An increasing number of mental health services are offered through mobile systems, a paradigm called mHealth. Although there is an unprecedented growth in the adoption of mHealth systems, partly due to the COVID-19 pandemic, concerns about data privacy risks due to security breaches are also increasing. Whilst some studies have analyzed mHealth apps from different angles, including security, there is relatively little evidence for data privacy issues that may exist in mHealth apps used for mental health services, whose recipients can be particularly vulnerable. This paper reports an empirical study aimed at systematically identifying and understanding data privacy incorporated in mental health apps. We analyzed 27 top-ranked mental health apps from Google Play Store. Our methodology enabled us to perform an in-depth privacy analysis of the apps, covering static and dynamic analysis, data sharing behaviour, server-side tests, privacy impact assessment requests, and privacy policy evaluation. Furthermore, we mapped the findings to the LINDDUN threat taxonomy, describing how threats manifest on the studied apps. The findings reveal important data privacy issues such as unnecessary permissions, insecure cryptography implementations, and leaks of personal data and credentials in logs and web requests. There is also a high risk of user profiling as the apps' development do not provide foolproof mechanisms against linkability, detectability and identifiability. Data sharing among third parties and advertisers in the current apps' ecosystem aggravates this situation. Based on the empirical findings of this study, we provide recommendations to be considered by different stakeholders of mHealth apps in general and apps developers in particular. We conclude that while developers ought to be more knowledgeable in considering and addressing privacy issues, users and health professionals can also play a role by demanding privacy-friendly apps. Copyright © 2022, The Authors. All r

关键词： Data privacy

来源：评论

学校读者我要写书评

暂无评论

Joint Admission Control and Resource Allocation of Virtual Network Embedding via Hierarchical Deep Reinforcement Learning

arXiv

引用

arXiv 2024年

作者： Wang, Tianfu Shen, Li Fan, Qilin Xu, Tong Liu, Tongliang Xiong, Hui Anhui Province Key Laboratory of Big Data Analysis and Application School of Computer Science University of Science and Technology of China Hefei230027 China The School of Big Data and Software Engineering Chongqing University ChinaScience Chongqing401331 China JD Explore Academy The UBTECH Sydney Artificial Intelligence Centre The School of Information Technologies Faculty of Engineering and Information Technologies The University of Sydney DarlingtonNSW2008 Australia Thrust of Artificial Intelligence Nansha Guangdong Guangzhou511400 China The Hong Kong University of Science and Technology Department of Computer Science and Engineering Hong Kong

As an essential resource management problem in network virtualization, virtual network embedding (VNE) aims to allocate the finite resources of physical network to sequentially arriving virtual network requests (VNRs) with different resource demands. Since this is an NP-hard combinatorial optimization problem, many efforts have been made to provide viable solutions. However, most existing approaches have either ignored the admission control of VNRs, which has a potential impact on long-term performances, or not fully exploited the temporal and topological features of the physical network and VNRs. In this paper, we propose a deep Hierarchical Reinforcement Learning approach to learn a joint Admission Control and Resource Allocation policy for VNE, named HRL-ACRA. Specifically, the whole VNE process is decomposed into an upper-level policy for deciding whether to admit the arriving VNR or not and a lower-level policy for allocating resources of the physical network to meet the requirement of VNR through the HRL approach. Considering the proximal policy optimization as the basic training algorithm, we also adopt the average reward method to address the infinite horizon problem of the upper-level agent and design a customized multi-objective intrinsic reward to alleviate the sparse reward issue of the lower-level agent. Moreover, we develop a deep feature-aware graph neural network to capture the features of VNR and physical network and exploit a sequence-to-sequence model to generate embedding actions iteratively. Finally, extensive experiments are conducted in various settings, and show that HRL-ACRA outperforms state-of-the-art baselines in terms of both the acceptance ratio and long-term average revenue. Our code is available at https://***/GeminiLight/hrl-acra. Copyright © 2024, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Application of Neural Networks for Network Traffic Monitoring and Analysis

Application of Neural Networks for Network Traffic Monitorin...

引用

International Symposium on Multidisciplinary Studies and Innovative Technologies (ISMSIT)

作者： Oleksandr Kushnerov Pierre Murr Serhii Herasymov Stanislav Milevskyi Marharyta Melnyk Sergii Golovashych Department of Economic Cybernetics Sumy State University Sumy Ukraine Computer Engineering Department International University of Science and Technology in Kuwait Kuwait Kuwait Cybersecurity department National Technical University “Kharkiv polytechnic institute” Kharkiv Ukraine Department of Cyber Security and information protection SET University Kyiv Ukraine Department of Software Engineering and Management Intelligent Technologies National Technical University “Kharkiv polytechnic institute” Kharkiv Ukraine

ISBN: (数字)9798350354423

ISBN: (纸本)9798350354430

Monitoring and analyzing network traffic are critically important tasks in the context of increasing cyber threats. Traditional data processing methods often struggle to handle the large volumes and complexity of modern network traffic, necessitating the use of advanced technologies such as neural networks and machine learning. This article demonstrates the application of neural networks for monitoring and analyzing network traffic, highlighting their ability to learn from large datasets to detect complex patterns and anomalies. Using TensorFlow, we developed a neural network model based on an autoencoder that effectively identifies and classifies anomalies in network traffic. The model's effectiveness was validated using a synthetic dataset from Kaggle, showing high accuracy on both training and testing data. Our approach significantly improves the efficiency and accuracy of threat detection compared to traditional methods, making it a valuable tool for enhancing cybersecurity.

关键词： Training Accuracy Neural networks Telecommunication traffic Machine learning Data models Threat assessment computer security Monitoring Testing

来源：评论

学校读者我要写书评

暂无评论

AdvMask: A Sparse Adversarial Attack Based Data Augmentation Method for Image Classification

arXiv

引用

arXiv 2022年

作者： Yang, Suorong Li, Jinqiao Zhao, Jian Shen, Furao State Key Laboratory for Novel Software Technology Department of Computer Science and Technology Nanjing University Nanjing210023 China The State Key Laboratory for Novel Software Technology School of Electronic Science and Engineering Nanjing University Nanjing210023 China

Data augmentation is a widely used technique for enhancing the generalization ability of convolutional neural networks (CNNs) in image classification tasks. Occlusion is a critical factor that affects on the generalization ability of image classification models. In order to generate new samples, existing data augmentation methods based on information deletion simulate occluded samples by randomly removing some areas in the images. However, those methods cannot delete areas of the images according to their structural features of the images. To solve those problems, we propose a novel data augmentation method, AdvMask, for image classification tasks. Instead of randomly removing areas in the images, AdvMask obtains the key points that have the greatest influence on the classification results via an end-to-end sparse adversarial attack module. Therefore, we can find the most sensitive points of the classification results without considering the diversity of various image appearance and shapes of the object of interest. In addition, a data augmentation module is employed to generate structured masks based on the key points, thus forcing the CNN classification models to seek other relevant content when the most discriminative content is hidden. AdvMask can effectively improve the performance of classification models in the testing process. The experimental results on various datasets and CNN models verify that the proposed method outperforms other previous data augmentation methods in image classification tasks. Copyright © 2022, The Authors. All rights reserved.

关键词： Image classification

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：