检索结果-内蒙古大学图书馆

ISAnWin: inductive generalized zero-shot learning using deep CNN for malware detection across windows and android platforms

引用

PEERJ COMPUTER SCIENCE 2024年 10卷 e2604-e2604页

作者： Tayyab, Umm-e-Hani Khan, Faiza Babar Khan, Asifullah Durad, Muhammad Hanif Khan, Farrukh Aslam Ali, Aftab Pakistan Inst Engn & Appl Sci Dept Comp & Informat Sci Islamabad Pakistan Pakistan Inst Engn & Appl Sci Pattern Recognit Lab Islamabad Pakistan King Saud Univ Ctr Excellence Informat Assurance Riyadh Saudi Arabia Ulster Univ Sch Comp BELFAST North Ireland

Effective malware detection is critical to safeguarding digital ecosystems from evolving cyber threats. However, the scarcity of labeled training data, particularly for cross-family malware detection, poses a significant challenge. This research proposes a novel architecture ConvNet-6 to be used in Siamese Neural Networks for applying Zero-shot learning to address the issue of data scarcity. The proposed model for malware detection uses the ConvNet-6 architecture even with limited training samples. The proposed model is trained with just one labeled sample per sub-family. We conduct extensive experiments on a diverse dataset featuring Android and Portable Executables' malware families. The model achieves high performance in terms of 82% accuracy on the test dataset, demonstrating its ability to generalize and effectively detect previously unseen malware variants. Furthermore, we examine the model's transferability by testing it on a portable executable malware dataset, despite being trained solely on the Android dataset. Encouragingly, the performance remains consistent. The results of our research showcase the potential of deep convolutional neural network (CNN) in Siamese neural networks for the application of zero-shot learning to detect cross-family malware, even when dealing with minimal labeled training data.

关键词： Malware detection PE malware Android malware End-point protection Artificial intelligence Deep learning Zero-shot learning Algorithms and analysis of algorithms data mining and machine learning data science

来源：评论

学校读者我要写书评

暂无评论

Incremental learning of privacy-preserving Bayesian networks

引用

APPLIED SOFT COMPUTING 2013年第8期13卷 3657-3667页

作者： Samet, Saeed Miri, Ali Granger, Eric Mem Univ Newfoundland Fac Med St John NF Canada Ryerson Univ Dept Comp Sci Toronto ON Canada Univ Quebec Ecole Technol Super Lab Imagerie Vis & Intelligence Artificielle Montreal PQ H3C 3P8 Canada

Bayesian Networks (BNs) have received significant attention in various academic and industrial applications, such as modeling knowledge in image processing, engineering, medicine and bio-informatics. Preserving the privacy of sensitive data, owned by different parties, is often a critical issue. However, in many practical applications, BNs must train from data that gradually becomes available at different period of times, on which the traditional batch learning algorithms are not suitable or applicable. In this paper, an algorithm based on a new and efficient version of Sufficient Statistics is proposed for incremental learning with BNs. The standard kappa 2 algorithm is also modified to be utilized inside the incremental learning algorithm. Next, some secure building blocks such as secure comparison, and factorial, which are resistant against colluding attacks and could be applied securely over public channels like internet, are presented to be used inside the main protocol. Then a privacy-preserving protocol is proposed for incremental learning of BNs, in which the structure and probabilities are estimated incrementally from homogeneously distributed and gradually available data among two or multi-parties. Finally, security and complexity analysis along with the experimental results are presented to compare with the batch algorithm and to show its performance and applicability in real world applications. (C) 2013 Elsevier B. V. All rights reserved.

关键词： Security and privacy preserving Bayesian networks Incremental learning data mining and machine learning

来源：评论

学校读者我要写书评

暂无评论

Simple Pattern Minimality Problems: Integer Linear Programming Formulations and Covering-Based Heuristic Solving Approaches

引用

INFORMS JOURNAL ON COMPUTING 2020年第4期32卷 1049-1060页

作者： Boccia, Maurizio Sforza, Antonio Sterle, Claudio Univ Federico II Naples Dept Elect Engn & Informat Technol I-80125 Naples Italy CNR Ist Anal Sistemi Informat Antonio Ruberti I-00185 Rome Italy

The simple pattern minimality problem (SPMP) represents a central problem in the logical analysis of data and association rules mining, and it finds applications in several fields as logic synthesis, reliability analysis, and automated reasoning. It consists of determining the minimum number of patterns explaining all the observations of a data set, that is, a Boolean logic formula that is true for all the elements of the data set and false for all the unseen observations. We refer to this problem as covering SPMP (C-SPMP), because each observation can be explained (covered) by more than one pattern. Starting from a real industrial application, we also define a new version of the problem, and we refer to it as partitioning SPMP (P-SPMP), because each observation has to be covered just once. Given a propositional formula or a truth table, C-SPMP and P-SPMP coincide exactly with the problem of determining the minimum disjunctive and minimum exclusive disjunctive normal form, respectively. Both problems are known to be NP-hard and have been generally tackled by heuristic methods. In this context, the contribution of this work is twofold. On one side, it provides two original integer linear programming formulations for the two variants of the SPMP. These formulations exploit the concept of Boolean hypercube to build a graph representation of the problems and allow to exactly solve instances with more than 1,000 observations by using an MIP solver. On the other side, two effective and fast heuristics are proposed to solve relevant size instances taken from literature (SeattleSNPs) and from the industrial database. The proposed methods do not suffer from the same dimensional drawbacks of the methods present in the literature and outperform either existing commercial and freeware logic tools or the available industrial solutions in the number of generated patterns and/or in the computational burden.

关键词： data mining and machine learning logical analysis of data simple pattern minimality problem covering/partitioning approach

来源：评论

学校读者我要写书评

暂无评论

A new nested ensemble technique for automated diagnosis of breast cancer

引用

PATTERN RECOGNITION LETTERS 2020年 132卷 123-131页

作者： Abdar, Moloud Zomorodi-Moghadam, Mariam Zhou, Xujuan Gururajan, Raj Tao, Xiaohui Barua, Prabal D. Gururajan, Rashmi Univ Quebec Montreal Dept Informat Montreal PQ Canada Ferdowsi Univ Mashhad Dept Comp Engn Mashhad Razavi Khorasan Iran Univ Southern Queensland Sch Management & Enterprise Toowoomba Qld Australia Univ Southern Queensland Fac Hlth Engn & Sci Toowoomba Qld Australia Queensland Hlth Royal Brisbane & Womens Hosp Brisbane Qld Australia

Nowadays, breast cancer is reported as one of most common cancers amongst women. Early detection of this cancer is an essential to aid in informing subsequent treatments. This study investigates automated breast cancer prediction using machine learning and data mining techniques. We proposed the nested ensemble approach which used the Stacking and Vote (Voting) as the classifiers combination techniques in our ensemble methods for detecting the benign breast tumors from malignant cancers. Each nested ensemble classifier contains "Classifiers" and "MetaClassifiers". MetaClassifiers can have more than two different classification algorithms. In this research, we developed the two-layer nested ensemble classifiers. In our two-layer nested ensemble classifiers the MetaClassifiers have two or three different classification algorithms. We conducted the experiments on Wisconsin Diagnostic Breast Cancer (WDBC) dataset and K-fold Cross Validation technique are used for the model evaluation. We compared the proposed two-layer nested ensemble classifiers with single classifiers (i.e., BayesNet and Naive Bayes) in terms of the classification accuracy, precision, recall, F 1 measure, ROC and computational times of training single and nested ensemble classifiers. We also compared our best model with previous works reported in the literatures in terms of accuracy. The results demonstrate that the proposed two-layer nested ensemble models outperformance the single classifiers and most of the previous works. Both SV-BayesNet-3MetaClassifier and SV-Naive Bayes-3-MetaClassifier achieved accuracy 98.07% (K = 10). However, SV-Naive Bayes-3-MetaClassifier is more efficiency as it needs less time to build the model. (c) 2018 Elsevier B.V. All rights reserved.

关键词： data mining and machine learning Breast cancer Nested ensemble technique BayesNet classifier Naive Bayes classifier

来源：评论

学校读者我要写书评

暂无评论

Privacy-Preserving Protocols for Perceptron learning Algorithm in Neural Networks

Privacy-Preserving Protocols for Perceptron Learning Algorit...

引用

4th International IEEE Conference Intelligent Systems

作者： Samet, Saeed Miri, Ali Univ Ottawa Sch Informat Technol & Engn Ottawa ON K1N 6N5 Canada

ISBN: (纸本)9781424417391

Neural networks have become increasingly important in areas such as medical diagnosis, bio-informatics, intrusion detection, and homeland security. In most of these applications, one major issue is preserving privacy of individual's private information and sensitive data. In this paper, we propose two secure protocols for perceptron learning algorithm when input data is horizontally and vertically partitioned among the parties. These protocols can be applied in both linearly separable and non-separable datasets, while not only data belonging to each party remains private, but the final learning model is also securely shared among those parties. Parties then can jointly and securely apply the constructed model to predict the output corresponding to their target data. Also, these protocols can be used incrementally, i.e. they process new coming data, adjusting the previously constructed network.

关键词： Security and Privacy Preserving Neural Networks data mining and machine learning Distributed data Structures

来源：评论

学校读者我要写书评

暂无评论

Highway Accident Severity Prediction for Optimal Resource Allocation of Emergency Vehicles and Personnel 11

Highway Accident Severity Prediction for Optimal Resource Al...

引用

IEEE 11th Annual Computing and Communication Workshop and Conference (CCWC)

作者： Alnami, Hani M. Mahgoub, Imad Al-Najada, Hamzah Florida Atlantic Univ Comp & Elect Engn & Comp Sci 777 Glades Rd Boca Raton FL 33431 USA

ISBN: (纸本)9781665414906

Traffic accidents could have significant impacts on people's lives. Roughly half a million highway traffic accidents occurred in 2018 in the USA. Intelligent Transportation Systems (ITSs) and Vehicular Ad Hoc Networks (VANETs) have great potential to enhance highway traffic safety and improve emergency response. This paper uses real-life traffic and accident data for a Florida highway to build prediction models to predict traffic accident severity. Accurate severity prediction is beneficial for both the responders and the drivers. First responders are in high demand, and the pandemic has made the situation worse. When an accident occurs, the emergency center dispatches a random number of emergency vehicles. Unfortunately, this number exceeds the number of vehicles needed most of the time, leaving fewer resources to respond to simultaneous accidents in different locations. Also, an increased number of emergency vehicles could introduce secondary accidents. In fact, for every ten accidents, one of them is a secondary accident. Our research gives an accurate prediction for the number of emergency vehicles needed based on the accident severity. We have used historical traffic and accident data obtained from the Florida Department of Transportation District 4 (FDOT-D4) to predict an accident and its severity. This can be used to esetimate the right number of emergency vehicles to respond to the accident. Our real-time prediction models can help reduce highway traffic accidents and congestion as well. Our prediction results demonstrate promising accuracy results and computation cost to support ITS applications.

关键词： data mining and machine learning Classification algorithms Intelligent Transportation System (ITS) Vehicle Ad Hoc Network (VANET) Big data

来源：评论

学校读者我要写书评

暂无评论

Impact of emerging technologies on Facility Services - A mixed-methodic approach on Smart Building Technologies 44

Impact of emerging technologies on Facility Services - A mix...

引用

44th Annual Conference of the IEEE Industrial-Electronics-Society (IECON)

作者： Redlein, Alexander Grasl, Lisa Vienna Univ Technol IFM Real Estate & Facil Management A-1040 Vienna Austria

ISBN: (纸本)9781509066841

The Facility Service (FS) industry is the third largest sector in the EU. In Europe, as well as in the US, around 10% of all employees work in this sector. Macro economic studies estimate that in general 47% of all jobs will be automated due to digitalization. FS will be highly affected by the megatrend digitalization as numerous routine tasks are performed in this sector. However, current studies only provide a macroeconomic view on the changes. Therefore, this paper aims to answer the following research questions: Which smart building technologies are relevant for FS? Which are already in use and which services will be affected? The basis for the current research was a qualitative pre-study. Fifty German speaking Facility Managers were asked about the technical and economic feasibility of smart building technologies in the FS sector. Based on the smart building technologies identified as relevant, the authors carried out a quantitative literature review. This analysis did not only include publications about the usage of smart building technologies in the FS industry, but also considered use cases on the technologies identified by the pre-study in other industries. In total, more than 350 cases were analyzed. Based on that literature review, a research database was set up to explore the relevant technologies and the affected services in detail. The next research step was to compare the results of scientific publication with those of commercial studies and the results of the pre-study. Thus, this paper outlines the relevant technologies and FS. It further presents the detailed results of the validation process.

关键词： evaluation of smart building technologies internet of things artificial intelligence data mining and machine learning augmented and virtual reality in buildings

来源：评论

学校读者我要写书评

暂无评论

To Fear or Not to Fear That is the Question: Code Characteristics of a Vulnerable Function with an Existing Exploit 16

To Fear or Not to Fear That is the Question: Code Characteri...

引用

6th ACM Conference on data and Application Security and Privacy (CODASPY)

作者： Younis, Awad Malaiya, Yashwant K. Anderson, Charles Ray, Indrajit Colorado State Univ Dept Comp Sci Ft Collins CO 80523 USA

ISBN: (纸本)9781450339353

Not all vulnerabilities are equal. Some recent studies have shown that only a small fraction of vulnerabilities that have been reported has actually been exploited. Since finding and addressing potential vulnerabilities in a program can take considerable time and effort, recently effort has been made to identify code that is more likely to be vulnerable. This paper tries to identify the attributes of the code containing a vulnerability that makes the code more likely to be exploited. We examine 183 vulnerabilities from the National Vulnerability database for Linux Kernel and Apache HTTP server. These include eighty-two vulnerabilities that have been found to have an exploit according to the Exploit database. We characterize the vulnerable functions that have no exploit and the ones that have an exploit using eight metrics. The results show that the difference between a vulnerability that has no exploit and the one that has an exploit can potentially be characterized using the chosen software metrics. However, predicting exploitation of vulnerabilities is more complex than predicting just the presence of vulnerabilities and further research is needed using metrics that consider security domain knowledge for enhancing the predictability of vulnerability exploits.

关键词： Vulnerabilities Severity Exploitability Software security Exploits data mining and machine learning Feature selection Prediction Software metrics

来源：评论

学校读者我要写书评

暂无评论

Packet Information Collection and Transformation for Network Intrusion Detection and Prevention

Packet Information Collection and Transformation for Network...

引用

International Symposium on Telecommunications

作者： Beheshti, Mohsen Han, Jianchao Kowalski, Kazimierz Ortiz, Joel Tomelden, Johnly Alvillar, Damian Calif State Univ Dominguez Hills Dept Comp Sci Carson CA 90747 USA

ISBN: (纸本)9781424427505

data mining and machine learning technology has been extensively applied in network intrusion detection and prevention systems by discovering user behavior patterns from the network traffic data. Some commercial tools for collecting network traffic data exist, such as SNORT. The traffic data collected from the network using these tools, however, usually doesn't fit the format requirement of the input data for data mining systems. Thus transforming the network traffic data into the required format is mandate for a data mining system to induce network intrusion detection rules. In this paper, collecting the network packet information using SNORT is introduced, storing the collected data into the MySq1 database is presented, and selecting the significant data in the database and transforming them to the format of input data for a data mining system See5 is discussed. The data collection, selection, and transformation approaches illustrated in this paper have been used in the Information Fusion in Sensor Based Intrusion Detection System that is being under development in our Computer Security Research Laboratory. The system framework is briefly introduced and the preliminary results for data collection from multiple resources are illustrated.

关键词： data collection and pre-processing data mining and machine learning data transformation information fusion network intrusion detection and prevention

来源：评论

学校读者我要写书评

暂无评论

Impact of green technology innovation based on IoT and industrial supply chain on the promotion of enterprise digital economy

引用

PEERJ COMPUTER SCIENCE 2023年 9卷 e1416页

作者： Song, Ruilin Hu, Hui Wuhan City Coll Econ & Management Div Wuhan Hube Peoples R China Hubei Sci & Technol Innovat High Qual Dev Res Ctr Wuhan Hubei Peoples R China

With the gradual deterioration of the natural environment, a green economy has become a competing goal for all countries. As a trend of green innovation development, the digital economy has become a research hotspot for scientists. In this article, we study the supply chain management of enterprises in green innovation and digital economy development and complete the identification and demand prediction of warehouse goods through the Internet of Things (IoT) and artificial intelligence (AI). As the stuff meets the goods detection and storage, we employ an intelligent method to detect and classify the goods. The demand prediction analysis is carried out based on historical data on goods demand in the enterprise. The absolute error between the prediction result and the actual demand within 1 week is less than 30 goods by the particle swarm optimization-support vector machine (PSO-SVM) method used in this article. First, the goods identification task is completed based on video surveillance data using YOLOv4, and the recognition rate is as high as 98.3%. This article realises enterprises' intelligent supply chain management through the intelligent identification of goods and the demand forecasting analysis of goods in the warehouse, which provides new ideas for green innovation and digital economy development.

关键词： IoT Supply chain management Green innovation Digital economy PSO-SVM data mining and machine learning

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：