检索结果-内蒙古大学图书馆

Towards an intrusion detection system for detecting web attacks based on an ensemble of filter feature selection techniques

引用

Cyber-Physical Systems 2023年第3期9卷 244-259页

作者： Kshirsagar, Deepak Kumar, Sandeep Department of Computer Science and Engineering Indian Institute of Technology Roorkee Roorkee India Department of Computer Engineering and IT College of Engineering Pune Pune India

The use of machine learning models in intrusion detection systems (IDSs) takes more time to build the model with many features and degrade the performance. The present paper proposes an ensemble of filter feature selection techniques (EFFST) to obtain a significant feature subset for web attack detection by selecting one-fourth split of the ranked features. The experimentation on the CICIDS 2017 dataset shows that the proposed EFFST method provides a detection rate of 99.9909%, with J48 using 24 features. The system’s performance is compared to the original features and traditional relevant feature selection methods employed in IDSs. © 2022 Informa UK Limited, trading as Taylor & Francis Group.

关键词： Intrusion detection

来源：评论

学校读者我要写书评

暂无评论

PUPC-GANs: A Novel Image Conversion Model using Modified CycleGANs in Healthcare

引用

Recent Advances in computer science and Communications 2023年第7期16卷 66-73页

作者： Taneja, Shweta Suri, Bhawna Kumar, Aman Chowdhry, Ashish Kumar, Harsh Dwivedi, Kautuk Department Computer Science & Engineering Bhagwan Parshuram Institute of Technology GGSIPU Delhi India

Introduction: Magnetic Resonance Imaging (MRI) and Computed Tomography (CT) both have their areas of specialty in the medical imaging world. MRI is considered to be a safer modality as it exploits the magnetic properties of the hydrogen nucleus. Whereas a CT scan uses multiple X-rays, which is known to contribute to carcinogenesis and is associated with affecting the patient's health. Methods: In scenarios, such as radiation therapy, where both MRI and CT are required for medical treatment, a unique approach to getting both scans would be to obtain MRI and generate a CT scan from it. Current deep learning methods for MRI to CT synthesis purely use either paired data or unpaired data. Models trained with paired data suffer due to a lack of availability of well-aligned data. Results: Training with unpaired data might generate visually realistic images, although it still does not guarantee good accuracy. To overcome this, we proposed a new model called PUPC-GANs (Paired Unpaired CycleGANs), based on CycleGANs (Cycle-Consistent Adversarial Net-works). Conclusion: This model is capable of learning transformations utilizing both paired and unpaired data. To support this, a paired loss is introduced. Comparing MAE, MSE, NRMSE, PSNR, and SSIM metrics, PUPC-GANs outperform CycleGANs. © 2023 Bentham science Publishers.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

Reconstruction probability-based anomaly detection using variational auto-encoders

引用

International Journal of computers and Applications 2023年第3期45卷 231-237页

作者： Iqbal, Touseef Qureshi, Shaima Department of Computer Science and Engineering National Institute of Technology Jammu and Kashmir Srinagar India

Anomaly detection is a method of categorizing unexpected data points or events in a dataset. Variational Auto-Encoders (VAEs) have proved to handle complex problems in a variety of disciplines. We propose a technique for detecting anomalies based on the reconstruction probability of VAEs. The proposed method trains VAEs on three different datasets. The reconstruction probability is a much more principled and realistic anomaly score than the reconstruction error utilized by auto-encoders and other data compression methods because of the theoretical background and by including the concept of variability. The paper describes recent deep learning models for anomaly detection, as well as a comparison to other methodologies. Variational auto-encoders are trained on three different datasets, in an unsupervised setup to classify the anomalies, based on reconstruction probability. Further, the in-depth study of anomaly detection techniques is presented in this paper. The data are reconstructed using the VAEs generative characteristics to investigate the root cause of the anomalies. © 2022 Informa UK Limited, trading as Taylor & Francis Group.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Deep learning model for plant-leaf disease detection in precision agriculture

引用

International Journal of Intelligent Systems Technologies and Applications 2023年第1期21卷 72-91页

作者： Bajpai, Chandrabhanu Sahu, Ramnarayan Naik, K. Jairam Department of Computer Science and Engineering National Institute of Technology Raipur Chhattisgarh Raipur India

Crop disease in the agricultural is the main factor limiting yield and food quality. It requires timely diagnosis of crop illnesses for the better economy developing country. Manual crop illness assessment is limited due to lesser accuracy and restricted accessibility. It is very difficult to accurately identify and classify plant diseases due to corrupt in the data samples, lesser intensity of foreground and background, and the extreme similarity between unhealthy and healthy leaves in terms of colouring and size of crop leaves. Hence the employments of automated and computerised optimisations are needed. To identify plant leaf diseases, a DNSVM classification strategy fusing DenseNet-201 with support vector machine (SVM) is proposed in this work. Plant-Village dataset that provides good-variations, colour-differences, differences in orientation and size-of-leaves. Sugarcane plants-leaves were used for performance analysis of proposed model and obtained 97.78% of classification accuracy over the existing DenseNet-121-based classifier model (94%). © 2023 Inderscience Enterprises Ltd.

关键词： Crops

来源：评论

学校读者我要写书评

暂无评论

PERFORMANCE TEST OF V2X VEHICLE COLLISION WARNING ALGORITHM BASED ON COMBINATION OF VIRTUAL REALITY FUSION

UPB Scientific Bulletin, Series C: Electrical Engineering an...

引用

UPB Scientific Bulletin, Series C: Electrical engineering and computer science 2023年第2期85卷 111-124页

作者： Han, Baojian Zhang, Yu Liu, Yunxiang Zhu, Jianlin Zhang, Qing School of Computer Science and Information Engineering Shanghai Institute of Technology Shanghai201418 China

Proposing a performance testing methodology for vehicle collision warning algorithm at intersections, this approach addresses the issues of the key V2X technology being challenging to simulate with real-scene data in virtual simulations, alongside the high-risk factor, elevated testing cost and limited space during the real vehicle verification process. The proposed method involves constructing a simulation environment based on PreScan and Matlab/Simulink, to verify the algorithm's performance. The sensory data obtained from an on-board unit (OBU) installed in a test vehicle on actual roads is then collected and imported into two indoor OBUs to evaluate the algorithm's efficiency further. The test outcomes reveal that combining real and virtual data with simulated data substantially enhances the efficiency of the algorithm testing and ensures security while further validating its effectiveness in genuine scenarios. © 2023, Politechnica University of Bucharest. All rights reserved.

关键词： Virtual reality

来源：评论

学校读者我要写书评

暂无评论

A Privacy-Preserving Quantum Blockchain Technique for Electronic Medical Records

引用

IEEE engineering Management Review 2023年第4期51卷 137-144页

作者： Venkatesh, Ranjitha Hanumantha, Brahmananda Savadatti Gandhi Institute of Technology and Management Department of Computer Science Engineering Bengaluru561203 India

Nowadays, electronic medical records are increasing rapidly. Electronic medical records consist of sensitive and confidential information. These pieces of information need to be protected from attackers during the exchange with patients. Blockchain technology can protect information from attackers during the exchange of information. There are various classical techniques to protect electronic medical records. These techniques can exchange information correctly but cannot resist collective and coherent attacks and have more communication and computation costs. In this article, we introduced a privacy-preserving quantum blockchain technique to protect electronic medical records. This technique can resist the intercept, intercept-resend, entangle-measure, man-in-the-middle, collective, and coherent attacks with less communication and computation costs. © 1973-2011 IEEE.

关键词： Quantum entanglement

来源：评论

学校读者我要写书评

暂无评论

Intrusion detection and prevention of DDoS attacks in cloud computing environment: a review on issues and current methods

引用

International Journal of Cloud Computing 2023年第5期12卷 450-481页

作者： Devi, B.S. Kiruthika Subbulakshmi, T. School of Computer Science and Engineering Vellore Institute of Technology Tamil Nadu Chennai India

Cloud computing has emerged as the most successful service model for the IT/ITES community due to the various long-term incentives offered in terms of reduced cost, availability, reliability and improved QoS to the cloud users. Most of the applications already migrated to centralised data centres in the cloud. Due to the growing needs of the business model, more small and medium enterprises rely on the cloud because little investment would suffice on the infrastructure and hardware/software. The most alarming cyber-attack in the cloud that interrupts the availability of the cloud services is distributed denial of service (DDoS) attack. In this paper, various existing intrusion detection systems (IDSs) and intrusion prevention systems (IPSs) and their positioning in the cloud are investigated and the essence of the current techniques in the literature is briefed in detail. The comprehensive review on the latest IDS/IPS solutions and their capabilities to detect and prevent intrusions in the cloud are explored and the comparisons of the methodology provides the researchers with the security issues/challenges exposed in the cloud computing environment. The significance of the design of a secure framework for cloud is also being emphasised for achieving improved security in the cloud. © 2023 Inderscience Enterprises Ltd.. All rights reserved.

关键词： Denial-of-service attack

来源：评论

学校读者我要写书评

暂无评论

An Efficient Real Time Decision Making System for Autonomous Vehicle Using Timber Chased Wolf Optimization Based Ensemble Classifier

引用

Journal of engineering science and technology Review 2023年第1期16卷 75-84页

作者： Jaiswal, Swati Mohan, B. Chandra School of Computer Science and Engineering Vellore Institute of Technology Tamil Nadu Vellore India

An autonomous vehicle is anticipated to increase comfort, safety, energy efficiency, emissions reduction, and mobility. The development of autonomous vehicles depends on decision-making algorithms that can handle complex and dynamic urban intersections. Hence in this research, a TCWO based ensemble classifier-based instantaneous decision-making model involved in driverless vehicles is devised. The ensemble classifier is designed through the combination of the Timber chased wolf optimization (TCWO) for detecting traffic sign along with decision process is performed. The bidirectional long short term (BiLSTM) and convolutional neural network (CNN) is combined to create the hybrid ensemble classifier, which is more effective. The TCWO is developed by hybridizing the characteristics of GWO and COA that helps to optimizing the classifiers and boots the classification performance. The TCWO based GAN helps for finding lane in the data that effectively reduces the problems of misclassification by generating synthetic data and training the data to differentiate the original and the generated data. The TCWO-based ensemble classifier attained the values of 98.88%, 98.36%, 98.88% while detecting the traffic sign, and 2.41%, 2.41%, 7.39% while predicting the lane using TCWO-based GAN, which is significantly higher than the competent technique © 2023 School of science, IHU. All rights reserved

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Fuzzing:Progress,Challenges,and Perspectives

引用

computers, Materials & Continua 2024年第1期78卷 1-29页

作者： Zhenhua Yu Zhengqi Liu Xuya Cong Xiaobo Li Li Yin Institute of Systems Security and Control College of Computer Science and TechnologyXi'an University of Science and TechnologyXi'an710054China School of Mathematics and Information Science Baoji University of Arts and SciencesBaoji721013China Institute of Systems Engineering Macao University of Science and TechnologyTaipaMacaoChina

As one of the most effective techniques for finding software vulnerabilities,fuzzing has become a hot topic in software *** feeds potentially syntactically or semantically malformed test data to a target program to mine vulnerabilities and crash the *** recent years,considerable efforts have been dedicated by researchers and practitioners towards improving fuzzing,so there aremore and more methods and forms,whichmake it difficult to have a comprehensive understanding of the *** paper conducts a thorough survey of fuzzing,focusing on its general process,classification,common application scenarios,and some state-of-the-art techniques that have been introduced to improve its ***,this paper puts forward key research challenges and proposes possible future research directions that may provide new insights for researchers.

关键词： Fuzzing vulnerability software testing software security

来源：评论

学校读者我要写书评

暂无评论

A Network Model to Study the Underlying Characteristics of Phishing Sites

IEEE Networking Letters

引用

IEEE Networking Letters 2024年第1期6卷 46-49页

作者： Gayen, Avijit Santra, Sukriti Dey, Ayush Jana, Angshuman Indian Institute of Information Technology Guwahati Department of Computer Science and Engineering Guwahati781015 India Swami Vivekanda University Department of Computer Science and Engineering Kolkata700121 India Techno India University Department of Computer Science and Engineering Kolkata700091 India

In the rapidly evolving landscape of cyber threats, phishing continues to be a prominent vector for cyberattacks, posing significant risks to individuals, organizations and information systems. This letter delves into a comprehensive analysis of phishing sites, focusing on their distinctive characteristics through the lens of network perspectives. In this letter, we study the underlying characteristics of phishing sites from the hyperlinked connectivity perspectives. In this letter, we have used a phishing site dataset available at Mendeley data. As the dataset does not contain any hyperlinked information, We further collect the hyperlinks in each site and store that information in a JSON file. We further analyze the hyperlinks and the various features of those sites. The initial study reveals that though the Phishing sites mimic the original legitimate sites to trap people in their sites, it has distinct differences from the perspective of structural connectivity as well as the content of sites. © 2019 IEEE.

关键词： Data mining

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：