检索结果-内蒙古大学图书馆

8th International Conference on Electronics, Communication and Aerospace Technology, ICECA 2024

作者： Kavya, S. Sumathi, D. Vellore Institute of Technology School of Computer Science Engineering and Information Systems Vellore India

ISBN: (纸本)9798350367904

Phishing attacks are always surfacing as key threats against internet users, necessitating advanced detection methods. Blacklist-based systems and rule-based models of phishing detection generally have had critical limitations in dealing with evolving tactics and new phishing schemes. Some of these approaches fail to cope with the temporal and visual patterns of phishing sites, which are crucial for timely and accurate detection. To overcome these difficulties, this work introduces a hybrid AI-based phishing website detection model that utilizes several machine learning and deep learning techniques to improve the accuracy of the detection and remove false positives. The proposed model uses LSTM networks, Genetic Algorithms, Random Forest, and CNN through the stacking ensemble framework. Since LSTM is adopted to capture the temporal dependencies in the website traffic and user interaction patterns, this model can effectively model their phishing behavior over time. GA is used for bioinspired feature selection to reduce the dimensionality of features while optimizing model performance. Random Forest is used as a base layer addressing structured features like URL characteristics and WHOIS information. CNNs are incorporated to extract feature content from a webpage and images that carry various visual indicators often used in phishing attacks including counterfeit logos or banners. A meta-classifier is then used to combine the outputs of LSTMs, CNN, and RF and generate the final classification to boost the detection rate. The proposed hybrid model surpasses the existing techniques and facilitates the analysis of temporal, visual, and structured data, making the detection considerably more accurate. Achieving accuracy of as much as 96-97% and having an AUC of 0.97 with a false positive rate below 3%, the model then impacts the more powerful and more flexible phishing detection system, which is then capable of being more protective against higher sophisticated phishing te

关键词： Phishing

来源：评论

学校读者我要写书评

暂无评论

CropViT: A light-weight Transformer Model for Crop Disease Detection 3

CropViT: A light-weight Transformer Model for Crop Disease D...

引用

3rd International Conference on Artificial Intelligence For Internet of Things, AIIoT 2024

作者： Chemmalar Selvi, G. Charan, H.J. Kumar, Dinesh Vellore Institute of Technology School of Computer Science Engineering and Information Systems Vellore India

ISBN: (纸本)9798350372120

Agricultural industry has grown significantly bring sustainable farming practices in improving the food quality, enhancing agricultural productivity and global food security. However, the crop yield and its quality are impacted when the timely identification and management of the crop diseases are not promptly solved. Thus, the crop disease detection becomes the critical aspect in the smart agriculture. Several researchers addressed this crop disease detection by developing optimized solutions through machine learning, deep learning and image processing techniques. However, these techniques face serious challenges when deployed in real-time crop disease identification problems like annotated training images, capturing long-range dependencies, adaption to real-time changes evolving over time and so on. This leads to performance degradation seeking for more powerful applications like some advanced deep learning techniques, in particular, the transformer models. In this paper, a novel crop disease detection model known as CropViT was proposed based on Vision Transformer. This CropViT was developed by fine-tuning the architecture of existing Vision Transformer and PlantVillage dataset was used in the experimental study. Nine crop species were selected and trained using CropViT whose performance was then compared with traditional Convolutional Neural Network model. The experimental study clearly showed the highest mean accuracy of 98.64% for CropViT when compared to 95.52% mean accuracy for traditional CNN. The experimental results also outperformed other existing state-of-the-art models. Finally, the work was concluded with the discussion of experimental results and its future scope of work. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Oversampling-Enhanced Feature Fusion-Based Hybrid ViT-1DCNN Model for Ransomware Cyber Attack Detection

引用

computer Modeling in engineering & Sciences 2025年第2期142卷 1667-1695页

作者： Muhammad Armghan Latif Zohaib Mushtaq Saifur Rahman Saad Arif Salim Nasar Faraj Mursal Muhammad Irfan Haris Aziz Department of Computer and Information System Cleveland State UniversityOhio44115USA Department of Electrical Electronics and Computer SystemsCollege of Engineering and TechnologyUniversity of SargodhaSargodha40100Pakistan Electrical Engineering Department College of EngineeringNajran UniversityNajran61441Saudi Arabia Department of Mechanical Engineering College of EngineeringKing Faisal UniversityAl Ahsa31982Saudi Arabia Department of Mechanical Industrial and Energy System EngineeringUniversity of SargodhaSargodha40100Pakistan

Ransomware attacks pose a significant threat to critical infrastructures,demanding robust detection *** study introduces a hybrid model that combines vision transformer(ViT)and one-dimensional convolutional neural network(1DCNN)architectures to enhance ransomware detection *** common challenges in ransomware detection,particularly dataset class imbalance,the synthetic minority oversampling technique(SMOTE)is employed to generate synthetic samples for minority class,thereby improving detection *** integration of ViT and 1DCNN through feature fusion enables the model to capture both global contextual and local sequential features,resulting in comprehensive ransomware *** on the UNSW-NB15 dataset,the proposed ViT-1DCNN model achieved 98%detection accuracy with precision,recall,and F1-score metrics surpassing conventional *** approach not only reduces false positives and negatives but also offers scalability and robustness for real-world cybersecurity *** results demonstrate the model’s potential as an effective tool for proactive ransomware detection,especially in environments where evolving threats require adaptable and high-accuracy solutions.

关键词： Ransomware attacks cybersecurity vision transformer convolutional neural network feature fusion encryption threat detection

来源：评论

学校读者我要写书评

暂无评论

Krushi Snehi: A Web-Based Application for Safe and Smart Farming 8th

Krushi Snehi: A Web-Based Application for Safe and Smart Far...

引用

8th International Conference on Information and Communication Technology for Competitive Strategies, ICTCS 2023

作者： Jain, Sanyam Thaseen, Sumaiya School of Computer Science Engineering and Information Systems Vellore Institute of Technology Vellore India

ISBN: (纸本)9789819712595

The challenges stemming from crop diseases and a limited grasp of optimal fertilization practices have significantly burdened farmers, leading to reduced crop yields and a ripple effect of interconnected issues. This research paper introduces a novel solution in the form of a web-based application, meticulously crafted to assist farmers in swiftly identifying crop diseases, providing relevant precautions, and offering tailored fertilizer recommendations for specific crops. Notably, the application boasts a user-friendly interface, seamlessly catering to intuitive navigation and content comprehension, presented in the user's preferred language. Of notable importance, the application serves as a conduit for disseminating valuable insights concerning government initiatives, and effectively acquainting farmers with available incentives and authoritative helpline resources. By harnessing the power of this application, farmers can cultivate a comprehensive understanding of pivotal strategies for mitigating crop infections, potentially culminating in a significant upswing in crop production rates. We had achieved an accuracy of 98.98% in classifying the crop diseases. This innovative tool not only promises to effectively tackle longstanding agricultural challenges but also to equip farmers with actionable insights, thereby underpinning the advancement of agricultural productivity. In doing so, it lays the groundwork for the adoption of sustainable and prosperous farming practices, promising a transformative trajectory for farming communities. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Fertilizers

来源：评论

学校读者我要写书评

暂无评论

A Robust Phaseless Imaging Approach Using Reverse Kullback Leibler Divergence and Wirtinger Flow

A Robust Phaseless Imaging Approach Using Reverse Kullback L...

引用

2024 IEEE Conference on Computational Imaging Using Synthetic Apertures, CISA 2024

作者： Choudhury, Nazia Afroz Yonel, Bariscan Yazici, Birsen Rensselaer Polytechnic Institute Electrical Computer and Systems Engineering TroyNY United States

ISBN: (纸本)9798350308648

Phaseless imaging is a prominent field of study in many imaging modalities. In practical applications, the phaseless measurements usually contain noise and outliers, limiting the reconstruction algorithms' performance. In this paper, we study the reverse Kullback-Leibler divergence (RKLD) as a robust objective function for mitigating the effects of corrupted measurements. We optimize RKLD using the state-of-the-art Wirtinger Flow (WF) algorithm for image reconstruction. Then, we numerically demonstrate the performance of RKLD using simulated coded diffraction measurements and a real optical dataset. Additionally, we compare RKLD's performance with other well-known loss functions used by the WF framework, namely, £2-intensity, Poisson, and £2-magnitude. Our simulation results demonstrate that RKLD-based optimization provides higher quality reconstructed images than the other loss functions in the presence of noise and outliers. © 2024 IEEE.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

A New Hybrid Model for Segmentation of the Skin Lesion Based on Residual Attention U-Net

引用

computers, Materials & Continua 2023年第6期75卷 5177-5192页

作者： Saleh Naif Almuayqil Reham Arnous Noha Sakr Magdy M.Fadel Department of Information Systems College of Computer and Information SciencesJouf UniversitySakakaSaudi Arabia Department of Communications and Electronics Delta Higher Institute for Engineering and Technology(DHIET)MansouraEgypt Computers Engineering and Control Systems Department Faculty of EngineeringMansoura UniversityMansouraEgypt

Skin segmentation participates significantly in various biomedical applications,such as skin cancer identification and skin lesion *** paper presents a novel framework for segmenting the *** framework contains two main stages:The first stage is for removing different types of noises from the dermoscopic images,such as hair,speckle,and impulse noise,and the second stage is for segmentation of the dermoscopic images using an attention residual U-shaped Network(U-Net).The framework uses variational Autoencoders(VAEs)for removing the hair noises,the Generative Adversarial Denoising Network(DGAN-Net),the Denoising U-shaped U-Net(D-U-NET),and Batch Renormalization U-Net(Br-U-NET)for remov-ing the speckle noise,and the Laplacian Vector Median Filter(MLVMF)for removing the impulse *** the second main stage,the residual attention u-net was used for *** framework achieves(35.11,31.26,27.01,and 26.16),(36.34,33.23,31.32,and 28.65),and(36.33,32.21,28.54,and 27.11)for removing hair,speckle,and impulse noise,respectively,based on Peak Signal Noise Ratio(PSNR)at the level of(0.1,0.25,0.5,and 0.75)of *** framework also achieves an accuracy of nearly 94.26 in the dice score in the process of segmentation before removing noise and 95.22 after removing different types of *** experiments have shown the efficiency of the used model in removing noise according to the structural similarity index measure(SSIM)and PSNR and in the segmentation process as well.

关键词： Skin tumor speckle noise impulse noise hair noise deep learning segmentation

来源：评论

学校读者我要写书评

暂无评论

Integrating AES-GCM, ECC, and Steganography for Enhanced Confidential Communication

Integrating AES-GCM, ECC, and Steganography for Enhanced Con...

引用

2024 International Conference on Electrical, Electronics and Computing Technologies, ICEECT 2024

作者： Shrinivas, S. Varun, G.K. Thiagarajan, Priya Thiagarajar College of Engineering Computer Science And Business Systems Tamil Nadu Madurai India

ISBN: (纸本)9798350378092

In the modern world of information and technology, the prime requirement is highly secure data communication against the cyber threat. Efficient data communication should support all principles of information security: confidentiality, integrity, availability, authentication, authorization, and key management. This paper attempts at integrating three robust cryptographic techniques, viz., AES-GCM, ECC, and steganography for developing a secure mechanism for data transfer. Other research objectives also examine the establishment of combined effectiveness techniques in safeguarding CIAAA and the management of keys to key management processes. Among the anticipated outcomes is an additional improvement in data security that would provide blanket, advanced coverage for modern information security practice. © 2024 IEEE.

关键词： Data integrity

来源：评论

学校读者我要写书评

暂无评论

Multifunctional Pre-processing Approach for Diabetes Mellitus Prediction Using Ensemble Learning 3

Multifunctional Pre-processing Approach for Diabetes Mellitu...

引用

3rd International Conference on Artificial Intelligence For Internet of Things, AIIoT 2024

作者： Divya, S. Sudha, M. Vellore Institute of Technology School of Computer Science Engineering and Information Systems Vellore India

ISBN: (纸本)9798350372120

Diabetes mellitus when untreated can result in a number of health issues. It is a metabolic disease marked by abnormal blood glucose levels. Early detection of diabetes improves a person's long-term health by halting its progression. Making better medical decisions can be greatly aided through the implementation into practice automated techniques that can precisely identify pre- and diabetic situations. In this paper Synthetic Minority Oversampling Technique and Adaptive Oversampling Technique is used to address class imbalance problem and Chi-square test, Recursive feature elimination methods are involved in detecting and extracting relevant components from unprocessed data. These techniques are applied to the framework and compared using different ensemble learning classifiers such as XGBoost, AdaBoost, LightGBM and CATBoost. The result shows us CATBoost with ADASYN and RFE provides us with better accuracy of 0.96%. © 2024 IEEE.

关键词： Adaptive boosting

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Approach to Validate and Retrieve Fingerprint Image for Authenticating Database Sensitive Information Access and to Verify Some of Topological Multi-Granular Rough Sets Properties on Authenticated Database Fields 2

A Hybrid Approach to Validate and Retrieve Fingerprint Image...

引用

2nd International Conference on Emerging Trends in Information Technology and engineering, ic-ETITE 2024

作者： Raghavan, R. John Singh, K. School of Computer Science Engineering and Information Systems Vellore Institute of Technology Vellore India

ISBN: (纸本)9798350328202

Content based image retrieval has already begun to turn into an intriguing and exceptionally needed field to meet with the client prerequisite. Fingerprint approvals likewise have become a fascinating field to principally uphold the confirmation framework. Notwithstanding foundations regulating guaranteed about information straightforwardly, affiliations are also obliging them to examine the fingerprint endorsement. Despite establishments overseeing ensured about data, directly associations are similarly obliging them to research the fingerprint check. Organizations and foundations both are typically utilizing the idea of fingerprint for the participation and presence reason. Nevertheless, establishments presently managing secured information as like institutes and additionally going along with them to investigate the fingerprint authentication. More than this usual action there are some particular applications where the authentication would be considerable to help the application than using a traditional pattern of password. We proposed a fingerprint authentication system for the scientific based industry database access system. We removed the noise if any found in the input fingerprint using anisotropic Gauss filtering. The noise free fingerprint image is not further passed to the binarization phase as the need of binarization and some form of the drawback of binarization is replaced with a thinning algorithm. The thinned fingerprint image is followed by the matching process and once it is matched, then only the sensitive and highly confidential information are allowed to access from the database. The testing is done using OpenCV and FVC 2004 dataset to assess the projected retrieval method. Further the matched fingerprints are used to prove some of the internal structure properties of multi-granular rough sets (MGRS) on authenticated database fields. The accuracy obtained in this hybrid approach is found to be more satisfactory and hence the security towards acce

关键词： Database systems

来源：评论

学校读者我要写书评

暂无评论

Enhancing Video Protection: A Reversible Digital Watermarking approach using Swin features and Arnold Transform enabled Multi-Aggregation Model 3

Enhancing Video Protection: A Reversible Digital Watermarkin...

引用

3rd International Conference on Artificial Intelligence For Internet of Things, AIIoT 2024

作者： Dilip, Mali Satish Agilandeeswari, L. Vellore Institute of Technology School of Computer Science Engineering and Information Systems Vellore India

ISBN: (纸本)9798350372120

Nowadays, the widespread internet technology brings out rapid advancement in the use of videos for sharing huge amounts of secret data. Conversely, the privacy of transmitted digital content is jeopardized by digital image processing techniques that are capable of producing flawless image or video duplication. Moreover, providing security to digital records in the form of videos is a highly challenging task, which requires a fusion-based watermarking technique to protect the data from illegitimate access and fraudulent usage. In this investigation, a tiny Swin and Arnold Transform-enabled Multi-aggregation model was introduced to protect video based on digital watermarking characteristics at a very low computational cost. Here, the Swin-T features are extracted from the input video, over which the Arnold transform and multi-aggregation model is developed in two phases. The best embedding location is identified by using multi aggregation model initially at the embedding phase and the inverse Arnold transform for secret image (VIT Logo) embedding in a binary embedding location to obtain the embedded video. The secret image is extracted from the attacked embedded video using the Arnold transform-multi-aggregation model in the extraction phase. The developed data-hiding technique is also evaluated to compute the robustness using the evaluation parameters. The simulation results reveal that the developed scheme achieved Peak-Signal-to-Noise Ratio (PSNR) and Similarity Index Measure (SSIM) values of 64.57 ∼dB and 0.9993 respectively. © 2024 IEEE.

关键词： Embeddings

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：