检索结果-内蒙古大学图书馆

Multimodal and Temporal Graph Fusion Framework for Advanced Phishing Website Detection

IEEE Access 2025年 13卷 74128-74146页

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

Phishing attacks are among the persistent threats that are dynamically evolving and demand advanced detection mechanisms to counter more sophisticated techniques. Traditional detection approaches are usually based on single-modal features or static analysis, failing to capture the complex, multi-faceted nature of phishing websites and their dynamic behaviors. Thus, we present a robust Multi-Modal and Temporal Graph Fusion Framework integrating advanced learning paradigms that enhance accuracy and adaptability in phishing detection. Our work proposes four brand-new methods: Multi-Modal Hypergraph Fusion Network (MM-HFN), Temporal Graph Neural Network with Attention (TGNN-Att), Federated Graph Contrastive Learning Network (FGCL-Net), and Multi-Modal Temporal Hypergraph Fusion Network (MMTHF-Net). MM-HFN leverages hypergraphs to capture complex, high-order relationships at textual levels (BERT) and graph-based features versus visual ones (CNNs) for an accuracy in the 95–97% range. TGNN-Att addresses temporal variations in phishing behavior by using attention-enhanced temporal graph networks and LSTMs, providing dynamic detection with 94–96% accuracy. FGCL-Net ensures privacy-preserving learning across decentralized datasets through federated contrastive learning, achieving 93–95% accuracy while safeguarding data privacy. Finally, MMTHF-Net fuses multi-modal and temporal features into a dynamic hypergraph framework, achieving state-of-the-art accuracy of 96–98% with an F1-score of 0.97. These approaches together allow for exact, real-time phishing detection by capturing static and temporal behaviors, high-order relationships, and cross-modal features. The framework proposed demonstrates significant improvements compared to the state of the art, eliminating the shortcomings of single-modality and static analysis while offering scalability, privacy, and adaptability levels. © 2013 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Power synchronization: taming massive diversified serverless functions under power constraints

引用

science China(Information sciences) 2025年第3期68卷 47-65页

作者： Du LIU Lu ZHANG Yechen XU Xinkai WANG Lingyu SUN Yifei PU Xiaofeng HOU Chao LI Minyi GUO Department of Computer Science and Engineering Shanghai Jiao Tong University AI Chip Center for Emerging Smart Systems The Hong Kong University of Science and Technology

Carbon neutrality has become an important design objective worldwide. However, the on-going shift to cloud-naive era does not necessarily mean energy efficiency. From the perspective of power management, co-hosted serverless functions are difficult to tame. They are lightweight, short-lived applications sensitive to power capping activities. In addition, they exhibit great individual and temporal variability, presenting idiosyncratic performance/power scaling goals that are often at odds with one another. To date, very few proposals exist in terms of tailored power management for serverless platforms. In this work, we introduce power synchronization, a novel yet generic mechanism for managing serverless functions in a power-efficient way. Our insight with power synchronization is that uniform application power behavior enables consistent and uncompromised function operation on shared host machines. We also propose PowerSync, a synchronization-based power management framework that ensures optimal efficiency based on a clear understanding of functions. Our evaluation shows that PowerSync can improve the energy efficiency of functions by up to 16% without performance loss compared to conventional power management strategies.

关键词： serverless computing variability energy efficiency power management power synchronization

来源：评论

学校读者我要写书评

暂无评论

Edge-aware Feature Aggregation Network for Polyp Segmentation

引用

Machine Intelligence Research 2025年第1期22卷 101-116页

作者： Tao Zhou Yizhe Zhang Geng Chen Yi Zhou Ye Wu Deng-Ping Fan PCA Lab Key Laboratory of Intelligent Perception and Systems for High-dimensional Information of Ministry of EducationSchool of Computer Science and EngineeringNanjing University of Science and TechnologyNanjing210094China School of Computer Science and Engineering Northwestern Polytechnical University(NPU)Xi’an710129China School of Computer Science and Engineering Southeast UniversityNanjing211189China Computer Vision Lab ETH ZürichZürich8092Switzerland

Precise polyp segmentation is vital for the early diagnosis and prevention of colorectal cancer(CRC)in clinical ***,due to scale variation and blurry polyp boundaries,it is still a challenging task to achieve satisfactory segmentation performance with different scales and *** this study,we present a novel edge-aware feature aggregation network(EFA-Net)for polyp segmentation,which can fully make use of cross-level and multi-scale features to enhance the performance of polyp ***,we first present an edge-aware guidance module(EGM)to combine the low-level features with the high-level features to learn an edge-enhanced feature,which is incorporated into each decoder unit using a layer-by-layer ***,a scale-aware convolution module(SCM)is proposed to learn scale-aware features by using dilated convolutions with different ratios,in order to effectively deal with scale ***,a cross-level fusion module(CFM)is proposed to effectively integrate the cross-level features,which can exploit the local and global contextual ***,the outputs of CFMs are adaptively weighted by using the learned edge-aware feature,which are then used to produce multiple side-out segmentation *** results on five widely adopted colonoscopy datasets show that our EFA-Net outperforms state-of-the-art polyp segmentation methods in terms of generalization and *** implementation code and segmentation maps will be publicly at https://***/taozh2017/EFANet.

关键词： Colorectal cancer polyp segmentation edge-aware guidance module scale-aware convolution module cross-level fusion module

来源：评论

学校读者我要写书评

暂无评论

Classifying distinct emotions from parents of ASD child using EEG source data by combining Bernoulli–Laplace Prior and graph neural networks

引用

Neural Computing and Applications 2025年第12期37卷 7877-7895页

作者： ArulDass, Stephen Dass Jayagopal, Prabhu School of Computer Science Engineering and Information Systems Vellore Institute of Technology Tamil Nadu Vellore632014 India

Emotion recognition using biological brain signals needs to be reliable to attain effective signal processing and feature extraction techniques. The impact of emotions in interpretations, conversations, and decision-making, has made automatic emotion recognition and examination of a significant feature in the field of psychiatric disease treatment and cure. The problem arises from the limited spatial resolution of EEG recorders. Predetermined quantities of electroencephalography (EEG) channels are used by existing algorithms, which combine several methods to extract significant data. The major intention of this study was to focus on enhancing the efficiency of recognizing emotions using signals from the brain through an experimental, adaptive selective channel selection approach that recognizes that brain function shows distinctive behaviors that vary from one individual to another individual and from one state of emotions to another. We apply a Bernoulli–Laplace-based Bayesian model to map each emotion from the scalp senses to brain sources to resolve this issue of emotion mapping. The standard low-resolution electromagnetic tomography (sLORETA) technique is employed to instantiate the source signals. We employed a progressive graph convolutional neural network (PG-CNN) to identify the sources of the suggested localization model and the emotional EEG as the main graph nodes. In this study, the proposed framework uses a PG-CNN adjacency matrix to express the connectivity between the EEG source signals and the matrix. Research on an EEG dataset of parents of an ASD (autism spectrum disorder) child has been utilized to investigate the ways of parenting of the child's mother and father. We engage with identifying the personality of parental behaviors when regulating the child and supervising his or her daily activities. These recorded datasets incorporated by the proposed method identify five emotions from brain source modeling, which significantly improves the accurac

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Domain generalization with semi-supervised learning for people-centric activity recognition

引用

science China(Information sciences) 2025年第1期68卷 171-188页

作者： Jing LIU Wei ZHU Di LI Xing HU Liang SONG Academy for Engineering & Technology Fudan University Shanghai East-bund Research Institute on Networking Systems of AI School of Optoelectronic Information and Computer Engineering University of Shanghai for Science & Technology

People-centric activity recognition is one of the most critical technologies in a wide range of real-world applications,including intelligent transportation systems, healthcare services, and brain-computer interfaces. Large-scale data collection and annotation make the application of machine learning algorithms prohibitively expensive when adapting to new tasks. One way of circumventing this limitation is to train the model in a semi-supervised learning manner that utilizes a percentage of unlabeled data to reduce the labeling burden in prediction tasks. Despite their appeal, these models often assume that labeled and unlabeled data come from similar distributions, which leads to the domain shift problem caused by the presence of distribution gaps. To address these limitations, we propose herein a novel method for people-centric activity recognition,called domain generalization with semi-supervised learning(DGSSL), that effectively enhances the representation learning and domain alignment capabilities of a model. We first design a new autoregressive discriminator for adversarial training between unlabeled and labeled source domains, extracting domain-specific features to reduce the distribution gaps. Second, we introduce two reconstruction tasks to capture the task-specific features to avoid losing information related to representation learning while maintaining task-specific consistency. Finally, benefiting from the collaborative optimization of these two tasks, the model can accurately predict both the domain and category labels of the source domains for the classification task. We conduct extensive experiments on three real-world sensing datasets. The experimental results show that DGSSL surpasses the three state-of-the-art methods with better performance and generalization.

关键词： activity recognition deep learning domain generalization semi-supervised learning adversarial training

来源：评论

学校读者我要写书评

暂无评论

A verifiable variable threshold visual image secret sharing scheme

引用

Multimedia systems 2025年第3期31卷 1-18页

作者： Yang, Yu-Guang Cheng, Wen Xu, Guang-Bao Jiang, Dong-Huan Zhou, Yi-Hua Shi, Wei-Min Jiang, Dong-Hua College of Computer Science and Technology Beijing University of Technology Beijing100124 China College of Computer Science and Engineering Shandong University of Science and Technology Qingdao266590 China College of Mathematics and Systems Science Shandong University of Science and Technology Qingdao266590 China School of Computer Science and Engineering Sun Yat-Sen University Guangzhou511400 China

This paper proposes a visual image encryption algorithm based on 2D compressive sensing and variable threshold secret sharing, aiming to achieve efficient, secure, and flexible image encryption and decryption. Firstly, the plain image is compressed and encrypted using the 2D compressive sensing technique, while the measurement matrix and disordered sequence are generated through an improved chaotic system. Secondly, the shadow image is produced using the variable threshold secret sharing scheme, and a corresponding authentication signature is generated to verify the integrity and authenticity of the shadow image. Finally, the shadow image and its signature are embedded into a carrier image to generate a cipher image with visual steganography. Experimental results demonstrate that the proposed algorithm achieves excellent performance in terms of operational efficiency, visual encryption quality, and decryption performance. The encryption execution time is 0.694 s, the PSNR of decrypted images is approximately 32 dB, and the PSNR of cipher images is around 42 dB, ensuring high visual concealment and reconstruction quality while maintaining security. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2025.

关键词： Image compression

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Based Side-Channel Attack Detection for Mobile Devices Security in 5G Networks

引用

清华大学学报自然科学版（英文版） 2025年第3期30卷 1012-1026页

作者： Amjed A.Ahmed Mohammad Kamrul Hasan Ali Alqahtani Shayla Islam Bishwajeet Pandey Leila Rzayeva Huda Saleh Abbas Azana Hafizah Mohd Aman Nayef Alqahtani Center for Cyber Security Faculty of Information Science and TechnologyUniversiti Kebangsaan MalaysiaBangi 43600Malaysia Imam Alkadhim University College Department of Computer Techniques EngineeringBaghdad 10066Iraq Center for Cyber Security Faculty of Information Science and TechnologyUniversiti Kebangsaan MalaysiaBangi 43600Malaysia Department of Networks and Communications Engineering College of Computer Science and Information SystemsNajran UniversityNajran 61441Saudi Arabia Institute of Computer Science and Digital Innovation UCSI UniversityKuala Lumpur 56000Malaysia Department of Intelligent Systems and Cyber Security Astana IT UniversityAstana 20000Kazakstan Department of Computer Science College of Computer Science and EngineeringTaibah UniversityMadinah 42353Saudi Arabia Department of Electrical Engineering College of EngineeringKing Faisal UniversityAl-Hofuf 31982Saudi Arabia

Mobile devices within Fifth Generation(5G)networks,typically equipped with Android systems,serve as a bridge to connect digital gadgets such as global positioning system,mobile devices,and wireless routers,which are vital in facilitating end-user communication ***,the security of Android systems has been challenged by the sensitive data involved,leading to vulnerabilities in mobile devices used in 5G *** vulnerabilities expose mobile devices to cyber-attacks,primarily resulting from security ***-permission apps in Android can exploit these channels to access sensitive information,including user identities,login credentials,and geolocation *** such attack leverages"zero-permission"sensors like accelerometers and gyroscopes,enabling attackers to gather information about the smartphone's *** underscores the importance of fortifying mobile devices against potential future *** research focuses on a new recurrent neural network prediction model,which has proved highly effective for detecting side-channel attacks in mobile devices in 5G *** conducted state-of-the-art comparative studies to validate our experimental *** results demonstrate that even a small amount of training data can accurately recognize 37.5％of previously unseen user-typed ***,our tap detection mechanism achieves a 92％accuracy rate,a crucial factor for text *** findings have significant practical implications,as they reinforce mobile device security in 5G networks,enhancing user privacy,and data protection.

关键词： Fifth Generation(5G)networks smartphone information leakage Side-Channel Attack(SCA) deep learning

来源：评论

学校读者我要写书评

暂无评论

Scattering Medium Removal Using Adaptive Masks for Scatter in the Spatial Frequency Domain

引用

IEEE Access 2025年 13卷 72769-72777页

作者： Jeong, Jongpil Lee, Min-Chul Kyushu Institute of Technology Graduate School of Computer Science and Systems Engineering Iizuka Fukuoka820-8502 Japan

To address this issue, this paper presents an adaptive method for removing scattering media using a mask based on wireless communication fading models. We hypothesize a similarity between light propagation and wireless communication systems, which incorporates scattering estimates through models such as the Rayleigh and Rician fading models, which are applied to process the captured images and mitigate scattering effects. Our proposed method incorporates two systems: the Scattered Image Model and the Scattering Media Model. The conventional dehazing method requires processing sequences’ approximated depth map or specific background. However, the proposed method functions regardless of the image’s depth and specific background colors. To validate the proposed method, we conducted optical experiments and tested outdoor images. The results were compared with conventional haze-removal methods, such as dark channel prior and Peplography, using various image quality metrics, e.g., the Peak Signal-to-Noise ratio, Structural Similarity Index Measurement, Tone Mapped Image Quality, and Feature Similarity Index Measurement extended to color imagery. The experimental results demonstrated significant improvements over the conventional methods across all metrics. © 2013 IEEE.

关键词： Frequency domain analysis

来源：评论

学校读者我要写书评

暂无评论

IMPROVEMENT OF THE ACO ALGORITHM FOR INTELLIGENT TASK SCHEDULING IN CLOUD systems

引用

Scalable Computing 2025年第2期26卷 531-539页

作者： DJEBBAR, ESMA INSAF BELALEM, GHALEM Department of Computer Science Systems Engineering National Polytechnic School of Oran-Maurie Audin Oran Algeria Department of Computer Science University of Oran1-Ahmed Ben Bella Algeria

Cloud computing involves accessing and using computing resources, such as servers, storage, and software applications, over the Internet, enabling scalable access on demand. Cloud computing systems are becoming an essential platform for scientific applications. They enable task scheduling and IT resource allocation. When these resources are not enough to meet demand, planning techniques are necessary. We propose to apply an improved ACO algorithm for intelligent task scheduling and appropriate resource allocation in a cloud environment. This work proposes a modified version of the ACO algorithm that can quickly converge to the best solution to further optimize the total response time, the average response time and the total execution cost. The algorithm suggested based on artificial intelligence application of enhanced ACO is compared with the classical ACO algorithm using Cloudsim simulator. The results obtained after the experiments and simulation are very encouraging to adopt this technique. © (2025), (West University of Timisoara). All rights reserved.

关键词： Cloud platforms

来源：评论

学校读者我要写书评

暂无评论

An enhanced framework for smart automated evaluations of answer scripts using NLP and deep learning methods

引用

Multimedia Tools and Applications 2025年第11期84卷 8491-8513页

作者： G, Mohanraj R.K, Nadesh M, Marimuthu V, Sathiyapriya School of Computer Science Engineering and Information Systems Vellore Institute of Technology Vellore632014 India School of Computer Science and Engineering Vellore Institute of Technology Chennai600127 India Knowledge Institute of Technology Salem637504 India

The manual process of evaluating answer scripts is strenuous. Evaluators use the answer key to assess the answers in the answer scripts. Advancements in technology and the introduction of new learning paradigms need automation of the evaluation process. This work aims to develop an enhanced novel hybrid framework that can evaluate answer scripts and automatically assign marks for different type of questions based on keywords, grammar, symbols, special keywords, and the given factors. First, the proposed system uses Optical Character Recognition (OCR) to convert image answer scripts into an editable text format. Second, the sentence transformers, the Natural Language Processing (NLP) technique flips the answer script and answers key texts into word embedding vectors. To find similarity measures, these vectors are matched using BERT encoding, spearmanś rank-order correlation, and fuzzy search. At last, the proposed model is trained using Deep Columnar Convolutional Neural Network (DCCNN) in the third step with MINST and Kaggle handwritten mathematical symbols and tested with the segmented mathematical equations to find the similarity. The performance of proposed model is measured using precision, recall, accuracy, and F1-score, and its gives highest accuracy of 93% and 95% when compared to the existing methodologies. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Optical character recognition

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：