检索结果-内蒙古大学图书馆

APWF: A Parallel Website Fingerprinting Attack with Attention Mechanism

computers, Materials & Continua 2025年第2期82卷 2027-2041页

作者： Dawei Xu Min Wang Yue Lv Moxuan Fu Yi Wu Jian Zhao College of Computer Science and Technology Changchun UniversityChangchun130022China School of Cyberspace Science and Technology Beijing Institute of TechnologyBeijing100081China Key Laboratory of Intelligent Rehabilitation and Barrier-Free for the Disabled Changchun UniversityChangchun130022China China Academy of Information and Communications Technology Beijing100083China Key Laboratory of Mobile Application Innovation and Governance Technology Ministry of Industry and Information TechnologyBeijing100846China

Website fingerprinting (WF) attacks can reveal information about the websites users browse by de-anonymizing encrypted traffic. Traditional website fingerprinting attack models, focusing solely on a single spatial feature, are inefficient regarding training time. When confronted with the concept drift problem, they suffer from a sharp drop in attack accuracy within a short period due to their reliance on extensive, outdated training data. To address the above problems, this paper proposes a parallel website fingerprinting attack (APWF) that incorporates an attention mechanism, which consists of an attack model and a fine-tuning method. Among them, the APWF model innovatively adopts a parallel structure, fusing temporal features related to both the front and back of the fingerprint sequence, along with spatial features captured through channel attention enhancement, to enhance the accuracy of the attack. Meanwhile, the APWF method introduces isomorphic migration learning and adjusts the model by freezing the optimal model weights and fine-tuning the parameters so that only a small number of the target, samples are needed to adapt to web page changes. A series of experiments show that the attack model can achieve 83% accuracy with the help of only 10 samples per category, which is a 30% improvement over the traditional attack model. Compared to comparative modeling, APWF improves accuracy while reducing time costs. After further fine-tuning the freezing model, the method in this paper can maintain the accuracy at 92.4% in the scenario of 56 days between the training data and the target data, which is only 4% less loss compared to the instant attack, significantly improving the robustness and accuracy of the model in coping with conceptual drift.

关键词： Website fingerprinting attack transfer learning concept drift

来源：评论

学校读者我要写书评

暂无评论

DYTC:Dynamic Graph Triangle Counting on GPU 24

DYTC:Dynamic Graph Triangle Counting on GPU

引用

8th International Conference on Algorithms, Computing and Systems, ICACS 2024

作者： Wang, Zhuo Li, Zhixiong Tu, Jinxing Huang, Jianqiang Department of Computer Technology and Applications Qinghai University Xining China Intelligent Computing and Application Laboratory of Qinghai Province Qinghai University Xining China

ISBN: (纸本)9798400718304

Triangle counting is a critical problem in graph theory and network analysis, with widespread applications in social network analysis, network science, and bioinformatics. Dynamic graphs are extensively utilized in various domains and are prevalent in real-world scenarios. Over time, dynamic graphs necessitate frequent updates, where vertices and edges are inserted, deleted, or modified. However, existing dynamic graph analysis methods often focus solely on the data structure of dynamic graphs, neglecting the algorithms for dynamic graph processing. Current triangle counting methods are typically designed for static graphs and are not suited for continuously updated dynamic graphs. In this paper, we propose an incremental triangle counting algorithm tailored for dynamic graphs, which only requires recomputing the affected subgraph caused by updated edges, rather than the entire graph. Consequently, in comparison to the previous algorithm, our algorithm is capable of attaining a maximum speedup of . © 2024 Copyright held by the owner/author(s). Publication rights licensed to ACM.

关键词： Graph algorithms

来源：评论

学校读者我要写书评

暂无评论

Communication Countermeasure Strategy Decision-Making Based on Incomplete Information Game 27

Communication Countermeasure Strategy Decision-Making Based ...

引用

27th International Conference on Advanced Communications technology, ICACT 2025

作者： Liu, Jinyue Gao, Xiang Yang, Haowei Zhang, Jihao Liu, Yuhan Gong, Peng National Key Laboratory of Mechatronic Engineering and Control School of Mechatronical Engineering Beijing Institute of Technology Beijing China Institute of Computer Application Technology Norinco Group Beijing China

ISBN: (纸本)9791188428137

In modern battlefields, the stability of wireless communications is crucial for intelligence transmission, command coordination, and maintaining strategic advantage. However, with the rapid advancement of communication technologies, the electromagnetic environment has become increasingly complex, making intelligent decision-making in communication countermeasures a prominent research focus. However, most existing studies adopt deep learning and reinforcement learning methods, which require extensive data samples and computational resources. To address these limitations, this paper proposes a game-theoretic model for intelligent radio communication countermeasures under incomplete information. It quantitatively evaluates common attack and defense tactcis used in communication countermeasures and explores the mixed-strategy equilibrium of the game when both the attackers and defenders consist of multiple types. Furthermore, simulation-based comparative analyses are conducted to assess the factors influencing the utility of both the attacker and defender. The findings offer theoretical insights and decision-making support for the deployment of communication countermeasure strategies in practical military operations, contributing to significant strategic value. © 2025 Institute of Electrical and Electronics Engineers Inc.. All rights reserved.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

FSA-Net:A Cost-efficient Face Swapping Attention Network with Occlusion-Aware Normalization

引用

Intelligent Automation & Soft Computing 2023年第7期37卷 971-983页

作者： Zhipeng Bin Huihuang Zhao Xiaoman Liang Wenli Chen College of Computer Science and Technology Hengyang Normal UniversityHengyang421002China Hunan Provincial Key Laboratory of Intelligent Information Processing and Application Hengyang421002China

The main challenges in face swapping are the preservation and adaptive superimposition of attributes of two *** this study,the Face Swapping Attention Network(FSA-Net)is proposed to generate photoreal-istic face *** existing face-swapping methods ignore the blending attributes or mismatch the facial keypoint(cheek,mouth,eye,nose,etc.),which causes artifacts and makes the generated face silhouette *** address this problem,a novel reinforced multi-aware attention module,referred to as RMAA,is proposed for handling facial fusion and expression occlusion *** framework includes two *** the first stage,a novel attribute encoder is proposed to extract multiple levels of target face attributes and integrate identities and attributes when synthesizing swapped *** the second stage,a novel Stochastic Error Refinement(SRE)module is designed to solve the problem of facial occlusion,which is used to repair occlusion regions in a semi-supervised way without any *** proposed method is then compared with the current state-of-the-art *** obtained results demonstrate the qualitative and quantitative outperformance of the proposed *** details are provided at the footnote link and at https://***/view/fsa-net-official.

关键词： Attention face-swapping neural network face manipulation identity swap image translation

来源：评论

学校读者我要写书评

暂无评论

Hybrid Electroencephalography-Induced Robot Navigation for Rehabilitative Platform 20

Hybrid Electroencephalography-Induced Robot Navigation for R...

引用

20th IEEE India Council International Conference, INDICON 2023

作者： Ghosh, Ahona Ghosh, Lidia Dey, Sharmistha Sarkar, Indranil Saha, Sriparna Maulana Abul Kalam Azad University of Technology Department of Computer Science & Engineering West Bengal India Rcc Institute of Information Technology Department of Computer Application Kolkata India University Institute of Computing Chandigarh University Punjab Gharuan India Guru Nanak Institute of Technology Department of Computer Application India

ISBN: (纸本)9798350305593

Decoding upper limb movement from electroencephalography (EEG) signals is an emerging field of research that has the potential to enhance the quality of life for individuals with motor impairments. This paper provides an informative overview of EEG-based upper limb movement decoding and addresses the limitations found in existing studies by proposing a novel rehabilitative robotics framework. The framework utilizes three types of EEG signals: motor imagery, error-related potential, and P300 signals, to navigate an OpenManipulatorX robotic arm. The novelty of this research lies in the utilization of a phase-sensitive Common Spatial Pattern approach for feature extraction, as well as the successful recognition of commands for robot control using Linear Discriminant Analysis. The proposed method achieves an impressive average success rate of 95% for target reaching, making it suitable for the design of prosthetics in real-time rehabilitative platforms. © 2023 IEEE.

关键词： Electroencephalography Linear Discriminant Analysis OpenManipulatorX Phase-sensitive Common Spatial Pattern Rehabilitation

来源：评论

学校读者我要写书评

暂无评论

Designing an AI driven intelligent Tutorial System 5

Designing an AI driven intelligent Tutorial System

引用

5th IEEE International Conference on Recent Trends in computer Science and technology, ICRTCST 2024

作者： Alam, Shamsher Kumar, Surjeet Khursheed, Zeeshan Mahato, Hemant Kumar Bashar, Shadan Suman, Anjali R.V.S College of Engineering & Technology Computer Science and Engineering Jamshedpur India Government Engineering College Sheikhpura Computer Science and Engineering Bihar India Jio Platform Limited DGM Mumbai India NSHM Master of Computer Application Durgapur India R.V.S College of Engineering & Technology Master of Computer Application Jamshedpur India R.V.S College of Engineering & Technology Computer Science & Engineering Student Jamshedpur India

ISBN: (纸本)9798350351378

With the fast-evolving field of education, there is an increase in the demand for intelligent tutorial systems that can adapt to the diverse learning needs of individual students. This research paper explores the design and implementation of an AI-driven Intelligent Tutorial System (ITS) aimed at enhancing the personalized learning experience. The system leverages advanced machine learning algorithms to dynamically adjust instructional content, pace, and assessments based on real-time analysis of individual student performance and preferences. The paper delves into the key components of the proposed ITS, including adaptive learning models, natural language processing capabilities for interactive communication, and data-driven decision-making mechanisms. Emphasis is placed on the seamless integration of AI technologies to create an intuitive and responsive educational *** considerations in the development and deployment of the intelligent tutorial system are discussed, addressing issues related to data privacy, algorithmic bias, and the role of human oversight. The paper also highlights the collaborative potential between AI and human educators, emphasizing the system's capacity to support rather than replace teaching professionals. Through a combination of theoretical frameworks and practical examples, the research examines the potential impact of the AI-driven ITS on student engagement, learning outcomes, and the overall educational experience. Case studies and pilot implementations are presented to illustrate the system's efficacy in diverse educational *** research contributes to the ongoing discourse on AI in education by providing insights into the design principles, implementation challenges, and ethical considerations associated with developing an intelligent tutorial system. The findings aim to inform educators, policymakers, and technologists about the potential of AI to revolutionize personalized learning and contribute to the ong

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Developing Campus Digital Twin with Integrated 3D Point Clouds and 3D Modeling Techniques 6

Developing Campus Digital Twin with Integrated 3D Point Clou...

引用

6th International Conference on Cybernetics and Intelligent System, ICORIS 2024

作者： Utama, Ryan Nathan Sutjiatmadja, Jonathan Osmond, Fabrian Stefan, Lucas Gunawan, Alexander A.S. Chowanda, Andry Irwansyah, Edy Pramudya, Fabian Surya Game Application & Technology Department School of Computer Science Bina Nusantara University Jakarta11480 Indonesia Computer Science Department School of Computer Science Bina Nusantara University Jakarta11480 Indonesia

ISBN: (纸本)9798331539603

Exploring digital twin technology through the creation of 3D digital model offers a powerful tool for enhancing real-time monitoring, predictive analysis, and optimization of complex systems. The purpose of this study is to develop a 3D digital model of our building campus as the first step towards developing a digital twin of the university. In this study, we develop a digital model with integrated 3D point clouds and 3D modeling techniques. By scanning the physical model of the campus, data in the form of point clouds is extracted and unnecessary noise is deleted using Autodesk Recap Pro. These point clouds are used as a benchmark to ensure the 3D models created using Blender are as accurate as possible to the physical model. After successfully creating the digital model, several features/interactions are implemented using Unity to mimic the physical model, thus developing the digital twin. The digital twin of the campus will be used to develop a virtual tour of the campus. We concluded that the 3D digital model of the campus was successfully developed, despite the time-consuming nature of the process. We hope that this study serves as a reference to optimize and enhance digital twin development in the future. © 2024 IEEE.

关键词： Digital elevation model

来源：评论

学校读者我要写书评

暂无评论

A fast target depth perception method based on stereo structured light 9

A fast target depth perception method based on stereo struct...

引用

9th Symposium on Novel Photoelectronic Detection technology and applications

作者： Long, Zhixin Wang, Yuxuan Tang, Taoxin Wu, Jianguo Yu, Zemiao Wang, Hongyu Li, Dongxue School of Artificial Intelligence Shenyang University of Technology Shenyang China Beijing Institute of Computer Technology and Application Beijing100854 China

ISBN: (纸本)9781510664432

Structured light stereo vision depth perception is a key method in the fields of 3D contour reconstruction and human-computer interaction. To address the problem that the array-encoded raw image cannot be accurately localized due to artifacts when the target under test is moving rapidly, we propose a linear sparse depth perception method based on artifact analysis. Also, in order to effectively perceive the artefact parameters in motion, we design a heterogeneous coding model with grid line mode and array coding mode. To obtain the artifact width parameters of fast moving objects under binocular vision, the artifact parameters were obtained based on a gradient ridge extraction method. Finally, to obtain the artefact analysis function required for depth perception of fast moving targets, we used discrete artefact parameters to obtain a global artefact analysis function. Linear sparse depth information is obtained from the artifact parameter information in the binocular images, thus improving the speed and robustness of depth perception. © 2023 SPIE.

关键词： Stereo vision

来源：评论

学校读者我要写书评

暂无评论

Identification of Age, Plumage, and Sex of Bird Species Using Pre-Trained Deep Convolutional Neural Network 2

Identification of Age, Plumage, and Sex of Bird Species Usin...

引用

2nd IEEE International Conference on Intelligent and Innovative Technologies in Computing, Electrical and Electronics, ICIITCEE 2024

作者： Banerjee, Sourik Gupta, Richa Pandian, J. Arun Saranya, S. Mariappan, L. Thanga Vellore Institute of Technology Department of Computer Application Vellore India Vellore Institute of Technology School of Computer Science Engineering and Information Systems Vellore India K.Ramakrishnan College of Engineering Department of Computer Science and Engineering Tiruchirappalli India

ISBN: (纸本)9798350306415

The research aims to identify the age, plumage, and sex of bird species using standard Pre-trained Deep Convolutional Neural Networks (Pre-DCNNs). The proposed work involves collecting various bird images, which are then used for training and validating the pre-trained DCNNs. The dataset contains 200 images of four bird species. The dataset was split into twelve labeled classes of images based on age, plumage, and sex. The standard image manipulation techniques such as cropping, flipping, mirroring, rotating, shearing, and skewing were used as image augmentation techniques to increase the size of the proposed dataset. The proposed data is preprocessed, including feature extraction and data cleaning, to ensure the performance of the Pre-Trained DCNNs. The Pre-Trained DCNNs were trained on 90% of the dataset to recognize patterns in bird images. The accuracy of the pre-trained DCNNs was evaluated using metrics such as classification accuracy. The research acknowledged the advantages and limitations of the standard Pre-Trained DCNNs on the age, plumage, and sex of birds using the images. Also, it compares the performance of the Pre-Trained DCNNs on the proposed bird species image dataset. © 2024 IEEE.

关键词： Bird Plumage Identification Bird Species Identification Deep Convolutional Neural Networks Image Augmentation Pre-trained networks

来源：评论

学校读者我要写书评

暂无评论

Dual-Branch Subgraph-Pattern attention graph neural network for link prediction 4

Dual-Branch Subgraph-Pattern attention graph neural network ...

引用

4th International Conference on Advanced Algorithms and Neural Networks, AANN 2024

作者： Ouyang, Zhongxuan Wang, Jinhua Computer Application Technology Computing Platform Department China Electronics Technology Group Corporation No. 32 Research Institute East China Computing Technology Research Institute Shanghai China

ISBN: (纸本)9781510686106

Graph data is a natural form of unstructured data, with nodes and edges representing entities and the relationships between them respectively. This type of data can be directly applied to various real-world scenarios. Graph Neural Networks (GNNs) have a natural advantage in handling graph-structured data, effectively processing the hierarchical structure of graphs to extract rich information. However, current GNNs have limitations in dealing with local information. In this paper, we discover a new attention-based network module that outperforms general GNNs. To better learn global-local information and overall hierarchical information, we propose a Dual-Branch Subgraph Pattern Attention Graph Neural Network (DB-SP-GAT). Experimental results demonstrate that DB-SP-GAT achieves superior link prediction performance across five benchmark datasets. © 2024 SPIE.

关键词： Graph neural networks

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：