检索结果-内蒙古大学图书馆

Multimodal misinformation detection based on the multi-granularity consistency

Neurocomputing 2025年 644卷

作者： Zhang, Shibo Chen, Hongchang Liu, Shuxin Li, ran Jiang, HaoCong dong, Liang Institute of Information Technology PLA Information Engineering University Henan Zheng Zhou450002 China National Digital Switching System Engineering and Technological R&D Center Henan Zheng Zhou450002 China

In the current era of information proliferation, social media platforms frequently present multimodal data that may propagate misinformation. To address this challenge, computer vision techniques have been increasingly applied to online misinformation detection. Existing approaches often concentrate on learning deep semantic features from text and images without sufficiently exploring coherent alignments across multiple granular levels. This could hinder the construction of a comprehensive multimodal detection framework for misinformation detection. To overcome these issues, in this paper, we propose a three-level granularity consistency detection framework that explores image-text alignments at fine-grained, medium-grained, and coarse-grained levels. Meanwhile, we delve into the hierarchical structures of two modalities as well as the intricate semantic relationships between them. Specifically, our framework models token-level consistency through a multi-head cross-attention mechanism, phrase-level consistency via a graph neural network (GNN), and global-level consistency using a contrastive language-image pre-training model (CLIP), respectively. An adaptive fusion module then integrates these consistency features across all three granularities, enabling more nuanced and robust multimodal misinformation detection. Extensive experiments conducted on multiple benchmark datasets demonstrate that our approach substantially improves the performance of multimodal misinformation detection. © 2025

关键词： Tweets

来源：评论

学校读者我要写书评

暂无评论

A Security Survey of NFV: From Causes to Practices 3

A Security Survey of NFV: From Causes to Practices

引用

3rd International Conference on Consumer Electronics and Computer engineering, ICCECE 2023

作者： He, Gang Liao, Xingxing Liu, Caixia School of Cyber Science and Engineering Southeast University Nanjing211189 China Purple Mountain Laboratories Nanjing211100 China National Digital Switching System Engineering and Technological R and D Center Zhengzhou450002 China Academy of Military Sciences Institute of System Engineering Beijing100091 China

ISBN: (纸本)9798350331578

Network Function Virtualization (NFV) is proposed as new technology to address massive proprietary devices, high operation costs, poor flexibility and other problems in current traditional network. By separating network functions and proprietary devices, NFV can significantly reduce operation costs and enable flexible configuration of services, etc. Now NFV is widely used in various fields. However, due to virtualization and softwareization and other technical characteristics, NFV faces more serious security threats compared to traditional networks. This paper focuses on analyzing the NFV security threats under the new technology and summarizes them according to the causes of security threats. Subsequently, based on the results of the analysis, we propose the corresponding safety practice solutions. Finally, we prospect the research directions for improving NFV security. © 2023 IEEE.

关键词： Network function virtualization

来源：评论

学校读者我要写书评

暂无评论

Altair: resource-Efficient Optimization and deployment for data Plane Programs

SSRN

引用

SSrN 2024年

作者： Cui, Zixi Hu, Yuxiang Tian, Le Yi, Peng Hou, Saifeng Chen, Hongchang PLA Strategic Support Force Information Engineering University Zhengzhou450001 China National Digital Switching System Engineering and Technological R&D Center Zhengzhou450001 China

As network applications are increasingly offloaded to the programmable switches, program fitting problems come to the fore, which means effectively mapping the programming entities into the hardware resources. However, existing works fail to achieve resource-efficient deployment in an acceptable time. In this paper, we present Altair, a high-performance compiler system for program optimization and resource allocation. In addition to proactively optimizing the program by reducing logical redundancy, Altair designs a two-layer framework to generate the optimal mapping solutions with respect to all the hardware constraints while minimizing resource usage. We also propose a new feedback mechanism between the two layers to make the best trade-offs among bottleneck resources and accelerate the solving process. Altair not only converts the network program into a functionally identical and compilable codes, but also uses up to 30% fewer hardware resources with at least 10X shorter execution time than state-of-the-art. © 2024, The Authors. All rights reserved.

关键词： resource allocation

来源：评论

学校读者我要写书评

暂无评论

Altair: resource-Efficient Optimization and deployment for data Plane Programs

SSRN

引用

SSrN 2024年

As network applications are increasingly offloaded to the programmable switches, program fitting problems come to the fore, which means effectively mapping the programming entities into the hardware resources. However, existing works fail to achieve resource-efficient deployment in an acceptable time. In this paper, we present Altair, a high-performance compiler system for program optimization and resource allocation. In addition to proactively optimizing the program by reducing logical redundancy, Altair designs a two-layer framework to generate the optimal mapping solutions with respect to all the hardware constraints while minimizing resource usage. We also propose a novel feedback mechanism between the two layers to make the best trade-offs among bottleneck resources and accelerate the solving process. Altair not only converts the network program into a functionally identical and compilable codes, but also uses up to 30% fewer hardware resources with at least 10X shorter execution time than state-of-the-art. © 2024, The Authors. All rights reserved.

关键词： resource allocation

来源：评论

学校读者我要写书评

暂无评论

Virtual Network Function resource requirements Prediction Model Based on CNN-GrU 22

Virtual Network Function Resource Requirements Prediction Mo...

引用

Proceedings of the 2022 6th International Conference on Electronic Information technology and Computer engineering

作者： Chunqiao Mao Peng Yi dan Li Juan Shen School of Cyber Science and Engineering Zhengzhou University China National Digital Switching System Engineering & Technological R&D Center of China China

ISBN: (纸本)9781450397148

The rise of network function virtualization (NFV) technology makes the realization of network function change from hardware middleware to virtual network function (VNF). The existing methods allocate fixed resources to each VNF instance, but this resource allocation method will cause resource waste, which will affect the quality of service. The resource requirements prediction model solves the resource allocation problem by predicting the change of resource requirements. In this paper, deep learning is used to solve the regression prediction problem, and a VNF resource requirements prediction model based on convolutional neural network (CNN) and gated recurrent unit (GrU) is proposed. Compared with other single model and combined model, the experimental results show that the prediction error rate of the proposed model is reduced by 23.3%.

关键词： resource requirements prediction Virtual network function Convolutional neural network Gated circulation unit

来源：评论

学校读者我要写书评

暂无评论

downlink MMSE Beamforming for dynamic Metasurface Antennas

Downlink MMSE Beamforming for Dynamic Metasurface Antennas

引用

Electronic Information engineering and Computer Science (EIECS), 2021 International Conference on

作者： Zhiqiang Han Shuming Guo Shifei Wang School of Cyber Science and Engineering Zhengzhou University Zhengzhou China National Digital Switching System Engineering & Technological R&D Center Zhengzhou China

dynamic metasurface antenna (dMA) array is a new type of array structure with low complexity and low cost, which is emerging as a promising technique for next-generation wireless networks. In this paper, a downlink multi-user MISO system based on dMA arrays is investigated, and the mean square error (MSE) is chosen as a performance metric to characterize the transmission reliability. The beamforming performance of dMA arrays is investigated using the minimum mean square error (MMSE) criterion. For the multiuser scenario, the optimization problem minimizes MSE by jointly optimizing the transmit precoder and dMA weights while satisfying the transmit power constraint. Our numerical results show that the proposed MMSE scheme converges fast and performs close to full digital beamforming.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A comprehensive evaluation of diversity systems based on mimic defense

引用

Science China(Information Sciences) 2021年第12期64卷 258-259页

作者： Qing TONG Yunfei GUO National Digital Switching System Engineering and Technological R&D Center

dear editor,diversity systems increase attacking challenges through mechanisms such as system diversification design, redundancy, or dynamic rotation. They resist various external threats, including the unknown attacks on the system. Several research studies have been conducted to analyze and validate the security and effectiveness of diversity systems,

关键词： Information systems and Communication Service

来源：评论

学校读者我要写书评

暂无评论

distributed Mimic Judgment Algorithm based on Multi-Strategy decentralization Model 22

Distributed Mimic Judgment Algorithm based on Multi-Strategy...

引用

7th International Conference on Cyber Security and Information engineering, ICCSIE 2022

作者： Song, Yu Sun, He Wang, Jiaxing Liu, Wenhe Zhang, Jianhui School of Information Engineering Zhengzhou University Zhengzhou China School of Cyber Science and Engineering Zhengzhou University Zhengzhou China National Digital Switching System Engineering & Technological R&D Centerr Zhengzhou China

ISBN: (纸本)9781450397414

The current mimic adjudication model is centered on a single adjudicator, and the adjudication algorithm is relatively single and static, which cannot cope with today's complex and changeable network environment. First, a distributed adjudication model is proposed to decentralize the adjudicator, each sub-arbiter is different from the previous use of all executive results, but randomly selects the output of the executive as the input incentive. Secondly, based on this model, a consensus mechanism algorithm is proposed to iteratively normalize the local adjudication results of the sub-arbiters to achieve the global optimal adjudication result. The analysis of the simulation experiment results shows that the algorithm proposed in this paper is more accurate than the traditional adjudication algorithm when multiple executors are online. The algorithm can further reduce the risk of common-mode escape and improve the security of the mimic defense system. © 2022 ACM.

关键词： Network security

来源：评论

学校读者我要写书评

暂无评论

A BErT-GCN-Based detection Method for FBS Telecom Fraud Chinese SMS Texts

A BERT-GCN-Based Detection Method for FBS Telecom Fraud Chin...

引用

Intelligent Computing and Human-Computer Interaction (ICHCI), International Conference on

作者： Xuanming Zhang ruiyang Huang Lixiao Jin Fangjie Wan School of Cyber Science and Engineering Zhengzhou University Zhengzhou China National Digital Switching System Engineering & Technological R&D Center Zhengzhou China

In the past decade, Fake Base Stations (FBS) have been consistently employed by criminals to target mobile users through spam text messages. despite the introduction of several techniques to mitigate this problem, spam messages remain a persistent and challenging issue in some countries, such as China, resulting in billions of dollars in annual economic losses. Therefore, this paper proposes an algorithm named BErT-GCN that combines large-scale pre-training models with Graph Convolutional Networks (GCN) for multi-class detection of fraudulent base station telecommunications scams in Chinese text messages. First, BErT (Bidirectional Encoder representation from Transformers) is used to encode the corpus and generate word embeddings. Subsequently, the generated word embeddings are fed into GCN for training. Finally, a Softmax layer is employed to perform multi-class detection on fraudulent base station telecommunications scams in Chinese text messages. Experimental results demonstrate that the proposed model achieves favorable performance on the FBS-SMS-dataset and exhibits outstanding performance in the domain of multi-class detection.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Malicious Website detection Method Based on BGresNet Multi-feature Fusion

Malicious Website Detection Method Based on BGResNet Multi-f...

引用

IEEE Eurasia Conference on IOT, Communication and engineering (ECICE)

作者： Lixiao Jin ruiyang Huang Xuanming Zhang School of Cyber Science and Engineering Zhengzhou University Zhengzhou China National Digital Switching System Engineering & Technological R&D Center Zhengzhou China

Website security detection is important for Internet security. Existing machine learning-based malicious UrL detection methods have a low accuracy and weak generalization ability. Thus, we proposed a new multi-feature fusion malicious website detection model BGresNet by integrating the advantages of Bidirectional Encoder representations from Transformers (BErT), Graph Convolutional Network (GCN), and residual neural network (resNet). The method integrates three features: Uniform resource Locator (UrL) creator, rule features, and website titles. First, we used BGresNet to process UrL characters and website titles separately, transforming them into vector representations. Then, these two vectors were fused with UrL rule vectors. Finally, we employed the softmax function to realize the detection of malicious websites. The experimental results showed that the proposed model exhibited significant superiority in detecting malicious websites, providing a new and effective method for malicious UrL detection in Internet security.

关键词：

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：