检索结果-内蒙古大学图书馆

Neural Networks, Information and Communication Engineering (NNICE), International Conference on

作者： Yue Liu Xiaoyong Li Xiaotian Si Mengyang Zhang Kaiguo Yuan Pengcheng Li Key Laboratory of Trustworthy Distributed Computing and Service Beijing University of Posts and Telecommunications Beijing China

In a new network architecture like NDN, designing an efficient name lookup method has always been a valuable challenge. The paper studies the name lookup technology based on the Bloom filter and BPNN neural network mapping model in named data networking. In the part of the hybrid model based on the Bloom filter and BPNN, the paper proposes the fusion idea of the Bloom filter and BPNN, and provides a detailed introduction to the construction process of the hybrid model. At the same time, in order to improve the memory utilization of traditional Bloom filters, this article proposes a way to use neural networks to enhance it, and proved its effectiveness through experiments.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Zero-Shot Detection of LLM-Generated Text using Token Cohesiveness

arXiv

引用

arXiv 2024年

作者： Ma, Shixuan Wang, Quan MOE Key Laboratory of Trustworthy Distributed Computing and Service Beijing University of Posts and Telecommunications China

The increasing capability and widespread usage of large language models (LLMs) highlight the desirability of automatic detection of LLM-generated text. Zero-shot detectors, due to their training-free nature, have received considerable attention and notable success. In this paper, we identify a new feature, token cohesiveness, that is useful for zero-shot detection, and we demonstrate that LLM-generated text tends to exhibit higher token cohesiveness than human-written text. Based on this observation, we devise TOCSIN, a generic dual-channel detection paradigm that uses token cohesiveness as a plug-and-play module to improve existing zero-shot detectors. To calculate token cohesiveness, TOCSIN only requires a few rounds of random token deletion and semantic difference measurement, making it particularly suitable for a practical black-box setting where the source model used for generation is not accessible. Extensive experiments with four state-of-the-art base detectors on various datasets, source models, and evaluation settings demonstrate the effectiveness and generality of the proposed approach. Code available at: https://***/Shixuan-Ma/TOCSIN. © 2024, CC BY-NC-ND.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

The Construction and Application of Work and Production Resuming Behavior System Dynamics Evolutionary Game Regulation and Control Model

引用

Journal of Systems Science and Information 2023年第2期11卷 160-178页

作者： Qiao HU Jiayin QI School of Business and Management Shanghai International Studies UniversityShanghai 201620China School of Cyberspace Security Guangzhou UniversityGuangzhou 510006ChinaKey Laboratory of Trustworthy Distributed Computing and Service(BUPT)Ministry of EducationBeijing 100084China

The resumption of production after the“suspension”caused by the COVID-19 has emerged as an urgent problem for many enterprises and the *** resumption of production is actually a dynamic evolution problem from 0 to 1(100%).This paper constructs a general game model and a dynamic replication system for the resumption of production and government support,and gives theorems for the construction of the *** analyzes the evolution mechanism and scenario conditions for the convergence of enterprise strategies to the“resumption of production”strategy,takes the resumption of production of hog farmers as an example to carry out a study on the regulation of countermeasures to resume hog production,and explores systemic countermeasures and suggestions for the rapid convergence of farmers’strategies to the“resumption of work and production”*** study found that the production resuming behavior system dynamics evolution game regulation model provides a systematic model and method for the study of resumption countermeasures,a general regulation model for the resumption ratio from 0 to 1(100%),and a systematic idea,method and model for exploring the“precise strategy”system to promote the rapid resumption of production.

关键词： the resumption of production system dynamics evolutionary game regulation and control model simulation

来源：评论

学校读者我要写书评

暂无评论

A Novel Color Image Encryption based on Chaos and DNA Mutation

A Novel Color Image Encryption based on Chaos and DNA Mutati...

引用

IEEE International Conference on Signal and Image Processing (ICSIP)

作者： Mingliang Sun Jie Yuan Xiaoyong Li Dongxiao Liu Xinghai Wei Key Laboratory of Trustworthy Distributed Computing and Service (BUPT) Beijing University of Posts and Telecommunications Beijing China

ISBN: (数字)9798350350920

ISBN: (纸本)9798350350937

The security of the color images is challenged by the illegal copying and distribution over various communication networks. This work proposed a novel color image encryption scheme based on the chaos and Deoxyribonucleic acid (DNA). Firstly, A novel four dimensions chaotic system is constructed and analyzed. Secondly, the DNA coding rules are controlled by the chaos-based pseudorandom sequence to substitute the image pixels. The column and row rotation are designed to disturb the image pixels. Finally, The DNA matrix coded from the color image is divided into blocks to implement the XOR and addition operation with the pseudorandom sequence. Its security is simulated and compared with other schemes. The comparison show that the proposed scheme has a higher key sensitivity, lower correlation of adjacent pixels, and higher NPCR and information entropy. Therefore, the proposed image encryption scheme is more capable against statical attacks and efficiency while keeping high robustness.

关键词： Sensitivity Image coding Chaotic communication DNA Color Robustness Matrices

来源：评论

学校读者我要写书评

暂无评论

Knowledge-Enabled Intent-Driven Network Configuration Generation for 5G Core Networks 24

Knowledge-Enabled Intent-Driven Network Configuration Genera...

引用

24th IEEE International Conference on Communication Technology, ICCT 2024

作者： Li, Qiuying Cai, Jiajun Xu, Ji'ang Liu, Ruosi Yuan, Caixia Gao, Hui Beijing University of Posts and Telecommunications Key Laboratory of Trustworthy Distributed Computing and Service Moe Beijing China Beijing University of Posts and Telecommunications School of Artificial Intelligence Beijing China Bantian Industrial Base Huawei Technoligies Shenzhen China

ISBN: (纸本)9798350363760

Automating the configuration of 5G core networks (CNs) is crucial for meeting increasingly diverse and specialized application requirements. In this paper, we propose an intent-driven automation model for configuring 5G CNs. Our approach leverages existing 5G CN equipment manuals and extracts the underlying configuration knowledge to enable intent translation. Unlike traditional methods, the proposed model employs a knowledge fusion approach that computes the semantic correlation between user intents and equipment configuration commands. Specifically, the proposed model integrates graph neural networks and pre-trained language models, exhibiting strong reasoning capabilities. Moreover, by converting complex texts into structured knowledge graphs, the proposed model provides precise command suggestions, significantly enhancing the degree of automation in 5G CN configurations. Simulation results show that the generated commands achieve high accuracy across various scenarios, validating the effectiveness of our approach. © 2024 IEEE.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Reliability Measurement Of Vehicle Sensor Data Based On Historical Perception

Reliability Measurement Of Vehicle Sensor Data Based On Hist...

引用

IEEE International Conference on Data Science in Cyberspace (DSC)

作者： Chenqing Guo Jinxin Zuo Yueming Lu Weixuan Xie School of Cyberspace Security Key Lab of Trustworthy Distributed Computing and Service Ministry of Education Beijing University of Posts and Telecommunications Beijing China

ISBN: (数字)9798350391367

ISBN: (纸本)9798350391374

On-board sensors are utilized for monitoring and collecting a diverse range of data pertaining to the vehicle and its surroundings. However, in the field of Internet of Vehicles, security threats encountered by vehicle sensors often result in compromised accuracy of collected data. Therefore, it is crucial to investigate trusted measurement methods for vehicle sensor data. This paper proposes a reliable measurement approach for vehicle sensor data based on historical perception. The method initially achieves historical feature extraction through time correlation of single sensor sequence data and spatial correlation of multisensor data. Subsequently, a reliability measurement method is devised to quantify real-time data reliability by assessing the deviation from the theoretical expected value. Finally, historical data reliability is integrated with real-time data reliability to enhance accuracy of the overall reliability measurement process. This approach takes into consideration spatio-temporal correlation of vehicle sensor data and resolves issues stemming from unbalanced datasets that lead to inaccurate evaluation results. Experimental findings demonstrate an accuracy rate of 98.91% for the proposed method.

关键词： Correlation Accuracy Reliability theory Feature extraction Real-time systems Spatial databases Sensors Security Monitoring Internet of Vehicles

来源：评论

学校读者我要写书评

暂无评论

Modification Method for Internal Network Flow Anomaly Detection Based on Multi-timescale Analysis

Modification Method for Internal Network Flow Anomaly Detect...

引用

IEEE International Conference on Data Science in Cyberspace (DSC)

作者： Xinyu Zhang Junmei Ding Yueming Lu Key Laboratory of Trustworthy Distributed Computing and Service Ministry of Education Beijing University of Posts and Telecommunications Beijing China

ISBN: (数字)9798350391367

ISBN: (纸本)9798350391374

With the continuous development of information technology, security issues from internal networks are becoming more and more important. Many anomaly detection algorithms are designed to identify anomalies, but these algorithms usually do not care about temporal information, or only care about fine-grained temporal information. On the other hand, deep-learning-based algorithms must rely on complex neural networks to capture temporal information, which is difficult to deploy and maintain in actual internal network environments. Addressing the aforementioned problems, this paper proposes a multi-timescale analyzer using wavelet packet transform and semi-supervised learning, and a method that uses the analyzer to modify the original anomaly scores called Multi-timescale Modification (MTM) method. The method is validated using the network flow dataset CIC-IDS 2017 and a real-world dataset. Experimental evaluations show that using the proposed method can obtain better performance than the original algorithms.

关键词： Hands Neural networks Cyberspace Semisupervised learning Data science Wavelet analysis Wavelet packets Security Information technology Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Generating a Personalised Sensor Data Generation System for the Fusion of Adversarial Networks and Behavioural Matter-of-Fact Mapping 8th

Generating a Personalised Sensor Data Generation System for ...

引用

8th EAI International Conference on Machine Learning and Intelligent Communications, MLICOM 2023

作者： Cao, Jingge Sun, Lijuan Wu, Jingchen Zhang, Xiujian Wu, Xu Key Laboratory of Trustworthy Distributed Computing and Service Ministry of Education Beijing China School of Cyberspace Security BUPT Beijing China Key Laboratory of Artificial Intelligence Measurement and Standards for State Market Regulation Beijing Aerospace Institute for Metrology and Measurement Technology Beijing100076 China

ISBN: (纸本)9783031717154

Generative models such as Generative Adversarial Networks and Variational Self-Encoders have been shown to generate highly simulated synthetic data with incredible results in areas such as text, images, and audio. However, to date there is no proven method for generating sensor data for mobile terminals. This is because sensor-generated data is high-dimensional, high-complexity, and contains a lot of noise and variations, which makes it difficult for generative models to learn realistic distributions from this data. In addition, different users acquiring sensor data for the same action will also have different features, which makes it more challenging to generate fine-grained sensor data. In order to solve the above problems, we propose a personalised sensor data generation system for fusion of generative adversarial networks and behavioural matter-of-fact mapping, which creatively introduces matter-of-fact mapping and aims to reduce the probability of occurrence of situations that do not conform to the matter-of-fact logic in the personalised sensor data set by utilising matter-of-fact logic and temporal relationships originated from matter-of-fact mapping, and thus improve the accuracy of user behavioural sensor data generation. The results demonstrate that the sensor data generated by the method proposed in this paper achieves 90% accuracy under the behavioural action recognition task and generates personalised sensor data for a long period of time through the designed state transfer template. © ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering 2024.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

An AdamW-Based Deep Neural Network Using Feature Selection and Data Oversampling for Intrusion Detection

An AdamW-Based Deep Neural Network Using Feature Selection a...

引用

IEEE International Conference on Data Science in Cyberspace (DSC)

作者： Zhuoer Lu Xiaoyong Li Pengfei Qiu Key Laboratory of Trustworthy Distributed Computing and Service (BUPT) Ministry of Education Beijing China

With the development of the Internet and the increasing number of Internet users, cyber security has become a major concern for most netizens. In this paper, we propose an AdamW-based neural network using feature selection and data oversampling for intrusion detection. First, we use the Random Forest classifier to select the 25 most important features for classifying network traffic. Second, given the imbalance of different types of samples in the NSL-KDD dataset, we use ADASYN oversampling to oversample the minority samples. In addition, to achieve better performance, we use AdamW as the optimizer of our deep neural network. Finally, we tune the hyperparameters of our deep neural network to get the best classification results for intrusion detection. Compared with other classical machine learning models for intrusion detection, our deep neural network achieves high intrusion detection performance: the test set loss is reduced to 0.0001 and the test set accuracy is improved to 99.8%.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Practical YOLOV5 Face Detector with Decoupled Swin Head

A Practical YOLOV5 Face Detector with Decoupled Swin Head

引用

2023 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2023

作者： Yuan, Shuozhi Guo, Wenming Yang, Feng Beijing University of Posts and Telecommunications Key Laboratory of Trustworthy Distributed Computing and Service Beijing China Beijing University of Posts and Telecommunications Xinjiang Institute of Engineering Beijing China Xinjiang Institute of Engineering Urumqi China

ISBN: (纸本)9798350337020

Face detection is a fundamental and practical problem in computer vision, which aims to indicate the face positions in a wild environment precisely. However, different from the generic object detection tasks, there are a large number of face samples that suffer from unconstrained poses, occlusion, extreame lights, or other harmful conditions. YOLOV5 is an incredible milestone in the object detection area, but still not powerful enough for the challenging samples. To ease these difficulties, in this paper, we customize DSH-YOLOV5, a practical face detector. Specifically, we integrate a decoupled head with swin transformer layers, whose self-attention mechanism has great potential to explore subtle interconnection details. Additionally, we use two context modules (CBAM and SSH) to enhance the performance of features. Furthermore, we design a novel copy-paste data augmentation to fit the above challenging scenes. Extensive experiments demonstrate that we achieve SOTA performance on WIDER FACE, FDDB, and PASCAL FACE with competitive computational costs. Moreover, under COVID-19, we add the breathing mask and gender classification branches based on the ROI Align to produce more practical face information. © 2023 IEEE.

关键词： Face Detection Swin-Transformer YOLOV5

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：