检索结果-内蒙古大学图书馆

IEEE International Conference on Data Science in Cyberspace (DSC)

作者： Weidong Shi Mingrui Fan Jiaqi Gao Jiahao Qi Daoqi Han Yueming Lu Key Laboratory of Trustworthy Distributed Computing and Service (BUPT) Ministry of Education School of Cyberspace Security The State Key Laboratory of Information Photonics and Optical Communications School of Information and Communication Engineering Beijing University of Posts and Telecommunications Beijing China

With the continuous expansion of network scale and increasing complexity, the application of the Internet of Things (IoT) is becoming more extensive. However, it is also vulnerable to various abnormal attacks, making security problems increasingly significant. Typically, traffic data dimensions are relatively large, and selecting features effectively is a key research issue. Addressing the aforementioned problems, this paper analyzes network traffic data and proposes a method(DOFS) to select the optimal feature subspace for different types of attacks, and verifies its effectiveness by comparative experiments. Then the T-S feature selection algorithm is improved, and DOFS is applied to the improved T-S feature selection algorithm, and the usability of the method is verified by experiments. By obtaining feature importance scores, the best feature subspace is selected for each type of traffic category. The method is verified using the network flow dataset CIC2018 and a real-world flow dataset. Experimental evaluations on diverse datasets demonstrate that the proposed method outperforms existing feature selection algorithms under different evaluation metrics, while exhibiting efficient time over-head and strong generalization ability. The results highlight the effectiveness and practicality of the proposed approach in IoT flow anomaly detection.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Research on the Electric Energy Metering Data Sharing Method in Smart Grid Based on Blockchain

引用

Journal on Big Data 2023年第1期5卷 57-67页

作者： Shaocheng Wu Honghao Liang Xiaowei Chen Tao Liu Junpeng Ru Qianhong Gong Jin Li Shenzhen Power Supply Co. Ltd.Shenzhen518001China School of Cyberspace Security Beijing University of Posts and TelecommunicationsBeijing100876China Key Laboratory of Trustworthy Distributed Computing and Service(BUPT) Beijing100876China

Enabling data sharing among smart grid power suppliers is a pressing challenge due to technical hurdles in verifying,storing,and synchronizing energy metering *** and sharing limitations are stringent for users,power companies,and researchers,demanding significant resources and time for permissions and *** paper proposes a blockchain-based architecture for secure and efficient sharing of electric energy metering ***,we propose a data sharing model based on evolutionary game *** on the Lyapunov stability theory,the model’s evolutionary stable strategy(ESS)is *** results verify the correctness and practicability of the scheme proposed in this paper,and provide a new method for realizing convenient,safe and fast data sharing.

关键词： Smart grid data sharing blockchain evolutionary stable strategy

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

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

引用

International Conference on Communication Technology (ICCT)

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

ISBN: (数字)9798350363760

ISBN: (纸本)9798350363777

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.

关键词： Adaptation models Translation Automation Accuracy 5G mobile communication Computational modeling Simulation Semantics Manuals Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Improving Chinese Spelling Check by Character Pronunciation Prediction: The Effects of Adaptivity and Granularity

Improving Chinese Spelling Check by Character Pronunciation ...

引用

2022 Conference on Empirical Methods in Natural Language Processing, EMNLP 2022

作者： Li, Jiahao Wang, Quan Mao, Zhendong Guo, Junbo Yang, Yanyan Zhang, Yongdong University of Science and Technology of China Hefei China MOE Key Laboratory of Trustworthy Distributed Computing and Service Beijing University of Posts and Telecommunications Beijing China People's Daily Online Co. Beijing China People's Public Security University of China Beijing China

Chinese spelling check (CSC) is a fundamental NLP task that detects and corrects spelling errors in Chinese texts. As most of these spelling errors are caused by phonetic similarity, effectively modeling the pronunciation of Chinese characters is a key factor for CSC. In this paper, we consider introducing an auxiliary task of Chinese pronunciation prediction (CPP) to improve CSC, and, for the first time, systematically discuss the adaptivity and granularity of this auxiliary task. We propose SCOPE which builds on top of a shared encoder two parallel decoders, one for the primary CSC task and the other for a fine-grained auxiliary CPP task, with a novel adaptive weighting scheme to balance the two tasks. In addition, we design a delicate iterative correction strategy for further improvements during inference. Empirical evaluation shows that SCOPE achieves new state-of-the-art on three CSC benchmarks, demonstrating the effectiveness and superiority of the auxiliary CPP task. Comprehensive ablation studies further verify the positive effects of adaptivity and granularity of the task. Code and data used in this paper are publicly available at https://***/jiahaozhenbang/SCOPE. © 2022 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Interpretable and Effective Reinforcement Learning for Attacking against Graph-based Rumor Detection

Interpretable and Effective Reinforcement Learning for Attac...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Yuefei Lyu Xiaoyu Yang Jiaxin Liu Sihong Xie Philip Yu Xi Zhang Key Laboratory of Trustworthy Distributed Computing and Service (BUPT) Ministry of Education Beijing University of Posts and Telecommunications Beijing China Lehigh University Bethlehem USA University of Illinois at Chicago Chicago USA

Social networks are frequently polluted by rumors, which can be detected by advanced models such as graph neural networks. However, the models are vulnerable to attacks, and discovering and understanding the vulnerabilities is critical to robust rumor detection. To discover subtle vulnerabilities, we design a attacking algorithm based on reinforcement learning to camouflage rumors against black-box detectors. We address exponentially large state spaces, high-order graph dependencies, and ranking dependencies, which are unique to the problem setting but fundamentally challenging for the state-of-the-art end-to-end approaches. We design domain-specific features that have causal effect on the reward, so that even a linear policy can arrive at powerful attacks with additional interpretability. To speed up policy optimization, we devise: (i) a credit assignment method that proportionally decomposes delayed and aggregated rewards to atomic attacking actions for enhance feature-reward associations; (ii) a time-dependent control variate to reduce prediction variance due to large state-action spaces and long attack horizon, based on reward variance analysis and a Bayesian analysis of the prediction distribution. On two real world datasets of rumor detection tasks, we demonstrate: (i) the effectiveness of the learned attacking policy on a wide spectrum of target models compared to both rule-based and end-to-end attacking approaches; (ii) the usefulness of the proposed credit assignment strategy and variance reduction components; (iii) the interpretability of the attacking policy.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Generalizing knowledge graph embedding with universal orthogonal parameterization 24

Generalizing knowledge graph embedding with universal orthog...

引用

Proceedings of the 41st International Conference on Machine Learning

作者： Rui Li Chaozhuo Li Yanming Shen Zeyu Zhang Xu Chen Gaoling School of Artificial Intelligence Renmin University of China Beijing China Key Laboratory of Trustworthy Distributed Computing and Service (MOE) Beijing University of Posts and Telecommunications China School of Computer Science and Technology Dalian University of Technology China

Recent advances in knowledge graph embedding (KGE) rely on Euclidean/hyperbolic orthogonal relation transformations to model intrinsic logical patterns and topological structures. However, existing approaches are confined to rigid relational orthogonalization with restricted dimension and homogeneous geometry, leading to deficient modeling capability. In this work, we move beyond these approaches in terms of both dimension and geometry by introducing a powerful framework named GoldE, which features a universal orthogonal parameterization based on a generalized form of Householder reflection. Such parameterization can naturally achieve dimensional extension and geometric unification with theoretical guarantees, enabling our framework to simultaneously capture crucial logical patterns and inherent topological heterogeneity of knowledge graphs. Empirically, GoldE achieves state-of-the-art performance on three standard benchmarks. Codes are available at https://***/xxrep/GoldE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Enhancement for Versatile Video Coding in Vehicular Ad Hoc Network Scenarios

Enhancement for Versatile Video Coding in Vehicular Ad Hoc N...

引用

International Symposium on Communications and Information Technologies (ISCIT)

作者： Jiacheng Wu Jiaqi Zou Songlin Sun School of Information and Communication Engineering Beijing University of Posts and Telecommunications (BUPT) Beijing China Key Laboratory of Trustworthy Distributed Computing and Service (BUPT) Ministry of Education China National Engineering Laboratory for Mobile Network Security Beijing University of Posts and Telecommunications Beijing China

ISBN: (数字)9798350353952

ISBN: (纸本)9798350353969

Vehicular Ad hoc Network (VANET) allows infor-mation exchange between vehicles. In VANET, video is the most recommended medium for transmitting information. However, the characteristics of VANET and the requirements of video content in terms of quality have resulted in various challenges. Besides, the movements of vehicles introduce complex motions in videos, making them more difficult to compress. As a result, it is a challenging task to transmit as less bits of video streams as possible while maintaining their visual quality. Therefore, we analyze Affine Motion Estimation (AME), a new coding tool in the latest generation video coding standard H.266NV C. Subsequently, a fast algorithm is proposed to make it able to describe complex motions such as rotation, zoom, shear, etc but also with low complexity. Experimental results show that the algorithm reduces the encoding complexity of AME by 20.19% and the overall encoding complexity by 3.25% compared to anchor VTM21.0, with eligible coding performance loss under Random Access (RA) configurations.

关键词： Video coding Visualization Motion estimation Vehicular ad hoc networks Streaming media Feature extraction Encoding Complexity theory Streams Standards

来源：评论

学校读者我要写书评

暂无评论

Cooperative Spectrum Sensing Based on Centralized Double Threshold in MCN

引用

China Communications 2020年第5期17卷 235-242页

作者： Hai Huang Junsheng Mu Xiaojun Jing School of Information and Communication Engineering Beijing University of Posts and TelecommunicationsBeijing 100876China Key Laboratory of Trustworthy Distributed Computing and Service Ministry of EducationBeijing 100876China

Cooperative spectrum sensing appears popular currently due to its ability to solve the issue of hidden terminal and improve detection performance in Cognitive Radio Networks. Meanwhile, double threshold based energy detector has attracted much attention for its low computational complexity and superior performance. Motivated by this, a cooperative spectrum sensing scheme is proposed in this paper based on centralized double threshold in the maritime communication networks(MCN), where the energy value of received signal in each cognitive node is forwarded to the fusion center for final decision based on double thresholds. Additionally, the proposed scheme is further optimized for the decisions that the energy is within the scope of maximum threshold and minimum threshold. Simulation experiments verify the performance of the proposed method.

关键词： cooperative spectrum sensing double threshold maritime communication network

来源：评论

学校读者我要写书评

暂无评论

A Lightweight and Robust Cross-Domain Authentication Scheme Based on Master-Slave Blockchain

A Lightweight and Robust Cross-Domain Authentication Scheme ...

引用

International Conference on Computer and Communications (ICCC)

作者： Kaiyang Deng Yali Gao Jie Yuan Zihan Hou Xiaoyong Li Key Laboratory of Trustworthy Distributed Computing and Service (BUPT) Ministry of Education College of Cyberspace Security Beijing University of Posts and Telecommunications Beijing China

In the era of network informatization, the Internet of Things has more and more complex requirements for information interaction across trust domains, and cross-domain identity authentication has become the focus of research and attention by security personnel. However, IoT devices often lack computing power and lack of security protection measures. The existing authentication schemes are complex and have poor robustness, which is not suitable for the IoT environment. to address this problem, this paper proposes a lightweight and robust cross-domain authentication scheme based on master-slave blockchain. Our method adopts the master-slave blockchain mode for cross-domain identity authentication, uses the trust evaluation mechanism to measure the reputation value of nodes, and selects nodes with high reputation values as cross-domain communication nodes. Experimental results show that our method is not only more robust than similar methods but also takes less time to complete the authentication.

关键词： Power measurement Authentication Computer architecture Main-secondary Robustness Blockchains Internet of Things

来源：评论

学校读者我要写书评

暂无评论

A DNS-based Data Exfiltration Traffic Detection Method for Unknown Samples 7

A DNS-based Data Exfiltration Traffic Detection Method for U...

引用

7th IEEE International Conference on Data Science in Cyberspace, DSC 2022

作者： Ruiling, Gan Jiawen, Diao Xiang, Cui Shouyou, Song QI-ANXIN Technology Group Beijing China Beijing University of Posts and Telecommunications Ministry of Education Key Laboratory of Trustworthy Distributed Computing and Service Beijing China Guangzhou University Cyberspace Institute Advanced Technology Guangzhou China Beijing DigApis Technology Co. Ltd Beijing China

ISBN: (数字)9781665474801

ISBN: (纸本)9781665474801

The advanced persistent threat (APT) is one of the most serious threats to cyberspace security. Posting back of exfiltrated data by way of DNS covert channels has become increasingly popular among APT attackers. Early detection techniques were mainly based on rule matching, whose accuracy may be affected by the subjectivity of the researchers. The rise of machine learning technology solves this problem. However, the current DNS traffic detection models based on machine learning lack the open-source datasets for training and they will lose detection accuracy for unknown malicious traffic whose abnormal points are different from the observed samples. As for the problem of insufficient data set, we propose a sample set enhancement method that simulating DNS attacks in the cyber range and using the captured flow as the training set. Regarding the detection of unknown malicious traffic, we put forward four new features (domain readability, domain structure, second-level domain phishing and IP discreteness) based on the principles for constructing malicious traffic. We use the decision tree algorithm to implement a detection model. In the unknown DNS data leakage traffic tests, our model achieved an average detection rate of 99.925%. After applying our sample set and feature set enhanced schemes to the existing work, the experimental results show that the enhanced detection model can detect unknown DNS data leakage traffic that could not be detected previously. © 2022 IEEE.

关键词： Decision trees

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：