检索结果-内蒙古大学图书馆

3rd International Conference on Algorithms, Microchips, and Network Applications, AMNA 2024

作者： Zhang, Mengyang Yuan, Kaiguo Li, Xiaoyong Key Laboratory of Trustworthy Distributed Computing and Service Beijing University of Posts and Telecommunications Beijing China

ISBN: (纸本)9781510680098

Most current network devices have multiple network interfaces, and multipath transport protocols can utilize multiple network paths (e.g., WiFi and cellular) to improve the performance and reliability of network transmission. The scheduler of the multipath transmission protocol determines the path to which each data packet should be transmitted, and is a key module that affects multipath transmission. However, current multipath schedulers cannot adapt well to various user usage scenarios. In this paper, we propose DRLMS, a deep reinforcement learning based multipath scheduler. DRLMS uses deep reinforcement learning to train neural networks to generate packet scheduling policies. It optimizes the scheduling strategy through feedback to the neural network through the reward function based on the current user usage scenario and QoS. We implement DRLMS in the MPQUIC protocol and compared it with current multipath schedulers. The results show that DRLMS's adaptability to user usage scenarios is significantly outperforms other schedulers. © 2024 SPIE.

关键词： Reinforcement learning

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

Zero-Shot Detection of LLM-Generated Text using Token Cohesi...

引用

2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024

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

ISBN: (纸本)9798891761643

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 Association for Computational Linguistics.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Robust Spatio-Temporal Trajectory Modeling Based on Auto-Gated Recurrent Unit 19

Robust Spatio-Temporal Trajectory Modeling Based on Auto-Gat...

引用

2022 IEEE SmartWorld, 19th IEEE International Conference on Ubiquitous Intelligence and computing, 2022 IEEE International Conference on Autonomous and Trusted Vehicles Conference, 22nd IEEE International Conference on Scalable computing and Communications, 2022 IEEE International Conference on Digital Twin, 8th IEEE International Conference on Privacy computing and 2022 IEEE International Conference on Metaverse, SmartWorld/UIC/ATC/ScalCom/DigitalTwin/PriComp/Metaverse 2022

作者： Jia, Jia Li, Xiaoyong Li, Ximing Li, Linghui Yuan, Jie Wang, Hongmiao Gao, Yali Qiu, Pengfei Tang, Jialu Beijing University of Posts and Telecommunications Key Laboratory of Trustworthy Distributed Computing and Service Beijing China

ISBN: (纸本)9798350346558

With the huge amount of crowd mobility data generated by the explosion of mobile devices, deep neural networks (DNNs) are applied to trajectory data mining and modeling, which make great progresses in those scenarios. However, recent studies have demonstrated that DNNs are highly vulnerable to adversarial examples which are crafted by adding subtle, imperceptible noise to normal examples, and leading to the wrong prediction with high confidence. To improve the robustness of modeling spatiotemporal trajectories via DNNs, we propose a collaborative learning model named 'Auto-GRU', which consists of an autoencoder-based self-representation network (SRN) for robust trajectory feature learning and gated recurrent unit (GRU)-based classification network which shares information with SRN for collaborative learning and strictly defending adversarial examples. Our proposed method performs well in defending both white and black box attacks, especially in black-box attacks, where the performance outperforms state-of-the-art methods. Moreover, extensive experiments on Geolife and Beijing taxi traces datasets demonstrate that the proposed model can improve the robustness against adversarial examples without a significant performance penalty on clean examples. © 2022 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

A Neural Network and Bloom Filter-Based Name Search Method in Named Data Networking 4

A Neural Network and Bloom Filter-Based Name Search Method i...

引用

4th International Conference on Neural Networks, Information and Communication Engineering, NNICE 2024

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

ISBN: (纸本)9798350394375

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. © 2024 IEEE.

关键词： Network architecture

来源：评论

学校读者我要写书评

暂无评论

Encrypted Traffic Classification Model Based on SwinT-CNN 4

Encrypted Traffic Classification Model Based on SwinT-CNN

引用

4th International Conference on Computer Engineering and Application, ICCEA 2023

作者： Wang, Yueyang Gao, Yali Li, Xiaoyong Yuan, Jie Beijing University of Posts and Telecommunications Key Laboratory of Trustworthy Distributed Computing and Service Beijing China

ISBN: (纸本)9798350347548

With the rapid development of the network, the proportion of encrypted traffic in the network is increasing, which brings great challenges to traffic classification. The traditional encrypted traffic classification algorithm extracts the port number of the traffic or the load information of the traffic packet for feature matching, which has no effect in the current encrypted traffic. The encrypted traffic classification algorithm based on machine learning especially relies on the features extracted by professionals for encrypted traffic, which is inefficient and has low accuracy. And, The accuracy and overall performance of existing deep learning methods also need to be improved. Therefore, in order to improve the accuracy of encrypted traffic classification, this paper proposes an encrypted traffic classification method based on deep learning, which tries to combine the core modules of CNN and Swin Transformer with the encrypted traffic classification model to realize the identification of the application type of encrypted traffic. Among them, the CNN module is able to capture the local spatial information characteristics of encrypted traffic data. The multi-head attention mechanism of Swin Transformer can capture global information about the association between attributes of the data. The model is tested on the public ISCX VPN-nonVPN encryption dataset to evaluate the performance of the proposed model. Experimental results show that the accuracy of our proposed model reaches 96.7%. Compared with the other best-performing deep learning models, the proposed model improves the accuracy by 3.1% and the F1 value by 2.7%. © 2023 IEEE.

关键词： Cryptography

来源：评论

学校读者我要写书评

暂无评论

An Intrusion Detection Method Based on Transformer-LSTM Model 3

An Intrusion Detection Method Based on Transformer-LSTM Mode...

引用

3rd International Conference on Neural Networks, Information and Communication Engineering, NNICE 2023

作者： Zhang, Zhipeng Si, Xiaotian Li, Linghui Gao, Yali Li, Xiaoyong Yuan, Jie Xing, Guoqiang Beijing University of Posts and Telecommunications Key Laboratory of Trustworthy Distributed Computing and Service Beijing China

ISBN: (纸本)9798350335972

With the development of network technologies, network intrusion has become increasing complex which makes the intrusion detection challenging. Traditional intrusion detection algorithms detect intrusion traffic through intrusion traffic characteristics or machine learning. These methods are inefficient due to the dependence of manual work. Therefore, in order to improve the efficiency and the accuracy, we propose an intrusion detection method based on deep learning. We integrate the Transformer and LSTM module with intrusion detection model to automatically detect network intrusion. The Transformer and LSTM can capture the temporal information of the traffic data which benefits to distinguish the abnormal data from normal data. We conduct experiments on the publicly available NSL-KDD dataset to evaluate the performance of our proposed model. The experimental results show that the proposed model outperforms other deep learning based models. © 2023 IEEE.

关键词： Intrusion detection

来源：评论

学校读者我要写书评

暂无评论

Real Time Attrition Prediction Mechanism Based on Deep Learning 2

Real Time Attrition Prediction Mechanism Based on Deep Learn...

引用

2nd International Signal Processing, Communications and Engineering Management Conference, ISPCEM 2022

作者： Wu, Chen Beijing University of Posts and Telecommunications Key Laboratory of Trustworthy Distributed Computing and Service Beijing China

ISBN: (纸本)9781665492713

Modern companies mostly have their own employee management systems, which retain a large amount of employee behavior data. These data can be used to mine valuable information, such as whether employees have attrition intentions. This paper proposes a mechanism of attrition prediction based on deep learning, which mainly includes three modules: (1) Using LSTM to build a performance-attrition pre-trained model;(2)Using Transformer to build a sentiment tendency model based on employee weekly reports;(3) Based on (1), (2), establishing Real Time Attrition Prediction Mechanism in the company's employee management system to predict employees' willingness to leave at any time. The purpose of this mechanism is to help companies manage better and reduce losses caused by employee attrition. © 2022 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

RDI: An adversarial robustness evaluation metric for deep neural networks based on sample clustering features

arXiv

引用

arXiv 2025年

作者： Song, Jialei Zuo, Xingquan Wang, Feiyang Huang, Hai Zhang, Tianle Shool of Computer Science Beijing University of Posts and Telecommunications Beijing China Key Laboratory of Trustworthy Distributed Computing and Service Ministry of Education Beijing China Shool of Cyberspace Security Beijing University of Posts and Telecommunications Beijing China

Deep neural networks (DNNs) are highly susceptible to adversarial samples, raising concerns about their reliability in safety-critical tasks. Currently, methods of evaluating adversarial robustness are primarily categorized into attack-based and certified robustness evaluation approaches. The former not only relies on specific attack algorithms but also is highly time-consuming, while the latter due to its analytical nature, is typically difficult to implement for large and complex models. A few studies evaluate model robustness based on the model’s decision boundary, but they suffer from low evaluation accuracy. To address the aforementioned issues, we propose a novel adversarial robustness evaluation metric, Robustness Difference Index (RDI), which is based on sample clustering features. RDI draws inspiration from clustering evaluation by analyzing the intra-class and inter-class distances of feature vectors separated by the decision boundary to quantify model robustness. It is attack-independent and has high computational efficiency. Experiments show that, RDI demonstrates a stronger correlation with the gold-standard adversarial robustness metric of attack success rate (ASR). The average computation time of RDI is only 1/30 of the evaluation method based on the PGD attack. Our open-source code is available at: https://***/r/RDI-B1DA. Copyright © 2025, The Authors. All rights reserved.

关键词： Open systems

来源：评论

学校读者我要写书评

暂无评论

An Effective Cloud Workflow Scheduling Approach Combining PSO and Idle Time Slot-Aware Rules

引用

IEEE/CAA Journal of Automatica Sinica 2021年第5期8卷 1079-1094页

作者： Yun Wang Xingquan Zuo the School of Computing Science Beijing University of Posts and TelecommunicationsBeijing 100876China the School of Information Engineering Nanchang Institute of TechnologyNanchang 330099China the Key Laboratory of Trustworthy Distributed Computing and Service(BUPT) Ministry of EducationBeijing 100876China

Workflow scheduling is a key issue and remains a challenging problem in cloud *** with the large number of virtual machine(VM)types offered by cloud providers,cloud users need to choose the most appropriate VM type for each *** task scheduling sequences exist in a workflow *** task scheduling sequences have a significant impact on the scheduling *** is not easy to determine the most appropriate set of VM types for tasks and the best task scheduling ***,the idle time slots on VM instances should be used fully to increase resources'utilization and save the execution cost of a *** paper considers these three aspects simultaneously and proposes a cloud workflow scheduling approach which combines particle swarm optimization(PSO)and idle time slot-aware rules,to minimize the execution cost of a workflow application under a deadline constraint.A new particle encoding is devised to represent the VM type required by each task and the scheduling sequence of *** idle time slot-aware decoding procedure is proposed to decode a particle into a scheduling *** handle tasks'invalid priorities caused by the randomness of PSO,a repair method is used to repair those priorities to produce valid task scheduling *** proposed approach is compared with state-of-the-art cloud workflow scheduling *** show that the proposed approach outperforms the comparative algorithms in terms of both of the execution cost and the success rate in meeting the deadline.

关键词： Cloud computing idle time slot particle swarm optimization task scheduling sequence workflow scheduling

来源：评论

学校读者我要写书评

暂无评论

Pulmonary tuberculosis detection model of chest X-ray images using convolutional neural network

引用

The Journal of China Universities of Posts and Telecommunications 2018年第6期25卷 1-6页

作者： He Jin Wang Cong Chen Zhao School of Software Engineering Beijing University of Posts and Telecommunications Key Laboratory of Trustworthy Distributed Computing and Service(BUPT) Ministry of Education China Electronic Data Service CO. LTD

The primary screening for pulmonary tuberculosis mainly relies on X-ray imaging all over the world. In recent years, the incidence of pulmonary tuberculosis has rebounded. This paper proposes a convolutional neural networks(CNN) based model on the tuberculosis detection of chest X-ray images, which is used for the automatic screening of pulmonary tuberculosis. Compared with the conventional CNN, this model can be used to detect the details of images and the areas of the disease quickly and accurately. There is an improvement in the learning speed and accuracy rate of our method, so it can better complete the work of anomaly detection and it can provide more effective auxiliary decision information for the practitioners.

关键词： X-ray images pulmonary tuberculosis CNN automatic screening

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：