检索结果-内蒙古大学图书馆

IEEE Transactions on Artificial Intelligence 2024年第12期5卷 6369-6384页

作者： Wang, Xiuhua Wang, Shuai Li, Yiwei Fan, Fengrui Li, Shikang Lin, Xiaodong Huazhong University of Science and Technology Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Wuhan430074 China University of Electronic Science and Technology of China National Key Laboratory of Wireless Communications Chengdu611731 China Xiamen University of Technology Fujian Key Laboratory of Communication Network and Information Processing Xiamen361024 China University of Guelph School of Computer Science GuelphONN1G 2W1 Canada

Federated learning (FL) is a popular distributed paradigm where enormous clients collaboratively train a machine learning (ML) model under the orchestration of a central server without knowing the clients' private raw data. The development of effective FL algorithms faces multiple practical challenges including data heterogeneity and clients' privacy protection. Despite that numerous attempts have been made to deal with data heterogeneity or rigorous privacy protection, none have effectively tackled both issues simultaneously. In this article, we propose a differentially private and heterogeneity-robust FL algorithm, named DP-FedCVR to mitigate the data heterogeneity by following the client-variance-reduction strategy. Besides, it adopts a sophisticated differential privacy (DP) mechanism where the privacy-amplified strategy is applied, to achieve a rigorous privacy protection guarantee. We show that the proposed DP-FedCVR algorithm maintains its heterogeneity-robustness though DP noises are incorporated, while achieving a sublinear convergence rate for a nonconvex FL problem. Numerical experiments based on image classification tasks are presented to demonstrate that DP-FedCVR provides superior performance over the benchmark algorithms in the presence of data heterogeneity and various DP privacy budgets. © 2020 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Mainlobe DRFM Jamming Suppression via Blind Source Separation Using Tensor Decomposition 8

Mainlobe DRFM Jamming Suppression via Blind Source Separatio...

引用

8th International Conference on Signal and Image Processing, ICSIP 2023

作者： Dong, Luxin Wang, Bing Pan, Bunian Kong, Yukai Yu, Xianxiang Cui, Guolong University of Electronic Science and Technology of China School of Information and Communication Engineering Chengdu611731 China Science and Technology on Electronic Information Control Laboratory Chengdu610036 China

ISBN: (纸本)9798350397932

This paper deals with the suppression problem of mainlobe digital radio frequency memory (DRFM) jamming especially for intra-pulse slice forwarding jamming for phased array radar. A novel mainlobe DRFM jamming suppression method resorting to blind source separation based on tensor decomposition (TD-BSS) is proposed to separate the target echo signal and jamming signal. Specifically, the received signals are reconstructed into higher-order tensor form. Further, the separating matrix optimization problem relying on tensor Canonical Polyadic (CP) decomposition principle is formulated and then solved by an enhanced line search alternating least square (ELS-ALS) algorithm. Finally, the performance of the proposed method is demonstrated through numerical simulations, showing its superior to suppress mainlobe DRFM jamming over the exiting method in terms of interrupted sampling and cyclic repeater jamming (ISCRJ) and chopping and interval (C&I) jamming. © 2023 IEEE.

关键词： Blind source separation

来源：评论

学校读者我要写书评

暂无评论

6G Network Traffic Intrusion Detection Using Multiresolution Auto-encoder and Feature Matching Discriminator 5th

6G Network Traffic Intrusion Detection Using Multiresolution...

引用

5th EAI International Conference on 6G for Future Wireless Networks, 6GN 2022

作者： Li, Yuhai Sun, Yuxin He, Dong Xi, Liang Science and Technology on Electro-Optical Information Security Control Laboratory Tianjin300300 China School of Computer Science and Technology Harbin University of Science and Technology Harbin150080 China

ISBN: (纸本)9783031360107

With the development of 6G technology, security and privacy have become extremely important in the face of larger network traffic bandwidth. An effective intrusion detection system can deal with the network attacks. Deep learning has been developed in the field of intrusion detection, which can identify normal and abnormal traffic. However, existing methods cannot guarantee good performance in accuracy and efficiency. In this paper, based on the autoencoder and generative adversarial network, the multiresolution autoencoder is adopted in the network traffic feature extraction, which can obtain different encoding lengths and guarantee better data reconstruction. In addition, we add an extra feature matching loss to encourage the discriminator to get more discriminative information from the reconstructed samples. Our experimental results on the CIC-IDS2018 dataset indicates that compared with autoencoder and generative adversarial network, our model can effectively improve the detection accuracy and can be applied to 6G network traffic security detection. © 2023, ICST Institute for Computer sciences, Social Informatics and Telecommunications Engineering.

关键词： Intrusion detection

来源：评论

学校读者我要写书评

暂无评论

Classification of Deforestation Factors in 6G Satellite Forest Images 5th

Classification of Deforestation Factors in 6G Satellite Fore...

引用

5th EAI International Conference on 6G for Future Wireless Networks, 6GN 2022

作者： Li, Yuhai Sun, Yuxin Meng, Xianglong Xi, Liang Science and Technology on Electro-Optical Information Security Control Laboratory Tianjin300300 China School of Computer Science and Technology Harbin University of Science and Technology Harbin150080 China

ISBN: (纸本)9783031360107

The terrestrial satellite network will play an essential role in 6G. Through the satellite system, people can obtain a lot of ground image information to process tasks and feedback. Forest resource is an essential resource. Determining the causes of deforestation is crucial for the development and implementation of forest protection plans. In this article, we propose a novel deep neural network model for distinguishing drivers of deforestation events from satellite forest images. To solve the problems of image rotation caused by satellite angle rotation and image blurring caused by extreme weather occlusion during satellite image acquisition, we add data enhancement and a self-supervised rotation loss to the model to improve the robustness and adaptability. We use deforestation maps generated from Landsat 8 satellite imagery as a dataset and demonstrate that our approach achieves better results than the baselines. © 2023, ICST Institute for Computer sciences, Social Informatics and Telecommunications Engineering.

关键词： Deforestation

来源：评论

学校读者我要写书评

暂无评论

An Asymmetric Channel Attack Monitoring Method for Round-Trip Fiber Time Synchronization System 37

An Asymmetric Channel Attack Monitoring Method for Round-Tri...

引用

37th European Frequency and Time Forum, EFTF 2024

作者： Xu, Xuesong Zhang, Yichen Xu, Hailong Bian, Yiming Li, Yang Xu, Bingjie Yu, Song School of Electronic Engineering Beijing University of Posts and Telecommunications State Key Laboratory of Information Photonics and Optical Communications Beijing100876 China Institute of Southwestern Communication Science and Technology on Communication Security Laboratory Chengdu610041 China

ISBN: (纸本)9798350354270

We present a method for monitoring potential asymmetric channel attacks within a round-trip fiber time synchronization system. This is achieved by observing and tracking the time difference at the remote end. Experimental results show that the attacking operation causes unavoidably obvious fluctuations in time difference, with the time difference measured by our monitoring module changing by nanoseconds when an attack occurs, which can be used for attack recognition. Our work provides a reference for further improving the security of fiber time synchronization systems and lays the foundation for the development of more advanced time synchronization attack identification techniques. © 2024 IEEE.

关键词： asymmetric channel attack attack monitoring round-trip time synchronization

来源：评论

学校读者我要写书评

暂无评论

A Study on Resource Allocation for Mobile Edge Computing-Assisted Industrial Iot

A Study on Resource Allocation for Mobile Edge Computing-Ass...

引用

2023 International Conference on Networks, communications and Intelligent Computing, NCIC 2023

作者： Lu, Jie Zhang, Yuexia Li, Junjie Ministry of Information Industry Beijing Information Science and Technology University Key Laboratory of Information and Communication Systems Beijing China Control Technology Ministry of Education Beijing Information Science and Technology University Key Laboratory of Modern Measurement Beijing China

ISBN: (纸本)9798350371949

Since the advancement of mobile communication technology, traditional industries are gradually transforming and upgrading, which leads to problems such as insufficient computing resources and excessive energy consumption of Internet of Things (IoT) devices. To address this issue, a resource allocation algorithm for the mobile edge computing-assisted industrial IoT (IIoT) is proposed. First, a mobile edge computing-assisted IIoT network model was constructed. Using the collaboration between IoT devices, mobile edge computing (MEC) servers, and cloud servers, the issue of minimizing all IIoT devices energy cost was proposed. Subsequently, in order to address the optimization issue, obtain its optimal solution, the alternating direction method of multipliers (ADMM) algorithm is introduced. Finally, the ADMM algorithm's convergence was verified through an experimental simulation. In contrast to baseline algorithm 1 and algorithm 2, the ADMM algorithm can significantly diminish energy cost, proving the effectiveness of the proposed scheme. © 2023 IEEE.

关键词： Resource allocation

来源：评论

学校读者我要写书评

暂无评论

OPTIMIZING MULTI-INPUT SCHEDULING FOR FUZZING TEST USING BAYESIAN ALGORITHM WEIGHT OPTIMIZATION 10

OPTIMIZING MULTI-INPUT SCHEDULING FOR FUZZING TEST USING BAY...

引用

10th International Symposium on Test Automation and Instrumentation, ISTAI 2024

作者： Fang, Junzhe Wang, Liyong Ji, Haojie Guo, Teng Hu, Te Key Laboratory of Modern Measurement and Control Technology Ministry of Education Beijing Information Science and Technology University Beijing China Zaozhuang Network Security Guarantee Center Zaozhuang China

ISBN: (纸本)9781837242672

As a major software testing method, fuzzing has the potential to enhance testing coverage and detect a great number of software vulnerabilities in complex code programs. The current fuzzy testing for multiple input parameters lacks an effective calling mechanism and treats all variant parameter equally, resulting in low efficiency. This paper presents a fuzzy testing method based on Bayesian algorithm for scheduling parameters. Firstly, it combines the characteristics of input parameters to match the appropriate variation strategy. Secondly, it utlizes the Bayesian algorithm to automatically generate weight values for the objective function index during sufficient testing. It evaluates test cases with multi-parameter inputs according to these weights and selects parameters with high utilization value for multiple tests. Finally, in order to evaluate the effectiveness of the method of this paper, an application programming interface of Amercian fuzzy lop (AFL-API) is developed based on the typical fuzzy testing tool AFL++, and compared with AFL++ as a fuzzy testing tool. The experimental results demonstate that when using the AFL-API for program testing, there was 47% increase in coverage rate, 52% increase in the number of discovered crashes, and more program vulnerabilities were identified during actual testing. © The Institution of Engineering & technology 2024.

关键词： Software testing

来源：评论

学校读者我要写书评

暂无评论

MULTI-ROBOT PATH PLANNING AND COOPERATIVE OBSTACLE AVOIDANCE BASED ON MONTE-CARLO TREE SEARCH 10

MULTI-ROBOT PATH PLANNING AND COOPERATIVE OBSTACLE AVOIDANCE...

引用

10th International Symposium on Test Automation and Instrumentation, ISTAI 2024

作者： Dai, Juan Jing, Yanzhang Su, Zhong Zhu, Cui Beijing Key Laboratory of High Dynamic Navigation Technology Beijing Information Science & Technology University Beijing China Key Laboratory of Modern Measurement and Control Technology Ministry of Education Beijing China School of Automation Beijing Information Science & Technology University Beijing China School of Information and Communication Engineering Beijing Information Science & Technology University Beijing China

ISBN: (纸本)9781837242672

With the rapid development of artificial intelligence technologies, multi-robot cooperative processing tasks are becoming more and more common in various applications. However, traditional single-robot planning algorithms show obvious limitations in dealing with complex social interactions and dynamic environments in the real world. To address this challenge, this paper applies Monte Carlo Tree Search (MCTS) to multi-robot path planning and proposes a collaborative obstacle avoidance motion planning algorithm based on MCTS. Specifically, the algorithm prunes the Monte Carlo tree by excluding cases that do not meet the robot speed constraints and potential collisions, which significantly improves the computational speed and success rate of the algorithm, making it applicable to the multi-robot path conflict problem. In addition, we design a policy space that conforms to the robot's operation and a cost function that meets the requirements of robot path planning to plan an efficient cooperative path for each robot. Through a series of simulation experiments, we demonstrate the algorithm's path planning and obstacle avoidance performance in a variety of conflict scenarios. The results show that the method is highly cooperative and effective in complex environments. © The Institution of Engineering & technology 2024.

关键词： Cost functions

来源：评论

学校读者我要写书评

暂无评论

Arbitrarily rotating polarization direction and manipulating phases in linear and nonlinear ways using programmable metasurface

引用

Light(science & Applications) 2024年第9期13卷 1789-1800页

作者： Wei Liu Si Ran Wang Jun Yan Dai Lei Zhang Qiao Chen Qiang Cheng Tie Jun Cui State Key Laboratory of Millimeter Waves Southeast UniversityNanjing 210096China Institute of Electromagnetic Space Southeast UniversityNanjing 210096China Frontiers Science Center for Mobile Information Communication and Security Southeast UniversityNanjing 210096China Electrical Engineering Department Chalmers University of TechnologyGothenburg 41258Sweden

Independent controls of various properties of electromagnetic(EM)waves are crucially required in a wide range of *** metasurface is a promising candidate to provide an advanced platform for manipulating EM ***,we propose an approach that can arbitrarily control the polarization direction and phases of reflected waves in linear and nonlinear ways using a stacked programmable ***,we extend the space-timecoding theory to incorporate the dimension of polarization,which provides an extra degree of freedom for manipulating EM *** proof-of-principle application examples,we consider polarization rotation,phase manipulation,and beam steering at linear and nonlinear *** validation,we design,fabricate,and measure a metasurface *** experimental results show good agreement with theoretical predictions and *** proposed approach has a wide range of applications in various areas,such as imaging,data storage,and wireless communication.

关键词： surface nonlinear rotating

来源：评论

学校读者我要写书评

暂无评论

Personalized Federated Learning for Heterogeneous Residential Load Forecasting

引用

Big Data Mining and Analytics 2023年第4期6卷 421-432页

作者： Xiaodong Qu Chengcheng Guan Gang Xie Zhiyi Tian Keshav Sood Chaoli Sun Lei Cui the Shanxi Key Laboratory of Advanced Control and Equipment Intelligence Taiyuan University of Science and TechnologyTaiyuan 030024China the Faculty of Engineering and Information Technology University of Technology SydneyUltimo 2007Australia the Centre for Cyber Security Research and Innovation Deakin UniversityMelbourne 3125Australia the School of Computer Science and Technology Taiyuan University of Science and TechnologyTaiyuan 030024China

Accurate load forecasting is critical for electricity production,transmission,and *** learning(DL)model has replaced other classical models as the most popular prediction ***,the deep prediction model requires users to provide a large amount of private electricity consumption data,which has potential privacy *** nodes can federally train a global model through aggregation using federated learning(FL).As a novel distributed machine learning(ML)technique,it only exchanges model parameters without sharing raw ***,existing forecasting methods based on FL still face challenges from data heterogeneity and privacy ***,we propose a user-level load forecasting system based on personalized federated learning(PFL)to address these *** obtained personalized model outperforms the global model on local ***,we introduce a novel differential privacy(DP)algorithm in the proposed system to provide an additional privacy *** on the principle of generative adversarial network(GAN),the algorithm achieves the balance between privacy and prediction accuracy throughout the *** perform simulation experiments on the real-world dataset and the experimental results show that the proposed system can comply with the requirement for accuracy and privacy in real load forecasting scenarios.

关键词： load forecasting personalized federated learning differential privacy

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：