检索结果-内蒙古大学图书馆

Personalized Federated Learning for Heterogeneous Residential Load Forecasting

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

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

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

security and Privacy for VR in non-entertainment sectors: a practice-based study of the challenges, strategies and gaps

Security and Privacy for VR in non-entertainment sectors: a ...

引用

Virtual Reality and 3D User Interfaces Abstracts and Workshops (VRW), IEEE Conference on

作者： Camille Sivelle David Palma Katrien De Moor Department of Information Security and Communication Technology Norwegian University of Science and Technology

ISBN: (数字)9798331514846

ISBN: (纸本)9798331525637

The adoption of Extended Reality (XR) for non-entertainment use cases, such as healthcare, industry or education, raises new security and privacy (S&P) concerns. Despite an emerging focus on these aspects in the literature, we lack insights into how S&P threats for XR are perceived and accounted for by relevant stakeholders, such as those who are responsible for the design, development and rollout of these experiences. In this work-in-progress, we investigate the S&P concerns expressed by development teams and organisations using Virtual Reality (VR) in non-entertainment sectors, as well as the strategies adopted to mitigate these. We performed semi-structured interviews with 7 industry practitioners involved in the conception or development of non-entertainment VR experiences. By analysing this data against a classification of VR S&P threats from the literature, we identify gaps in the practitioners’ awareness of existing threats and in their defence strategies. We found that while most participants were concerned about S&P threats, there was an overall lack of awareness about VR-specific challenges. Our current findings and the intended follow-up work aim to inform future efforts towards providing usable and practical solutions for S&P in XR, based on systematic S&P threat modelling.

关键词： Industries Threat modeling Privacy Three-dimensional displays Systematics Extended reality Medical services User interfaces Stakeholders Interviews

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

Blockchain state channels with compact states through the use of RSA accumulators

引用

Blockchain(Research and Applications) 2023年第1期4卷 71-89页

作者： Lydia Negka Angeliki Katsika Georgios Spathoulas Vassilis Plagianakos Department of Computer Science and Biomedical Informatics University of Thessaly2-4 Papasiopoulou st.Lamia35131Greece Department of Information Security and Communication Technology Norwegian University of Science and Technology(NTNU)Mail Box 191GjøvikNO-2815Norway

One of the major concerns regarding currently proposed public blockchain systems relates to the feasible transaction processing *** is common for such systems to limit this rate to maintain the required levels of security and *** channels are an approach to overcome this limitation,as they aim to decrease the required on-chain transactions for a given application and thus indirectly increase the capacity(in terms of applications)of public blockchain *** the present paper,we propose a state channel design that,through the use of RSA accumulators,operates on a compact state *** scheme is optimal for applications whose state includes large sets of *** novel state channel design is presented by analysing all state channel operations and how they have to be *** security of the design is discussed,while a practical use case scenario regarding the use of the design for an on-chain asset(e.g.,non-fungible tokens)exchange application is also analysed.

关键词： Blockchain State channels Accumulators Layer 2 NFTs

来源：评论

学校读者我要写书评

暂无评论

Vector Approximate Message Passing with Sparse Bayesian Learning for Gaussian Mixture Prior

引用

China communications 2023年第5期20卷 57-69页

作者： Chengyao Ruan Zaichen Zhang Hao Jiang Jian Dang Liang Wu Hongming Zhang National Mobile Communications Research Laboratory Frontiers Science Center for Mobile Information Communication and SecuritySoutheast UniversityNanjing 210096China Purple Mountain Laboratories No.9 Mozhou East RoadNanjing 211111China School of Artificial Intelligence Nanjing University of Information Science and TechnologyNanjing 210044China School of Information and Communication Engineering Beijing University of Posts and TelecommunicationsBeijing 100876China

Compressed sensing(CS)aims for seeking appropriate algorithms to recover a sparse vector from noisy linear ***,various Bayesian-based algorithms such as sparse Bayesian learning(SBL)and approximate message passing(AMP)based algorithms have been *** SBL,it has accurate performance with robustness while its computational complexity is high due to matrix *** AMP,its performance is guaranteed by the severe restriction of the measurement matrix,which limits its application in solving CS *** overcome the drawbacks of the above algorithms,in this paper,we present a low complexity algorithm for the single linear model that incorporates the vector AMP(VAMP)into the SBL structure with expectation maximization(EM).Specifically,we apply the variance auto-tuning into the VAMP to implement the E step in SBL,which decrease the iterations that require to converge compared with VAMP-EM algorithm when using a Gaussian mixture(GM)*** results show that the proposed algorithm has better performance with high robustness under various cases of difficult measurement matrices.

关键词： sparse Bayesian learning approximate message passing compressed sensing expectation propagation

来源：评论

学校读者我要写书评

暂无评论

Phishing detection on Ethereum via transaction subgraphs embedding

IET Blockchain

引用

IET Blockchain 2023年第4期3卷 194-203页

作者： Lv, Haifeng Ding, Yong Guangxi Key Laboratory of Machine Vision and Intelligent Control WuZhou University Wuzhou China Guangxi Key Laboratory of Cryptography and Information Security School of Computer Science and Information Security Guilin University of Electronic Technology Guilin China Guangxi Colleges and Universities Key Laboratory of Industry Software Technology WuZhou University Wuzhou China

With the rapid development of blockchain technology in the financial sector, the security of blockchain is being put to the test due to an increase in phishing fraud. Therefore, it is essential to study more effective measures and better solutions. Graph models have been proven to provide abundant information for downstream assignments. In this study, a graph-based embedding classification method is proposed for phishing detection on Ethereum by modeling its transaction records using subgraphs. Initially, the transaction data of normal addresses and an equal number of confirmed phishing addresses are collected through web crawling. Multiple subgraphs using the collected transaction records are constructed, with each subgraph containing a target address and its nearby transaction network. To extract features of the addresses, a modified Graph2Vec model called imgraph2vec is designed, which considers block height, timestamp, and amount of transactions. Finally, the Extreme Gradient Boosting (XGBoost) algorithm is employed to detect phishing and normal addresses. The experimental results show that the proposed method achieves good performance in phishing detection, indicating the effectiveness of imgraph2vec in feature acquisition of transaction networks compared to existing models. © 2023 The Authors. IET Blockchain published by John Wiley & Sons Ltd on behalf of The Institution of Engineering and technology.

关键词： Graphic methods

来源：评论

学校读者我要写书评

暂无评论

An Explainable Deep Learning-based Approach for Multivariate Time Series Anomaly Detection in IoT 20

An Explainable Deep Learning-based Approach for Multivariate...

引用

20th International Conference on Frontiers of information technology, FIT 2023

作者： Toor, Aafan Ahmad Lin, Jia-Chun Gran, Ernst Gunnar Lee, Ming-Chang Department of Information Security and Communication Technology Gjovik Norway Electrical Engineering and Mathematical Sciences Department of Computer Science Bergen Norway

ISBN: (纸本)9798350395785

Detecting anomalies from Internet of Things (IoT) data is important for a smooth flow of events. Timely detection of anomalies and raising alarms can help avoid any potential health and safety hazards in an IoT environment such as detecting falling people by activity recognition using wearable sensors. However, most IoT data lacks labels and sometimes when the labels are available, the context is missing, which makes anomaly detection and inference a challenging task. In this paper, we propose an explainable deep learning-based approach to detect anomalies from multivariate time series data using Long Short-Term Memory (LSTM) and the results are explained using the Local Interpre table Model-agnostic Explanations (LIME). The experiments show promising classification results with good accuracy, precision, recall, and F1 Score values. LIME provided useful explanations for anomalous and non-anomalous instances. The effectiveness of LIME for time series anomaly detection is discussed, and its limitations are also highlighted. © 2023 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Detection of PFCP Protocol Based on Fuzz Method 2

Detection of PFCP Protocol Based on Fuzz Method

引用

2nd International Conference on Computer, control and Robotics, ICCCR 2022

作者： Cao, Yebei Chen, Yucheng Zhou, Wenan Science and Technology on Communication Information Security Control Laboratory Jiaxing China School of Computer Science Beijing University of Posts and Telecommunications Beijing China

ISBN: (纸本)9781665466745

5G as a widely used mobile network, its security is of great significance. PFCP protocol is one of the important protocols that introduced into 5G core network, After the analysis of PFCP protocol and its security threat, this paper profoundly fuzzed the PFCP protocol. In order to improve the efficiency, this paper improves the random Fuzzing test technology, proposes a new data mutation algorithm and frame. By analyzing the test results, we found that the application of the new algorithm made the fuzzing technology greatly improved in terms of efficiency and found security vulnerabilities. © 2022 IEEE.

关键词： Efficiency

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：