检索结果-内蒙古大学图书馆

International Joint Conference on Neural networks (IJCNN)

作者： Jiayi Huang Yuanyuan Zhang Renwan Bi Jiayin Lin Jinbo Xiong Fujian Provincial Key Lab of Network Security & Cryptology College of Computer and Cyber Security Fujian Normal University Fuzhou China

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

Applying knowledge distillation (KD) in federated learning (FL) can transfer model knowledge between clients’ local models and global model, which helps to improve the generalization of the global model. However, this requires both the clients and the server to have public data sets, which may lead to potential privacy disclosure issues. In this paper, we propose a federated data-free knowledge distillation framework, namely FedDFKD, which does not rely on any public data sets. There is a lightweight delivery model we design to learn and transfer model knowledge in different clients. During local training, the local model is jointly trained with delivery model using local data sets, and the local model feeds back its knowledge to the delivery model after it has finished its training phase in this communication round. Afterwards, the server performs global model aggregation and knowledge distillation of the delivery model. Finally, the server returns global model and distillation result to clients. We compare FedDFKD with the most representative aggregation algorithms in FL, and the results show that our method is feasible and outperforms the compared methods by between 0.1 and 3.96 percent of the global model on the MNIST dataset.

关键词： Training Knowledge engineering Data privacy Accuracy Federated learning Neural networks Data models

来源：评论

学校读者我要写书评

暂无评论

Weakly supervised temporal action localization with proxy metric modeling

引用

Frontiers of computer Science 2023年第2期17卷 63-72页

作者： Hongsheng XU Zihan CHEN Yu ZHANG Xin GENG Siya MI Zhihong YANG NARI Group Corporation(State Grid Electric Power Research Institute) Nanjing 211106China School of Computer Science and Engineering and the Key Lab of Computer Network and Information Integration(Ministry of Education)Southeast UniversityNanjing 211189China School of Cyber Science and Engineering Southeast UniversityNanjing 211189China Purple Mountain Laboratories Nanjing 211111China

Temporal localization is crucial for action video *** the manual annotations are expensive and time-consuming in videos,temporal localization with weak video-level labels is challenging but *** this paper,we propose a weakly-supervised temporal action localization approach in untrimmed *** settle this issue,we train the model based on the proxies of each action *** proxies are used to measure the distances between action segments and different original action *** use a proxy-based metric to cluster the same actions together and separate actions from *** with state-of-the-art methods,our method achieved competitive results on the THUMOS14 and ActivityNet1.2 datasets.

关键词： temporal action localization weakly supervised videos proxy metric

来源：评论

学校读者我要写书评

暂无评论

Block-based fine-grained and publicly verifiable data deletion for cloud storage: Block-based fine-grained and publicly verifiable..: C. Yang et al.

引用

Soft Computing 2024年第21期28卷 12491-12506页

作者： Yang, Changsong Liu, Yueling Ding, Yong Wu, Yongqiang Guangxi Key Laboratory of Cryptography and Information Security Guilin University of Electronic Technology Guilin541004 China Lion Rock Labs of Cyberspace Security Institute of Cyberspace Technology HKCT Institute for Higher Education 999077 Hong Kong Guangxi Engineering Research Center of Industrial Internet Security and Blockchain Guilin University of Electronic Technology Guilin541004 China School of Computer Guangdong University of Science & Technology Dongguan523083 China South China Technical Support Department Topsec Network Technology Inc. Guangzhou510000 China

One of the most important services provided by cloud service providers (CSPs), cloud storage is economically attractive and can provide on-demand data storage service to resource-constrained tenants in the manner of pay-per-use. Therefore, by embracing cloud storage service, tenants can store their large-scale data on the remote cloud host to tremendously reduce local storage burden and computational overhead. However, due to the separation of cloud data ownership and management, cloud storage inevitably suffers from a few new security challenges, such as fine-grained cloud data deletion. To achieve data deletion in cloud storage, we design a vector-commitment-based publicly verifiable data deletion scheme, which can achieve data integrity auditing and block-based fine-grained data deletion. Specifically, our proposed scheme disguises the data deletion operation as data update operation. Therefore, the tenants can achieve data deletion by updating the cloud data blocks with some unrelated data blocks. Meanwhile, the tenants can prevent cloud data from being polluted by periodically performing data integrity auditing operation, thus guaranteeing that the cloud host sincerely maintains the data. Moreover, we formally analyze the security, which shows that our proposed scheme can satisfy all of the anticipative security requirements without interaction with a centralized third party. Finally, we develop a prototype system and evaluate the performance of our proposed scheme, which can intuitively demonstrate the high-efficiency and practicality of our proposal. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2024.

关键词： Data integrity

来源：评论

学校读者我要写书评

暂无评论

Self-Anomaly-Detection Model Training via Initialized Meta Model

Self-Anomaly-Detection Model Training via Initialized Meta M...

引用

2022 International Conference on networking and network Applications, NaNA 2022

作者： Ma, Xindi Su, Cunzhu Ma, Jianfeng Jiang, Qi Xi, Ning Gao, Sheng Xie, Kang School of Cyber Engineering Xidian University Shaanxi China School of Information Central University of Finance and Economics Beijing China Key Lab of Information Network Security Ministry of Public Security Shanghai China

ISBN: (数字)9781665461313

ISBN: (纸本)9781665461313

Anomaly detection has become a key challenge affecting the training accuracy of machine learning. Because the training data is usually collected from Internet, many noised samples will be captured and these samples can decrease the model training accuracy. However, because the abnormal samples are difficult to predict when the samples are collected, and the training samples collected may contain many unknown exception categories, and the labels of normal samples may be incorrect, in this case, it is difficult to train an anomaly detection model based on supervised learning to accurately identify the anomaly samples. In this paper, we propose a new unsupervised anomaly detection method based on BiGAN, namely Rt-BiGAN, to identify the outliers in the training data. Firstly, we propose a Bigan network initialization method based on meta-learning algorithm with a small number of normal samples. Then, a self-supervised drop training is designed to improve the detection ability of the model. Finally, we evaluate our Rt-BiGAN over real-world datasets and the simulations results demonstrate that our mechanism is effective to detect the outliers in model training data. © 2022 IEEE.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Discourse Relation-Aware Multi-turn Dialogue Response Generation 12th

Discourse Relation-Aware Multi-turn Dialogue Response Genera...

引用

12th National CCF Conference on Natural Language Processing and Chinese Computing, NLPCC 2023

作者： Wang, Huijie He, Ruifang Jia, Yungang Xu, Jing Wang, Bo College of Intelligence and Computing Tianjin University Tianjin China Tianjin Key Laboratory of Cognitive Computing and Application Tianjin China Tianjin Branch of National Computer Network and Information Security Management Center Tianjin China

ISBN: (纸本)9783031446924

Multi-turn dialogue response generation aims to generate a response with consideration of the context. It is not equal to multiple single-turn dialogues due to the context dependence of response. Many existing models achieve great success for response generation, but they still struggle to model the contextual semantics of dialogue history. Sequence models have difficulties to explore the interactive relations between contextual utterances, which affects the coherence of generated responses. To solve the issue, we propose a discourse relation-aware model, which encodes the contextual utterances with a directed acyclic graph neural network (DAGNN) with constraints on dialogue-specific discourse relations to better model the intrinsic structure. Besides, we introduce an auxiliary discourse relation recognition task to enhance the model’s ability of representing the context. Extensive experimental results show that our proposed model outperforms baselines. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Directed graphs

来源：评论

学校读者我要写书评

暂无评论

Mal-lightDet: A light method to detect malicious encrypted traffic based on machine learning 23

Mal-lightDet: A light method to detect malicious encrypted t...

引用

2023 4th International Conference on Control, Robotics and Intelligent System, CCRIS 2023

作者： Liu, Xu Liu, Zhang Zhao, Xiaojing Ren, Zhengwei School of Computer Science and Technology Changchun University of Science and Technology China Jilin Province Key Laboratory of Network and Information Security China School of Artificial Intelligence Changchun University of Science and Technology Changchun China

ISBN: (纸本)9798400708190

Encryption not only protects the network security and privacy, but also encrypts attackers' malicious traffic to evade detection. Thus, how to detect malicious encrypted traffic is critical for network security. From the perspective of privacy, methods based on ciphertext seem to be more attractive than decryption-based methods. However, due to performance limitation or privacy violations, most existing methods are far from satisfactory. Machine learning models provide a solution to the malicious encrypted traffic detection, but they place great demand on data features. To balance the detection performance and feature effectiveness, this paper proposes a framework called Mal-lightDet for light detection of malicious encrypted traffic based on machine learning. Mal-lightDet includes a feature-group selection model that mines the relevance between features to represent the traffic flow, which is less considered in the existing methods, and a voting-based detection model to eliminate the bias of different machine learning models. The selected feature subset not only preserves the detection effectiveness but also reduces the computation brought by massive training data. The experimental results prove the efficiency and stability of Mal-lightDet to distinguish malicious flow data by comparing it with other state-of-art methods. Besides, Mal-lightDet performs faster, more accurately, and more stably than some deep learning methods. © 2023 ACM.

关键词： network security

来源：评论

学校读者我要写书评

暂无评论

Collecting and analyzing key-value data under shuffled differential privacy

引用

Frontiers of computer Science 2023年第2期17卷 241-243页

作者： Ning WANG Wei ZHENG Zhigang WANG Zhiqiang WEI Yu GU Peng TANG Ge YU Faculty of Information Science and Engineering Ocean University of ChinaQingdao 266100China School of Computer Science and Engineering Northeastern UniversityShenyang 110819China Key Lab of Cryptologic Technology and Information Security Ministry of EducationShandong UniversityQingdao 266200China School of Cyber Science and Technology Shandong UniversityQingdao 266200China

1 Introduction key-value data,as NoSQL data widely used in recent years,has been frequently collected and used for analysis in major websites and mobile *** frequency distribution estimation on the key domain,as well as the mean estimation of values associated with the same key,are crucial and worth billion dollars in the ***,in real applications,the key-value records are submitted by terminal devices of different *** collecting the information from users may pose serious risks on personal *** the other hand,the emerging shuffled differential privacy(SDP)model[1]is proposed to collect sensitive data from users.

关键词： NoSQL app value

来源：评论

学校读者我要写书评

暂无评论

Fusion of Dynamic Hypergraph and Clinical Event for Sequential Diagnosis Prediction 29

Fusion of Dynamic Hypergraph and Clinical Event for Sequenti...

引用

29th IEEE International Conference on Parallel and Distributed Systems, ICPADS 2023

作者： Zhang, Xin Peng, Xueping Guan, Hongjiao Zhao, Long Qiao, Xinxiao Lu, Wenpeng Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Jinan China Shandong Fundamental Research Center for Computer Science Shandong Provincial Key Laboratory of Computer Networks Jinan China Australian Artificial Intelligence Institute University of Technology Sydney Sydney Australia

ISBN: (纸本)9798350330717

Sequential diagnosis prediction (SDP) is a challenging task, aiming to predict patients' future diagnoses based on their historical medical records. While methods based on graph neural networks (GNNs) have proven successful for this task, they typically focus on modeling pairwise diseases using a global disease combination graph. However, these approaches neglect the fine-grained higher-order relations among persistent and emerging diseases within a single visit, which may contain crucial clues to predict the next diagnosis. Additionally, they fail to fully leverage patient-related clinical information present in electronic health records (EHRs). To address these challenges, this paper proposes a novel approach called the fusion of Dynamic Hypergraph and Clinical Event (DHCE) for sequential diagnosis prediction. The proposed method aims to exploit the fine-grained higher-order relations among diagnoses within a visit and leverage clinical event information from EHRs to improve the accuracy of predicting the next diagnosis. Specifically, DHCE categorizes diagnoses within a single visit in a fine-grained granularity into persistent and emerging categories based on a patient's historical diagnoses. It then constructs dynamic hypergraphs to capture higher-order disease relations within each visit. Next, we design a transition function to extract the transitional context from previous visits in order to generate the visit representation. Furthermore, to fully leverage patient-related clinical events in a visit, we utilize Bio-Clinical BERT to encode them and generate the clinical event representation for each visit. Finally, we combine the visit representation and event representation to generate a comprehensive patient representation, which is then used to predict the patient's next diagnosis. Experimental results on two benchmark datasets consistently demonstrate that DHCE outperforms state-of-the-art methods. © 2023 IEEE.

关键词： Bio-Clinical BERT clinical event dynamic hypergraph sequential diagnosis prediction

来源：评论

学校读者我要写书评

暂无评论

A multiple sensitive attributes data publishing method with guaranteed information utility

引用

CAAI Transactions on Intelligence Technology 2023年第2期8卷 288-296页

作者： Haibin Zhu Tong Yi Songtao Shang Minyong Shi Zhucheng Li Wenqian Shang Department of Computer Science and Mathematics Nipissing UniversityNorth BayOntarioCanada Key Lab of Education Blockchain and Intelligent Technology Ministry of EducationGuangxi Normal UniversityGuilinChina Guangxi Key Lab of Multi‐Source Information Mining and Security Guangxi Normal UniversityGuilinChina School of Computer and Communication Engineering Zhengzhou University of Light IndustryZhengzhouChina School of Computer Science Communication University of ChinaBeijingChina Business College Beijing Union UniversityBeijingChina

Data publishing methods can provide available information for analysis while preserving *** multiple sensitive attributes data publishing,which preserves the relationship between sensitive attributes,may keep many records from being grouped and bring in a high record suppression *** category of multiple sensitive attributes data publishing,which reduces the possibility of record suppression by breaking the relationship between sensitive attributes,cannot provide the sensitive attributes association for ***,the existing multiple sensitive attributes data publishing fails to fully account for the comprehensive information *** acquire a guaranteed information utility,this article defines comprehensive information loss that considers both the suppression of records and the relationship between sensitive attributes.A heuristic method is leveraged to discover the optimal anonymity scheme that has the lowest comprehensive information *** experimental results verify the practice of the proposed data publishing method with multiple sensitive *** proposed method can guarantee information utility when compared with previous ones.

关键词： data analysis data privacy security of data

来源：评论

学校读者我要写书评

暂无评论

A multipath routing algorithm for satellite networksbased on service demand and traffic awareness

引用

Frontiers of information Technology & Electronic Engineering 2023年第6期24卷 844-858页

作者： Ziyang XING Hui QI Xiaoqiang DI Jinyao LIU Rui XU Jing CHEN Ligang CONG Jilin Key Laboratory of Network and Information Security Changchun 130022China School of Computer Science and Technology Changchun University of Science and TechnologyChangchun 130022China Information Center Changchun University of Science and TechnologyChangchun 130022China

With the reduction in manufacturing and launch costs of low Earth orbit satellites and the advantages of large coverage and high data transmission rates,satellites have become an important part of data transmission in air-ground ***,due to the factors such as geographical location and people’s living habits,the differences in user’demand for multimedia data will result in unbalanced network traffic,which may lead to network congestion and affect data *** addition,in traditional satellite network transmission,the convergence of network information acquisition is slow and global network information cannot be collected in a fine-grained manner,which is not conducive to calculating optimal *** service quality requirements cannot be satisfied when multiple service requests are *** on the above,in this paper artificial intelligence technology is applied to the satellite network,and a software-defined network is used to obtain the global network information,perceive network traffic,develop comprehensive decisions online through reinforcement learning,and update the optimal routing strategy in real *** results show that the proposed reinforcement learning algorithm has good convergence performance and strong *** with traditional routing,the throughput is 8%higher,and the proposed method has load balancing characteristics.

关键词： Software-defined network(SDN) Quick user datagram protocol Internet connection(QUIC) Reinforcement learning Sketch Multi-service demand Satellite network

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：