检索结果-南通市图书馆

同方期刊数据库

cross-domain Data Traceability Mechanism Based on Blockchain

在线全文

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2023年第8期76卷 2531-2549页

作者： Shoucai Zhao Lifeng Cao Jinhui Li Jiling Wan Jinlong Bai He’nan Province Key Laboratory of Information Security Zhengzhou450000China

With the application and development of blockchain technology,many problems faced by blockchain traceability are gradually *** as cross-chain information collaboration,data separation and storage,multisystem,multi-security domain collaboration,*** solve these problems,it is proposed to construct trust domains based on federated *** public chain is used as the authorization chain to build a cross-domain data traceability mechanism applicable to multi-domain ***,the architecture of the blockchain cross-domain model is *** with the data access strategy and the decision mechanism,the open and transparent judgment of cross-domain permission and cross-domain identity authentication is *** the public chain consensus node election mechanism is realized based on ***,according to the characteristics of a nonsingle chain structure in the process of data flow,a data retrievalmechanism based on a Bloom filter is designed,and the cross-domain traceability algorithm is ***,the safety and effectiveness of the traceability mechanism are verified by security evaluation and performance analysis.

关键词： cross-domain data traceability blockchain bloom filter

ATLRec:An Attentional Adversarial Transfer Learning Network for cross-domain Recommendation

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Computer Science & Technology 2020年第4期35卷 794-808页

作者： Ying Li Jia-Jie Xu Peng-Peng Zhao Jun-Hua Fang Wei Chen Lei Zhao School of Computer Science and Technology Soochow UniversitySuzhou 215006China

Entity linking is a new technique in recommender systems to link users'interaction behaviors in different domains,for the purpose of improving the performance of the recommendation ***-based cross-domain recom-mendation aims to alleviate the data sparse problem by utilizing the domain-sharable knowledge from auxiliary ***,existing methods fail to prevent domain-specific features to be transferred,resulting in suboptimal *** this paper,we aim to address this issue by proposing an adversarial transfer learning based model ATLRec,which effec-tively captures domain-sharable features for cross-domain *** ATLRec,we leverage adversarial learning to generate representations of user-item interactions in both the source and the target domains,such that the discrimina-tor cannot identify which domain they belong to,for the purpose of obtaining domain-sharable *** each domain learns its domain-specific features by a private feature *** recommendation of each domain considers both domain-specific and domain-sharable *** further adopt an attention mechanism to learn item latent factors of both domains by utilizing the shared users with interaction history,so that the representations of all items can be learned sufficiently in a shared space,even when few or even no items are shared by different *** this method,we can represent all items from the source and the target domains in a shared space,for the purpose of better linking items in different domains and capturing cross-domain item-item relatedness to facilitate the learning of domain-sharable *** proposed model is evaluated on various real-world datasets and demonstrated to outperform several state-of-the-art single-domain and cross-domain recommendation methods in terms of recommendation accuracy.

关键词： adversarial transfer learning attention mechanism cross-domain recommendation entity linking

Scalable protocol for cross-domain group password-based authenticated key exchange

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Frontiers of Computer Science 2015年第1期9卷 157-169页

作者： Cong GUO Zijian ZHANG Liehuang ZHU Yu-an TAN Zhen YANG Beijing Engineering Research Center of Massive Language Information Processing and Cloud Computing Application School of Computer Science and Technology Beijing Institute of Technology Beijing 100081 China

cross-domain password-based authenticated key exchange （PAKE） protocols have been studied for many years. However, these protocols are mainly focusing on multi-participant within a single domain in an open network environment. This paper proposes a novel approach for designing a cross-domain group PAKE protocol, that primarily handles with the setting of multi-participant in the multi- domain. Moreover, our protocol is proved secure against active adversary in the Real-or-Random （ROR） model. In our protocol, no interaction occurs between any two domain authentication servers. They are regarded as ephemeral certificate authorities （CAs） to certify key materials that participants might subsequently use to exchange and agree on group session key. We further justify the computational complexity and measure the average computation time of our protocol. To the best of our knowledge, this is the first work to analyze and discuss a provably secure multi-participant cross-domain group PAKE protocol.

关键词： cross-domain password-based authenticated key exchange (PAKE) group key exchange Real-Or-Random (ROR) model provable secure

Weighted Co-Training for cross-domain Image SentimentClassification

在线全文

学校读者我要写书评

暂无评论

Journal of Computer Science & Technology 2017年第4期32卷 714-725页

作者： Meng Chen Lin-Lin Zhang Xiaohui Yu Yang Liu School of Computer Science and Technology Shandong University Jinan 250101 China School of Information Technology York University Toronto M3J 1P3 Canada

Image sentiment classification, which aims to predict the polarities of sentiments conveyed by the images, has gained a lot of attention. Most existing methods address this problem by training a general classifier with certain visual features, ignoring the discrepancies across domains. In this paper, we propose a novel weighted co-training method for cross-domain image sentiment classification, which iteratively enlarges the labeled set by introducing new high-confidence classified samples to reduce the gap between the two domains. We train two sentiment classifiers with both the images and the corresponding textual comments separately, and set the similarity between the source domain and the target domain as the weight of a classifier. We perform extensive experiments on a real Flickr dataset to evaluate the proposed method, and the empirical study reveals that the weighted co-training method significantly outperforms some baseline solutions.

关键词： sentiment classification cross-domain weighted co-training

A cross-domain Trust Model of Smart City IoT Based on Self-Certification

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Intelligent Automation & Soft Computing 2023年第4期36卷 981-996页

作者： Yao Wang Yubo Wang Zhenhu Ning Sadaqat ur Rehman Muhammad Waqas Faculty of Information Technology Beijing University of TechnologyBeijing100124China Department of Natural and Computing Science University of AberdeenUK School of Engineering Edith Cowan UniversityPerth6027Australia

Smart city refers to the information system with Intemet of things and cloud computing as the core tec hnology and government management and industrial development as the core content,forming a large scale,heterogeneous and dynamic distributed Internet of things environment between different Internet of *** is a wide demand for cooperation between equipment and management institutions in the smart ***,it is necessary to establish a trust mechanism to promote cooperation,and based on this,prevent data disorder caused by the interaction between honest terminals and malicious ***,most of the existing research on trust mechanism is divorced from the Internet of things environment,and does not consider the characteristics of limited computing and storage capacity and large differences of Internet of hings devices,resuling in the fact that the research on abstract trust trust mechanism cannot be directly applied to the Internet of things;On the other hand,various threats to the Internet of things caused by security vulnerabilities such as collision attacks are not *** at the security problems of cross domain trusted authentication of Intelligent City Internet of things terminals,a cross domain trust model(CDTM)based on self-authentication is *** most trust models,this model uses self-certiﬁed *** cross-domain process of internet of things(IoT)terminal can quickly establish a trust relationship with the current domain by providing its trust certiﬁcate stored in the previous domain *** the same time,in order to alleviate the collision attack and improve the accuracy of trust evaluation,the overall trust value is calculated by comprehensively considering the quantity weight,time attenuation weight and similarity ***,the simulation results show that CDTM has good anti collusion attack *** success rate of malicious interaction will not increase signiﬁ*** with other model

关键词： Smart city cross-domain trust model self-certiﬁcation trust evaluation

Three Heads Better than One:Pure Entity,Relation Label and Adversarial Training for cross-domain Few-shot Relation Extraction

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Data Intelligence 2023年第3期5卷 807-823页

作者： Wenlong Fang Chunping Ouyang Qiang Lin Yue Yuan School of Computer University of South ChinaHengyangHunan421001China

In this paper,we study cross-domain relation *** new data mapping to feature spaces always differs from the previously seen data due to a domain shif,few-shot relation extraction often perform *** solve the problems caused by cross-domain,we propose a method for combining the pure entity,relation labels and adversarial(PERLA).We first use entities and complete sentences for separate encoding to obtain context-independent entity ***,we combine relation labels which are useful for relation extraction to mitigate context *** combine adversarial to reduce the noise caused by *** conducted experiments on the publicly available cross-domain relation extraction dataset Fewrel 2.o[1]o,and the results show that our approach improves accuracy and has better transferability for better adaptation to cross-domain tasks.

关键词： cross-domain Adversarial Learning Prototypical Networks Pure eatity Relation label Meta-learning

Scheme on cross-domain Identity Authentication Based on Group Signature for Cloud Computing

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Wuhan University Journal of Natural Sciences 2019年第2期24卷 134-140页

作者： YANG Yanyan HU Mingsheng KONG Shan GONG Bei LIU Xinxin School of Information Science and Technology Zhengzhou Normal University

In the cloud computing, different cloud service providers are often in different trust domains. As the traditional identity authentication mode cannot be applied to the cloud computing, the cross-domain identity authentication mechanism is needed to solve the identity authentication problem in the cloud computing. In view of the security problems in cloud computing, a cross-domain identity authentication scheme based on group signature is proposed. This scheme introduces a group of cloud service providers and users who are located in different trust domains. Any member of the group can generate the signature on behalf of the whole group, making the user access the cloud service provider in the case of privacy security. At the same time, with traceability it can track illegal operation of illegal users. In addition, the scheme uses the Chinese Remainder Theorem to integrate the message, and it can control the length of the data in the calculation process, simplifying the calculation process. It also realizes the join and revocation of group members without changing the key of other legitimate group members, and the maintenance cost of authentication schemes is low. The results show that the scheme has the advantages of anonymity, anti-counterfeit, traceability, anti-joint attack and so on. It can not only realize tracking function under the condition of guaranteeing user's privacy, but can also simplify the authentication calculation process to improve the efficiency of the cross domain identity authentication, and its performance is more suitable for large-scale cloud computing environment.

关键词： cloud computing cross-domain identity authentication group signature Chinese Remainder Theorem traceability

Words alignment based on association rules for cross-domain sentiment classification

在线全文

学校读者我要写书评

暂无评论

Frontiers of Information Technology & Electronic Engineering 2018年第2期19卷 260-272页

作者： Xi-bin JIA Ya JIN Ning LI Xing SU Barry CARDIFF Bir BHANU Faculty of Information Technology Beijing University of Technology School of Electrical and Electronic Engineering University College Dublin Visualization and Intelligent Systems Laboratory University of CaliforniaRiverside

Automatic classification of sentiment data（e.g., reviews, blogs） has many applications in enterprise user management systems, and can help us understand people＇s attitudes about products or services. However, it is difficult to train an accurate sentiment classifier for different domains. One of the major reasons is that people often use different words to express the same sentiment in different domains, and we cannot easily find a direct mapping relationship between them to reduce the differences between domains. So, the accuracy of the sentiment classifier will decline sharply when we apply a classifier trained in one domain to other domains. In this paper, we propose a novel approach called words alignment based on association rules（WAAR） for cross-domain sentiment classification,which can establish an indirect mapping relationship between domain-specific words in different domains by learning the strong association rules between domain-shared words and domain-specific words in the same domain. In this way, the differences between the source domain and target domain can be reduced to some extent, and a more accurate cross-domain classifier can be trained. Experimental results on Amazon~ datasets show the effectiveness of our approach on improving the performance of cross-domain sentiment classification.

关键词： Sentiment classification cross-domain Association rules

cross-domain Industrial Process Monitoring Based on Multiple Structured Latent Transfer Dictionary Pair Learning

在线全文

学校读者我要写书评

暂无评论

Cross-Domain Industrial Process Monitoring Based on Multiple...