检索结果-内蒙古大学图书馆

Challenges and future directions of secure federated learning:a survey

Frontiers of computer science 2022年第5期16卷 173-180页

作者： Kaiyue ZHANG Xuan SONG Chenhan ZHANG Shui YU Department of Computer Science and Engineering Southern University of Science and TechnologyShenzhen 518055China Faculty of Engineering and Information Technology University of Technology SydneySydney 2007Australia SUSTech-UTokyo Joint Research Center on Super Smart City Department of Computer Science and EngineeringSouthern University of Science and TechnologyShenzhen 518055China Guangdong Provincial Key Laboratory of Brain-inspired Intelligent Computation Department of Computer Science and EngineeringSouthern University of Science and TechnologyShenzhen 518055China

Federated learning came into being with the increasing concern of privacy security,as people’s sensitive information is being exposed under the era of big *** is an algorithm that does not collect users’raw data,but aggregates model parameters from each client and therefore protects user’s ***,due to the inherent distributed nature of federated learning,it is more vulnerable under attacks since users may upload malicious data to break down the federated learning *** addition,some recent studies have shown that attackers can recover information merely from ***,there is still lots of room to improve the current federated learning *** this survey,we give a brief review of the state-of-the-art federated learning techniques and detailedly discuss the improvement of federated *** open issues and existing solutions in federated learning are *** also point out the future research directions of federated learning.

关键词： federated learning privacy protection security

来源：评论

学校读者我要写书评

暂无评论

Towards optimized tensor code generation for deep learning on sunway many-core processor

引用

Frontiers of computer science 2024年第2期18卷 1-15页

作者： Mingzhen LI Changxi LIU Jianjin LIAO Xuegui ZHENG Hailong YANG Rujun SUN Jun XU Lin GAN Guangwen YANG Zhongzhi LUAN Depei QIAN State Key Laboratory of Software Development Environment Beijing 100191China School of Computer Science and Engineering Beihang UniversityBeijing 100191China National University of Singapore Singapore 119077Singapore State Key Laboratory of Mathematical Engineering and Advanced Computing Wuxi 214000China Science and Technology on Special System Simulation Laboratory Beijing Simulation Center Beijing 100854China Department of Computer Science and Technology Tsinghua UniversityBeijing 100084China

The flourish of deep learning frameworks and hardware platforms has been demanding an efficient compiler that can shield the diversity in both software and hardware in order to provide application *** the existing deep learning compilers,TVM is well known for its efficiency in code generation and optimization across diverse hardware *** the meanwhile,the Sunway many-core processor renders itself as a competitive candidate for its attractive computational power in both scientific computing and deep learning *** paper combines the trends in these two ***,we propose swTVM that extends the original TVM to support ahead-of-time compilation for architecture requiring cross-compilation such as *** addition,we leverage the architecture features during the compilation such as core group for massive parallelism,DMA for high bandwidth memory transfer and local device memory for data locality,in order to generate efficient codes for deep learning workloads on *** experiment results show that the codes generated by swTVM achieve 1.79x improvement of inference latency on average compared to the state-of-the-art deep learning framework on Sunway,across eight representative *** work is the first attempt from the compiler perspective to bridge the gap of deep learning and Sunway processor particularly with productivity and efficiency in *** believe this work will encourage more people to embrace the power of deep learning and Sunwaymany-coreprocessor.

关键词： sunway processor deep learning compiler code generation performance optimization

来源：评论

学校读者我要写书评

暂无评论

Diverse Co-saliency Feature Learning for Text-Based Person Retrieval

引用

IEEE Transactions on Information Forensics and Security 2025年 20卷 5465-5477页

作者： You, Shuai Chen, Cuiqun Feng, Yujian Liu, Hai Ji, Yimu Ye, Mang School of Internet of Things Nanjing China Anhui University School of Computer Science and Technology Hefei China South China Normal University school of computer Guangdong China NJUPT School of Computer Science Nanjing China Wuhan University National Engineering Research Center for Multimedia Software Hubei Key Laboratory of Multimedia and Network Communication Engineering Institute of Artificial Intelligence School of Computer Science Wuhan430072 China

Text-based Person Retrieval (TPR) plays a pivotal role in video surveillance systems for safeguarding public safety. As a fine-grained retrieval task, TPR faces the significant challenge of precisely capturing highly discriminative features across image and text modalities. Existing methods primarily focus on establishing modality-shared feature spaces to bridge cross-modal discrepancies. However, these methods are prone to disturbances from irrelevant information, such as background noises in the visual modality, and often over-emphasize specific local regions while neglecting the capture of diverse discriminative modal features, thereby limiting the robustness of cross-modal matching. In this paper, we introduce a novel framework, termed the Diverse Co-saliency Feature Learning Network (DCFL), which mines the co-saliency information between image and text modalities and enhances the diversity of cross-modal discriminative features while mitigating the interference of noise. Specifically, to construct cross-modal co-saliency features, we devise the Intra-modal Saliency Feature Learning (ISFL) and Cross-modal Saliency Feature Matching (CSFM) modules. ISFL employs a weighted mask mechanism to guide the model in reducing the impact of noise information in both modalities. Complementing ISFL, CSFM establishes consistent relationships between saliency features across modalities, leveraging text descriptions to align pedestrian-relevant visual regions. Furthermore, we propose the Diverse Co-saliency Feature Mining (DCFM) to bolster the diversity of discriminative co-saliency features across both image and text modalities. This module integrates a diversity regularization term, enabling the extraction of varied visual cues and capturing comprehensive features of the target individual. Extensive benchmark experiments demonstrate a substantial superiority of our approach over the state-of-the-art methods. The code will be released publicly. © 2005-2012 IEEE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Object Counting Using a Refinement Network

引用

Tsinghua science and technology 2022年第5期27卷 869-879页

作者： Lehan Sun Junjie Ma Liping Jing School of Science Beijing Jiaotong UniversityBeijing 100044China Department of Computer Science and Technology and Beijing National Research Center for Information Science and Technology(BNRist)Tsinghua UniversityBeijing 100084China School of Computer and Information Technology Beijing Jiaotong UniversityBeijing 100044China

To address the scale variance and uneven distribution of objects in scenarios of object-counting tasks,an algorithm called Refinement Network(RefNet) is *** proposed top-down scheme sequentially aggregates multiscale features,which are laterally connected with low-level *** by a multiresolution density regression loss,a set of intermediate-density maps are estimated on each scale in a multiscale feature pyramid,and the detailed information of the density map is gradually added through coarse-to-fine granular refinement progress to predict the final density *** evaluate our RefNet on three crowd-counting benchmark datasets,namely,ShanghaiTech,UCFC0,and UCSD,and our method achieves competitive performances on the mean absolute error and root mean squared error compared to the state-of-the-art *** further extend our RefNet to cell counting,illustrating its effectiveness on relative counting tasks.

关键词： object counting Refinement Network(RefNet) scale variation uneven distribution

来源：评论

学校读者我要写书评

暂无评论

Semantic and secure search over encrypted outsourcing cloud based on BERT

引用

Frontiers of computer science 2022年第2期16卷 152-159页

作者： Zhangjie FU Yan WANG Xingming SUN Xiaosong ZHANG Engineering Research Center of Digital Forensice Ministry of EducationNanjing University of Information Science and TechnologyNanjing 210044China School of Computer and Software Nanjing University of Information Science and TechnologyNanjing 210044China School of Computer Science and Engineering University of Electronic Science and Technology of ChinaChengdu 611731China

Searchable encryption provides an effective way for data security and privacy in cloud *** can retrieve encrypted data in the cloud under the premise of protecting their own data security and ***,most of the current content-based retrieval schemes do not contain enough semantic information of the article and cannot fully reflect the semantic information of the *** this paper,we propose two secure and semantic retrieval schemes based on BERT(bidirectional encoder representations from transformers)named SSRB-1,*** training the documents with BERT,the keyword vector is generated to contain more semantic information of the documents,which improves the accuracy of retrieval and makes the retrieval result more consistent with the user’s ***,through testing on real data sets,it is shown that both of our solutions are feasible and effective.

关键词： cloud computing semantic search BERT model searchable encryption

来源：评论

学校读者我要写书评

暂无评论

Secure RFID-Assisted Authentication Protocol for Vehicular Cloud Computing Environment

引用

IEEE Transactions on Intelligent Transportation Systems 2024年第9期25卷 12528-12537页

作者： Saleem, Muhammad Asad Li, Xiong Mahmood, Khalid Tariq, Tayyaba Alenazi, Mohammed J. F. Das, Ashok Kumar University of Electronic Science and Technology of China School of Computer Science and Engineering Chengdu611731 China Institute for Cyber Security School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu611731 China Sichuan University Key Laboratory of Data Protection and Intelligent Management Ministry of Education Chengdu610065 China Shenzhen Institute for Advanced Study University of Electronic Science and Technology of China Shenzhen518000 China National Yunlin University of Science and Technology Graduate School of Intelligent Data Science Yunlin Douliu64002 Taiwan National Yunlin University of Science and Technology Graduate School of Engineering Science and Technology Yunlin Douliu64002 Taiwan King Saud University College of Computer and Information Sciences Department of Computer Engineering Riyadh11451 Saudi Arabia International Institute of Information Technology Center for Security Theory and Algorithmic Research Hyderabad500032 India

Vehicular network technology has made substantial advancements in recent years in the field of Intelligent Transportation Systems. Vehicular Cloud Computing (VCC) has emerged as a novel paradigm with a substantial increase in data exchange within Vehicular ad-hoc networks (VANETs). VCC integrates cloud computing, vehicular networking, and Internet of Things (IoT) technologies. It enables Infrastructure-to-Vehicle (I2V), Vehicle-to-Vehicle (V2V), and Vehicle-to-Device (V2D) communication. VCC optimizes vehicle, cloud infrastructure, and IoT resources while addressing significant communication security and vehicle-user privacy challenges. To address these issues, we developed an RFID-based authentication protocol for VCC based on a Henon map using a hash function. In addition, we also incorporated a Physical Unclonable Function (PUF) to resist physical tampering attacks. We validate the protocol's security formally and informally. The formal security analysis is conducted through a widely used RoR model. We use the Scyther simulation tool to verify the proposed protocol's security against various attacks. Moreover, we compare the performance of our protocol with similar existing protocols across important performance parameters such as communication and computation overheads and security attributes. The proposed protocol yields substantial improvements, demonstrating a 40.74% reduction in computation overhead and a 13.03% decrease in communication overhead as compared to related protocols, delivering both enhanced performance and resource efficiency. The analysis demonstrates its capacity to support secure communication in the VCC environment and satisfy desirable security attributes. © 2024 IEEE.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

Key Agreement and Management Scheme Based on Blockchain for 5G-Enabled Vehicular Networks

引用

China Communications 2025年第3期22卷 270-287页

作者： Wang Zhihua Wang Shuaibo Wang Haofan Li Jiaze Yao Yizhe Wang Yongjian Yang Xiaolong School of Computer and Communication Engineering University of Science and Technology BeijingBeijing 100083China School of Cyber Science and Engineering Zhengzhou UniversityZhengzhou 449001China Lab of National Computer Network Emergency Response Technical Team/Coordination Center of China Beijing 100029China

5G technology has endowed mobile communication terminals with features such as ultrawideband access,low latency,and high reliability transmission,which can complete the network access and interconnection of a large number of devices,thus realizing richer application scenarios and constructing 5G-enabled vehicular ***,due to the vulnerability of wireless communication,vehicle privacy and communication security have become the key problems to be solved in vehicular ***,the large-scale communication in the vehicular networks also makes the higher communication efficiency an inevitable *** order to achieve efficient and secure communication while protecting vehicle privacy,this paper proposes a lightweight key agreement and key update scheme for 5G vehicular networks based on ***,the key agreement is accomplished using certificateless public key cryptography,and based on the aggregate signature and the cooperation between the vehicle and the trusted authority,an efficient key updating method is proposed,which reduces the overhead and protects the privacy of the vehicle while ensuring the communication ***,by introducing blockchain and using smart contracts to load the vehicle public key table for key management,this meets the requirements of vehicle traceability and can dynamically track and revoke misbehaving ***,the formal security proof under the eck security model and the informal security analysis is conducted,it turns out that our scheme is more secure than other authentication schemes in the vehicular *** analysis shows that our scheme has lower overhead than existing schemes in terms of communication and computation.

关键词： blockchain certificateless public key cryptography 5G vehicular networks key agreement key management

来源：评论

学校读者我要写书评

暂无评论

Self-adaptive label filtering learning for unsupervised domain adaptation

引用

Frontiers of computer science 2023年第1期17卷 225-227页

作者： Qing TIAN Heyang SUN Shun PENG Tinghuai MA School of Computer and Software Nanjing University of Information Science and TechnologyNanjing 210044China Engineering Research Center of Digital Forensics Ministry of EducationNanjing University of Information Science and TechnologyNanjing 210044China

1 Introduction As an emerging machine learning paradigm,unsupervised domain adaptation(UDA)aims to train an effective model for unlabeled target domain by leveraging knowledge from related but distribution-inconsistent source *** of the existing UDA methods[2]align class-wise distributions resorting to target domain pseudo-labels,for which hard labels may be misguided by misclassifications while soft labels are confusing with trivial noises so that both of them tend to cause frustrating *** overcome such drawbacks,as shown in Fig.1,we propose to achieve UDA by performing self-adaptive label filtering learning(SALFL)from both the statistical and the geometrical perspectives,which filters out the misclassified pseudo-labels to reduce negative ***,the proposed SALFL firstly predicts labels for the target domain instances by graph-based random walking and then filters out those noise labels by self-adaptive learning strategy.

关键词： filtering resort overcome

来源：评论

学校读者我要写书评

暂无评论

Post-hoc Part-prototype Networks 41

Post-hoc Part-prototype Networks

引用

41st International Conference on Machine Learning, ICML 2024

作者： Tan, Andong Zhou, Fengtao Chen, Hao Department of Computer Science and Engineering Hong Kong University of Science and Technology Hong Kong Center for Aging Science HKUST Hong Kong

Post-hoc explainability methods such as Grad-CAM are popular because they do not influence the performance of a trained model. However, they mainly reveal "where" a model looks at for a given input, fail to explain "what" the model looks for (e.g., what is important to classify a bird image to a Scott Oriole?). Existing part-prototype networks leverage part-prototypes (e.g., characteristic Scott Oriole’s wing and head) to answer both "where" and "what", but often under-perform their black box counterparts in the accuracy. Therefore, a natural question is: can one construct a network that answers both "where" and "what" in a post-hoc manner to guarantee the model’s performance? To this end, we propose the first post-hoc part-prototype network via decomposing the classification head of a trained model into a set of interpretable part-prototypes. Concretely, we propose an unsupervised prototype discovery and refining strategy to obtain prototypes that can precisely reconstruct the classification head, yet being interpretable. Besides guaranteeing the performance, we show that our network offers more faithful explanations qualitatively and yields even better part-prototypes quantitatively than prior part-prototype networks. Copyright 2024 by the author(s)

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Sentiment Analysis of Low-Resource Language Literature Using Data Processing and Deep Learning

引用

computers, Materials & Continua 2024年第4期79卷 713-733页

作者： Aizaz Ali Maqbool Khan Khalil Khan Rehan Ullah Khan Abdulrahman Aloraini Department of IT and Computer Science Pak-Austria Fachhochschule:Institute of Applied Sciences and TechnologyHaripur22620Pakistan Software Competence Center Hagenberg Softwarepark 32aHagenberg4232Austria Department of Computer Science School of Engineering and Digital SciencesNazarbayev UniversityAstana010000Kazakhstan Department of Information Technology College of ComputerQassim UniversityP.O.Box 1162BuraydahSaudi Arabia

Sentiment analysis, a crucial task in discerning emotional tones within the text, plays a pivotal role in understandingpublic opinion and user sentiment across diverse *** numerous scholars conduct sentiment analysisin widely spoken languages such as English, Chinese, Arabic, Roman Arabic, and more, we come to grapplingwith resource-poor languages like Urdu literature which becomes a challenge. Urdu is a uniquely crafted language,characterized by a script that amalgamates elements from diverse languages, including Arabic, Parsi, Pashtu,Turkish, Punjabi, Saraiki, and more. As Urdu literature, characterized by distinct character sets and linguisticfeatures, presents an additional hurdle due to the lack of accessible datasets, rendering sentiment analysis aformidable undertaking. The limited availability of resources has fueled increased interest among researchers,prompting a deeper exploration into Urdu sentiment analysis. This research is dedicated to Urdu languagesentiment analysis, employing sophisticated deep learning models on an extensive dataset categorized into fivelabels: Positive, Negative, Neutral, Mixed, and Ambiguous. The primary objective is to discern sentiments andemotions within the Urdu language, despite the absence of well-curated datasets. To tackle this challenge, theinitial step involves the creation of a comprehensive Urdu dataset by aggregating data from various sources such asnewspapers, articles, and socialmedia comments. Subsequent to this data collection, a thorough process of cleaningand preprocessing is implemented to ensure the quality of the data. The study leverages two well-known deeplearningmodels, namely Convolutional Neural Networks (CNN) and Recurrent Neural Networks (RNN), for bothtraining and evaluating sentiment analysis performance. Additionally, the study explores hyperparameter tuning tooptimize the models’ efficacy. Evaluation metrics such as precision, recall, and the F1-score are employed to assessthe effectiv

关键词： Urdu sentiment analysis convolutional neural networks recurrent neural network deep learning natural language processing neural networks

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：