检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Dong, Xuewen Li, Jiachen Li, Shujun You, Zhichao Qu, Qiang Kholodov, Yaroslav Shen, Yulong School of Computer Science and Technology Xidian University The Engineering Research Center of Blockchain Technology Application and Evaluation Ministry of Education China The Shaanxi Key Laboratory of Blockchain and Secure Computing Xi’an710071 China University of Kent CanterburyCT2 7NP United Kingdom Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences China Intelligent Transportation Systems Lab Innopolis University Innopolis Russia School of Computer Science and Technology Xidian University China The Shaanxi Key Laboratory of Network and System Security Xi’an710071 China

Recent studies show that graph neural networks (GNNs) are vulnerable to backdoor attacks. Existing backdoor attacks against GNNs use fixed-pattern triggers and lack reasonable trigger constraints, overlooking individual graph characteristics and rendering insufficient evasiveness. To tackle the above issues, we propose ABARC, the first Adaptive Backdoor Attack with Reasonable Constraints, applying to both graph-level and node-level tasks in GNNs. For graph-level tasks, we propose a subgraph backdoor attack independent of the graph’s topology. It dynamically selects trigger nodes for each target graph and modifies node features with constraints based on graph similarity, feature range, and feature type. For node-level tasks, our attack begins with an analysis of node features, followed by selecting and modifying trigger features, which are then constrained by node similarity, feature range, and feature type. Furthermore, an adaptive edge-pruning mechanism is designed to reduce the impact of neighbors on target nodes, ensuring a high attack success rate (ASR). Experimental results show that even with reasonable constraints for attack evasiveness, our attack achieves a high ASR while incurring a marginal clean accuracy drop (CAD). When combined with the state-of-the-art defense randomized smoothing (RS) method, our attack maintains an ASR over 94%, surpassing existing attacks by more than 7%. Copyright © 2025, The Authors. All rights reserved.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

RobustPFL: Robust Personalized Federated Learning

引用

IEEE Transactions on Dependable and Secure Computing 2025年

作者： Chen, Guorong Wang, Wei Wu, Yufang Li, Chao Xu, Guangquan Ji, Shouling Li, Tao Shen, Meng Han, Yufei Xi'an Jiaotong University Ministry of Education Key Lab for Intelligent Networks and Network Security Xi'an China Beijing Jiaotong University 3 Shangyuancun Beijing Key Laboratory of Security and Privacy in Intelligent Transportation Beijing100044 China Tianjin University Tianjin Key Laboratory of Advanced Networking College of Intelligence and Computing Tianjin300350 China Zhejiang University College of Computer Science and Technology Hangzhou310027 China ITAI Haihe Lab Tianjin China Nankai University College of Computer Science Tianjin300350 China Beijing Institute of Technology School of Cyberspace Security Beijing100081 China Peng Cheng Laboratory Cyberspace Security Research Center Shenzhen518066 China INRIA Bretagne Rennes35042 France

Conventional federated learning (FL) coordinated by a central server focuses on training a global model and protecting the privacy of clients' training data by storing it locally. However, the statistical heterogeneity hinders the global model from adapting to the non-IID distributions among clients. Moreover, untrusted and unreliable central servers and malicious clients may compromise model integrity and availability, thus degrading the robustness of FL. To address these challenges, we present RobustPFL, a decentralized personalized federated learning (PFL) approach that combines α-based Layer-position Normalized Similarity (α-LNS) and local collaborative training to improve personalized performance while utilizing a blockchain-based committee mechanism to coordinate the aggregation process, thereby achieving high personalized accuracy and robustness. Extensive experiments show that our RobustPFL approach outperforms multiple algorithms, including Local training, FedAvg, FedReptile, Per-FedAvg, FedBN, and SPFL, on MNIST, CIFAR10, EMNIST, and N-BaIoT datasets in four non-IID settings. We also evaluate RobustPFL's effectiveness against attacks - poisoning attacks and free-riding attacks. Particularly, for three prevalent poisoning attacks (backdoor, label flipping, and model poisoning attacks), we compare non-defensive (FedAvg) and defensive (Krum, trimmed mean, Bulyan, FedBN, FLAME, and FangTrmean) methods with our proposed RobustPFL. The results show that our approach achieves significant defensive effects. © 2004-2012 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Robot and its living space:A roadmap for robot development based on the view of living space

引用

Digital Communications and networks 2021年第4期7卷 505-517页

作者： Xiaofeng Cai Huansheng Ning Sahraoui Dhelim Rongjuan Zhou Tao Zhang Yang Xu Yueliang Wan School of Computer and Communication Engineering University of Science and Technology Beijing Beijing 100083China Beijing Engineering Research Center for Cyberspace Data Analysis and Applications Beijing 100083China School of Foreign Studies University of Science and Technology Beijing Beijing 100083China Key Lab of Information Network Security Ministry of Public SecurityChina Run Technologies Co. LidBeijing China

Robot’s living space Human-robot relationship Robot humanization Hybrid intelligence Human-robot integrated society Robots,as the creation of humans,became an irreplaceable component in human *** the advancement of technologies,robots have become more and more intelligent and have been widely used in many fields,such as disease diagnosis,customer services,healthcare for the older people,and so *** robots made our lives much more convenient than ever before,they also brought many potential risks and challenges in technology,security,and *** better understand the development of robots,we proposed a concept of a robot’s living space and analyzed the role of robots in our *** this paper,we focus on setting a theoretical framework of the robot’s living space to further understand the human-robot *** research in this paper contains three central ***,we interpret the concept of the robot’s living space and the functions of each ***,we analyze and summarize the relative technologies which support robots living well in each ***,we provide advice and improvement measures based on a discussion of potential problems caused by the developments of *** the trend of robots humanization and human-robot society integration,we should seriously consider how to collaborate with intelligent robots to achieve hybrid *** build a harmonious human-robot integrated society,studying the robot’s living space and its relationship with humans is the prerequisite and roadmap.

关键词： Robot's living space Human-robot relationship Robot humanization Hybrid intelligence Human-robot integrated society

来源：评论

学校读者我要写书评

暂无评论

Learning to adapt unknown noise for hyperspectral image denoising

arXiv

引用

arXiv 2022年

作者： Rui, Xiangyu Cao, Xiangyong Shu, Jun Zhao, Qian Meng, Deyu School of Mathematics and Statistics Ministry of Education Key Lab of Intelligent Networks and Network Security Xi’an Jiaotong University NO 28 Xianning West Road Shaanxi Xi’an710049 China School of Computer Science and Technology Ministry of Education Key Lab For Intelligent Networks and Network Security Xi’an Jiaotong University NO 28 Xianning West Road Shaanxi Xi’an710049 China

For hyperspectral image (HSI) denoising task, the causes of noise embeded in an HSI are typically complex and uncontrollable. Thus, it remains a challenge for model-based HSI denoising methods to handle complex noise. To enhance the noise-handling capabilities of existing model-based methods, we resort to design a general weighted data fidelity term. The weight in this term is used to assess the noise intensity and thus elementwisely adjust the contribution of the observed noisy HSI in a denoising model. The similar concept of "weighting" has been hinted in several methods. Due to the unknown nature of the noise distribution, the implementation of "weighting" in these works are usually achieved via empirical formula for specific denoising method. In this work, we propose to predict the weight by a hyper-weight network (i.e., HWnet). The HWnet is learned exactly from several model-based HSI denoising methods in a bi-level optimization framework based on the data-driven methodology. For a noisy HSI, the learned HWnet outputs its corresponding weight. Then the weighted data fidelity term implemented with the predicted weight can be explicitly combined with a target model-based HSI denoising method. In this way, our HWnet achieves the goal of enhancing the noise adaptation ability of model-based HSI denoising methods for different noisy HSIs. Extensive experiments verify that the proposed HWnet can effecitvely help to improve the ability of an HSI denoising model to handle different complex noises. This further implies that our HWnet could transfer the noise knowledge at the model level and we also study the corresponding generalization theory for simple illustration. Copyright © 2022, The Authors. All rights reserved.

关键词： Image denoising

来源：评论

学校读者我要写书评

暂无评论

A Low-rank Matching Attention based Cross-modal Feature Fusion Method for Conversational Emotion Recognition

arXiv

引用

arXiv 2023年

作者： Shou, Yuntao Liu, Huan Cao, Xiangyong Meng, Deyu Dong, Bo School of Computer Science and Technology The Ministry of Education Key Laboratory for Intelligent Networks and Network Security The Shaanxi Province Key Laboratory of Big Data Knowledge Engineering Xi’an Jiaotong Shaanxi Xi’an710049 China School of Computer Science and Technology Xi’an Jiaotong Shaanxi Xi’an710049 China The BigKE Joint Innovation Center SHMEEA Shanghai China School of Mathematics and Statistics Xi’an Jiaotong University Xi’an China

Conversational emotion recognition (CER) is an important research topic in human-computer interactions. Although recent advancements in transformer-based cross-modal fusion methods have shown promise in CER tasks, they tend to overlook the crucial intra-modal and inter-modal emotional interaction or suffer from high computational complexity. To address this, we introduce a novel and lightweight cross-modal feature fusion method called Low-Rank Matching Attention Method (LMAM). LMAM effectively captures contextual emotional semantic information in conversations while mitigating the quadratic complexity issue caused by the self-attention mechanism. Specifically, by setting a matching weight and calculating inter-modal features attention scores row by row, LMAM requires only one-third of the parameters of self-attention methods. We also employ the low-rank decomposition method on the weights to further reduce the number of parameters in LMAM. As a result, LMAM offers a lightweight model while avoiding overfitting problems caused by a large number of parameters. Moreover, LMAM is able to fully exploit the intra-modal emotional contextual information within each modality and integrates complementary emotional semantic information across modalities by computing and fusing similarities of intra-modal and inter-modal features simultaneously. Experimental results verify the superiority of LMAM compared with other popular cross-modal fusion methods on the premise of being more lightweight. Also, LMAM can be embedded into any existing state-of-the-art CER methods in a plug-and-play manner, and can be applied to other multi-modal recognition tasks, e.g., session recommendation and humour detection, demonstrating its remarkable generalization ability. Copyright © 2023, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Splicer+: Secure Hub Placement and Deadlock-Free Routing for Payment Channel network Scalability

arXiv

引用

arXiv 2025年

作者： Yang, Lingxiao Dong, Xuewen Wang, Wei Gao, Sheng Qu, Qiang Tian, Wensheng Shen, Yulong The School of Computer Science and Technology Xidian University Xi’an710071 China The Shaanxi Key Laboratory of Network and System Security Xi’an710071 China The Beijing Key Laboratory of Security and Privacy in Intelligent Transportation Beijing Jiaotong University Beijing100044 China The School of Information Central University of Finance and Economics Beijing100081 China The Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen518055 China The Huawei Blockchain Lab Huawei Cloud Tech Co. Ltd. Shenzhen518055 China The Nanhu Lab Jiaxing314001 China The Cryptology and Computer Security Laboratory Shanghai Jiao Tong University Shanghai200240 China

Payment channel hub (PCH) is a promising approach for payment channel networks (PCNs) to improve efficiency by deploying robust hubs to steadily process off-chain transactions. However, existing PCHs, often preplaced without considering payment request distribution across PCNs, can lead to load imbalance. PCNs' reliance on source routing, which makes decisions based solely on individual sender requests, can degrade performance by overlooking other requests, thus further impairing scalability. In this paper, we introduce Splicer+, a highly scalable multi-PCH solution based on the trusted execution environment (TEE). We study tradeoffs in communication overhead between participants, transform the original NP-hard PCH placement problem by mixed-integer linear programming, and propose optimal/approximate solutions with load balancing for different PCN scales using supermodular techniques. Considering global PCN states and local directly connected sender requests, we design a deadlock-free routing protocol for PCHs. It dynamically adjusts the payment processing rate across multiple channels and, combined with TEE, ensures high-performance routing with confidential computation. We provide a formal security proof for the Splicer+ protocol in the UC-framework. Extensive evaluations demonstrate the effectiveness of Splicer+, with transaction success ratio (↑51.1%), throughput (↑181.5%), and latency outperforming state-of-the-art PCNs. Copyright © 2025, The Authors. All rights reserved.

关键词： Scalability

来源：评论

学校读者我要写书评

暂无评论

Detecting Inconsistent Vulnerable Software Version in security Vulnerability Reports 1

引用

4th International Conference on Frontiers in Cyber security, FCS 2021

作者： Ren, Hansong Li, Xuejun Lei, Liao Ou, Guoliang Sun, Hongyu Wu, Gaofei Tian, Xiao Hu, Jinglu Zhang, Yuqing School of Cyber Engineering Xidian University Shaanxi Xian710126 China Guangxi Key Laboratory of Cryptography and Information Security Guilin University of Electronic Technology Guangxi Guilin541010 China National Computer Network Intrusion Prevention Center University of Chinese Academy of Sciences Beijing100049 China School of Information Production and Systems Waseda University Tokyo169-805 Japan College of Computer and Cyberspace Security Hainan University Haikou570228 China

ISBN: (数字)9789811905230

ISBN: (纸本)9789811905223

At present, the vulnerability database research has mainly focused on whether the disclosed information is accurate. However, the information differences between the various vulnerability databases have received little attention. This article proposes a WITTY (softWare versIon inconsisTency measuremenT sYstem) to detect the differences between the affected software versions of NVD and different language vulnerability databases (including English CVE, OpenWall, Chinese CNNVD, CNVD, and other eight databases). WITTY can enable Our large-scale quantitative information consistency. We introduce named entity recognition (NER) and relation extraction (RE) based on deep learning. We present custom design into named entity recognition (NER) and relation extraction (RE) based on deep learning, enabling WITTY to recognize previously invisible software names and versions based on sentence structure and context. Ground-truth shows that the system has a high accuracy rate (95.3% accuracy rate, 89.9% recall rate). We use data from 8 vulnerability databases in the past 21 years, involving 554,725 vulnerability reports. The results show that they are inconsistent. The software version is prevalent. The average exact match rate of English vulnerability databases CVE, OpenWall, and other vulnerability databases with cve is only 22.1%. The average exact match rate of Chinese CNNVD and CNVD is 49.5%, and the excat match rate of Russian vulnerability databases is 25.8%. © 2022, Springer Nature Singapore Pte Ltd.

关键词： Database systems

来源：评论

学校读者我要写书评

暂无评论

Adaptive Loose Optimization for Robust Question Answering

arXiv

引用

arXiv 2023年

作者： Ma, Jie Wang, Pinghui Wang, Zewei Kong, Dechen Hu, Min Han, Ting Liu, Jun The Ministry of Education of Key Laboratory for Intelligent Networks and Network Security School of Cyber Science and Engineering Xi’an Jiaotong University Shaanxi Xi’an710049 China The Ministry of Education of Key Laboratory for Intelligent Networks and Network Security School of Automation Science and Engineering Xi’an Jiaotong University Shaanxi Xi’an710049 China The China Mobile Research Institute China The Shannxi Provincial Key Laboratory of Big Data Knowledge Engineering School of Computer Science and Technology Xi’an Jiaotong University Shaanxi Xi’an710049 China

Question answering methods are well-known for leveraging data bias, such as the language prior in visual question answering and the position bias in machine reading comprehension (extractive question answering). Current debiasing methods often come at the cost of significant in-distribution performance to achieve favorable out-of-distribution generalization ability, while non-debiasing methods sacrifice a considerable amount of out-of-distribution performance in order to obtain high in-distribution performance. Therefore, it is challenging for them to deal with the complicated changing real-world situations. In this paper, we propose a simple yet effective novel loss function with adaptive loose optimization, which seeks to make the best of both worlds for question answering. Our main technical contribution is to reduce the loss adaptively according to the ratio between the previous and the current optimization state on mini-batch training data. This loose optimization can be used to prevent non-debiasing methods from overlearning data bias while enabling debiasing methods to maintain slight bias learning. Experiments on the visual question answering datasets, including VQA v2, VQA-CP v1, VQA-CP v2, GQA-OOD, and the extractive question answering dataset SQuAD demonstrate that our approach enables QA methods to obtain state-of-the-art in- and out-of-distribution performance in most cases. The source code has been released publicly in https://***/reml-group/ALO. Copyright © 2023, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

An Ensemble of CapsNet and KSVM Using Feature Fusion: Application to COVID-19 Detection 3

An Ensemble of CapsNet and KSVM Using Feature Fusion: Applic...

引用

3rd International Conference on Pattern Recognition and Machine Learning, PRML 2022

作者： Aggrey, Esther Stacy E. B. Zhen, Qin Kodjiku, Seth Larweh Aidoo, Evans Fiasam, Linda Delali Mensah, Acheampong Edward University of Electronic Science & Technology of China School of Information & Software Engineering Chengdu China University of Electronic Science & Technology of China School of Information & Software Engineering Network and Data Security Key Lab of Sichuan Province Chengdu China Zhejiang Gongshang University School of Computer & Information Engineering Hangzhou China

ISBN: (数字)9781665499507

ISBN: (纸本)9781665499507

COVID-19 virus is a major worldwide pandemic that is growing at a fast pace throughout the world. The usual approach for diagnosing COVID-19 is the use of a real-time polymerase chain reaction (RT-PCR) based nucleic acid test. However, RT-PCR has lower sensitivity in the early phases of COVID-19 detection. Recent studies have indicated that X-ray images may be useful throughout the early detection of the virus. Human screening has been shown to be cost-effective, susceptible to mistakes, and time-demanding, which has sparked an interest in using Convolutional Neural networks (CNNs) to automate the process. CNNs, on the other hand, fail to view the exact placement of features as advantageous in medical imaging. Furthermore, for successful training and prediction, CNNs need a huge quantity of datasets. CNNs are rapidly reducing picture resolution, resulting in worsening accuracy in classification. We used newly created capsule networks (CapsNets) in our study to circumvent these disadvantages. The primary contribution is to improve the identification of SARS-CoV-2 with images obtained from X-ray by coupling capsule network with a kernel support vector machine (KSVM). The technique was evaluated using a publicly available dataset, and the proposed model shows that the accuracy of the CapsNet-KSVM based model is improved by 94.6% accuracy, 95% sensitivity, and 98% specificity, which outperforms the traditional CNN and other existing ensemble models. The proposed CapsNet-KSVM based system can be employed to identify the presence of COVID-19 in the human body using X-ray images. © 2022 IEEE.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Using Depth-Enhanced Spatial Transformation for Student Gaze Target Estimation in Dual-View Classroom Images

Using Depth-Enhanced Spatial Transformation for Student Gaze...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Haonan Miao Peizheng Zhao Yuqi Sun Fang Nan Xiaolong Zhang Yaqiang Wu Feng Tian School of Computer Science and Technology Xi’an Jiaotong University Xi’an China Ministry of Education Key Laboratory of Intelligent Networks and Network Security Xi’an Jiaotong University Xi’an China School of Advanced Technology Xi’an Jiaotong-Liverpool University Suzhou China Shaanxi Province Key Laboratory of Big Data Knowledge Engineering Xi’an Jiaotong University Xi’an China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Dual-view gaze target estimation in classroom environments has not been thoroughly explored. Existing methods lack consideration of depth information, primarily focusing on 2D image information and neglecting the latent 3D spatial context, which could lead to suboptimal transformation and cause the gaze cone to intersect with an incorrect object. This paper introduces a novel dual-view gaze target estimation method tailored for classroom settings, leveraging depth-enhanced spatial transformations. By formulating a depth-enhanced 2D space, our method uses depth-enhanced spatial transformation to accurately project students’ gaze cones to the teacher-oriented image. Additionally, we collected a dataset named DVSGE, specifically for student gaze target estimation in dual-view classroom images. Experimental results demonstrate significant performance improvements of 9.8% in AUC and 19.9% in L2-Distance for our method, surpassing existing methods.

关键词： Three-dimensional displays Estimation Focusing Signal processing Acoustics Speech processing

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：