检索结果-内蒙古大学图书馆

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

作者： Zan Mao Xin Li Ze Luo Yingjuan Tang Dongmei Jiang Computer Network Information Center Chinese Academy of Sciences University of the Chinese Academy of Sciences PengCheng Laboratory National Key Laboratory of Advanced Vehicle Integration and Control Beijing Institute of Technology

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Currently, many change detection (CD) methods rely on supervised learning, which necessitates extensive manually annotated data, resulting in significant labor and time requirements. Recently, semi-supervised (SS) approaches have emerged in the CD community, which exploit large amounts of unlabeled data by utilizing consistency regularization. However, these methods do not consider the broader perturbation consistency to confer better generalization of the model. In this paper, we propose a novel SS CD framework with a comprehensive perturbation consistency called CPC, which extends perturbation consistency to the entire learning period. Specifically, our CPC combines the input, feature, and network perturbations for comprehensive perturb space. And, we design two distinct structures in practice, decoupled CPC and coupled CPC. Furthermore, we propose a change-aware input perturbation that introduces expensive annotation information to further expand the input perturb space. Extensive experiments conducted on the WHUCD, and GZ-CD datasets demonstrate that the proposal performs favorably against the state-of-the-art methods.

关键词： Codes Annotations Perturbation methods Supervised learning Signal processing Acoustics Proposals Labeling Speech processing Remote sensing

来源：评论

学校读者我要写书评

暂无评论

THC-DL: Three-Party Homomorphic Computing Delegation Learning for Secure Optimization

引用

IEEE Internet of Things Journal 2025年

作者： Yang, Ze Tian, Youliang Xiong, Jinbo Niu, Kun Li, Mengqian Zhang, Xinyu Ma, Jianfeng Guizhou University Guizhou Provincial Key Laboratory of Cryptography and Blockchain Technology College of Computer Science and Technology Guiyang550025 China Guizhou University College of Big Data and Information Engineering Guiyang550025 China Fujian Normal University Fujian Provincial Key Laboratory of Network Security and Cryptology College of Computer and Cyber Security Fuzhou350117 China Xidian University State Key Laboratory of Integrated Services Network Xi’an710071 China Xidian University State Key Laboratory of Integrated Services Network School of Cyber Engineering Xi’an710071 China

Delegation Learning(DL) flourishes data sharing, enabling agents to delegate data to the cloud for model training. To preserve privacy, homomorphic encryption (HE) offers an effective solution for privacy-preserving machine learning (PPML) in delegation learning, yet faces critical challenges in functionality (non-linear activation support), practicality (ciphertext blow-up from iterative computations), and security (data leakage risks caused by public knowledge of the mathematical principles applied in model training). To tackle these challenges, we propose THC-DL, a three-party HE framework addressing these challenges holistically for the first time. We elaborately design the ciphertext secure comparison (DL-CSC) protocol to satisfy secure comparison with private inputs, enabling efficient non-linear operations with O(1) communication complexity that reduces runtime to 12.5% of the DGK (Dolev-Greensmith-Kent protocol, the well-known comparison protocol). Second, we construct a Truncation-Mapping (Tru-Map) scheme, a mechanism that transforms input data by truncating and mapping it into a domain that facilitates more efficient processing, and the addition of truncated mapped data to resolve ciphertext blow-up by adaptively scaling ciphertexts during iterative training, ensuring correctness. Third, we formalize data leakage risks in HE-based quadratic convex optimization (standard in ML) and apply THC-DL to construct a secure optimization scheme. Theoretical analysis confirms THC-DL’s resilience against input recovery attacks, even when adversaries exploit public model parameters. Experiments on a real-world platform validate DL-CSC’s efficiency and scalability while reducing the computational complexity and communication complexity from O(n) to O(1) where n denotes the length of the input bits. © 2014 IEEE.

关键词： Convex optimization

来源：评论

学校读者我要写书评

暂无评论

Research on the Design of Government Data Governance Evaluation System under the Perspective of Digital Government 9

Research on the Design of Government Data Governance Evaluat...

引用

9th IEEE International Conference on Data Science in Cyberspace, DSC 2024

作者： Xu, Zirui Sun, Jinyang Lu, Zhe Han, Delong Qilu University of Technology Shandong Academy of Sciences Information Research Institute Shandong Academy of Sciences Jinan China SHANDONG SCICOM Information and Economy Research Institute Co. Ltd. Jinan China Qilu University of Technology Shandong Academy of Sciences Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center National Supercomputer Center in Jinan Jinan China

ISBN: (纸本)9798350391367

In the context of the digital era, government data governance is a key factor in promoting the modernization of government governance, but there is a lack of a complete set of evaluation index system to standardize the content and scope of government data governance. This paper adopts the policy tool theory to code and analyze the 12 policies from the three policy tool dimensions of supply layer, demand layer, and environment layer, and proposes three first-level evaluation indicators of basic environment, actual effectiveness, and safeguard mechanism, on the basis of which the evaluation content is selected in a focused manner based on the integration of policy documents related to data governance. Meanwhile, a comprehensive, scientific and objective evaluation system of government data governance is constructed by adopting assessment means combining subjectivity and objectivity, and quantitative and qualitative. The system is designed to assess and guide the data governance practices of the domestic government, point out the direction for government departments at all levels to carry out data governance, and play an important role in promoting the transparency and efficiency of data management. © 2024 IEEE.

关键词： data governance digital government government information indicator system policy tools

来源：评论

学校读者我要写书评

暂无评论

A two Stage Mixed Integer Programming Model for Distributionally Robust State Based Non-Intrusive Load Monitoring

引用

IEEE Transactions on Consumer Electronics 2025年

作者： Zhang, Chen Chai, Zimo Yang, Linfeng University of Shanghai for Science and Technology School of Mechanical Engineering Shanghai China Guangxi University School of Computer Electronics and Information the Guangxi Key Laboratory of Multimedia Communication and Network Technology Nanning China

This paper presents a non-intrusive load monitoring (NILM) model based on two-stage mixed-integer linear programming theory. Compared with other mixed integer optimization-based models, this paper model introduces fewer integer variables and richer absolute error function of load decomposition, which makes the power state selection of each device more accurate and the power consumption more accurate fitting. First, to tackle the issues related to noisy load data, an innovative load feature extraction model based on Kullback-Leibler distributionally robust optimization principles is introduced. Then the key features (power boundary/fluctuation features) of each device identified through this robust model are integrated into the constraints of the two-stage NILM model. The two-stage complementary framework includes: the determination of device state interval in the first stage;and the accurate fitting of device power consumption within the device state interval in the second stage. Comparative validation against existing optimization-based models on the AMPds, REFIT, and actual laboratory data sets demonstrate that our proposed model significantly enhances power decomposition accuracy and computational efficiency. In addition, the two-stage complementary framework and load feature extraction model can be applied to other optimization-based models of NILM to improve the computational efficiency of each model and the accuracy of load decomposition. © 2025 IEEE.

关键词： Mixed-integer linear programming

来源：评论

学校读者我要写书评

暂无评论

A Novel Classical-Quantum Transfer Learning Framework for Image Recognition

SSRN

引用

SSRN 2024年

作者： Ruan, Banyao Liu, Zhihao Li, Xi School of Computer Science and Engineering Southeast University Nanjing211189 China Key Laboratory of Computer Network and Information Integration Southeast University Ministry of Education Nanjing211189 China

With the advent of the era of Noisy Intermediate-Scale quantum (NISQ), quantum processors have demonstrated clear quantum supremacy, marking a new milestone in the development of quantum computing. At the same time, classical deep learning algorithms have been widely used in many fields such as image recognition and natural language processing. In this context, the Classical-Quantum transfer learning (CQ-TL) method, which combines the advantages of quantum computing and classical deep learning algorithms, emerged. In view of the problem of unclear quantum advantage in the existing CQ-TL framework, this paper proposes a novel CQ-TL framework based on amplitude encoding and effective learning algorithm is given. It not only has the flexibility of the existing framework, but also reduces the number of classical parameters, and can better demonstrate quantum advantages. Based on the CQ-TL framework, we designed and implemented two CQ-TL neural network models: named Transfer Learning Quantum Neural network (TLQNN) and Transfer Learning Quantum Convolutional Neural network (TLQCNN). TLQNN is structurally similar to a multi-layer feedforward neural network, and it achieves feature extraction through repeated quantum unit layers (ansatz). TLQCNN, on the other hand, employs quantum convolution and quantum pooling operations, which can effectively alleviate the effects of the barren plateau phenomenon, making it highly trainable and possessing great potential for practical applications. In cross-experiments with three benchmark datasets (MNIST, Fashion-MNIST and CIFAR10) and three source models (ResNet18, ResNet50 and DenseNet121), the two models have exceeded the benchmark classical classifier in many performance measures such as accuracy, convergence, stability and generalization capability. Our research shows that the proposed novel CQ-TL framework and its models have potential quantum advantages in the NISQ era, providing strong support for the practical application of qu

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

EVADE: Targeted Adversarial False Data Injection Attacks for State Estimation in Smart Grid

IEEE Transactions on Sustainable Computing

引用

IEEE Transactions on Sustainable Computing 2024年第03期10卷 534-546页

作者： Tian, Jiwei Shen, Chao Wang, Buhong Ren, Chao Xia, Xiaofang Dong, Runze Cheng, Tianhao Ministry of Education Key Laboratory for Intelligent Networks and Network Security School of Cyber Science and Engineering Xi'an Jiaotong University Xi'an China Air Traffic Control and Navigation College Air Force Engineering University Xi'an China Information and Navigation College Air Force Engineering University Xi'an China School of Electrical and Electronic Engineering Nanyang Technological University Singapore School of Computer Science and Technology Xidian University Xi'an China

Although conventional false data injection attacks can circumvent the detection of bad data detection (BDD) in sustainable power grid cyber physical systems, they are easily detected by well-trained deep learning-based detectors. Still, state estimation models with deep leaning-based detectors are not secure due to the vulnerabilities and fragility of deep learning models. Using the related laws of conventional false data injection attacks and adversarial sample attacks, this paper proposes the targEted adVersarial fAlse Data injEction (EVADE) strategy to explore targeted adversarial false data injection attacks for state estimation in Smart Grid. The proposed EVADE attack strategy selects key state variables based on adversarial saliency maps to improve the attack efficiency and perturbs as few state variables as possible to reduce the attack cost. In this way, the EVADE attack strategy can bypass the detection of BDD and neural attack detection (NAD) methods (that is, maintaining deep stealthy) with a high success rate and achieve the attack target simultaneously. Experimental results demonstrate the effectiveness of the proposed strategy, posing serious and pressing concerns for sustainable cyber physical power system security. © 2016 IEEE.

关键词： Cyber attacks

来源：评论

学校读者我要写书评

暂无评论

Byzantine-Robust Federated Learning Framework via a Server-Client Defense Mechanisms

引用

IEEE Internet of Things Journal 2025年

作者： Song, Anxiao Zhang, Tao Cheng, Ke Cao, Yang Zhu, Xinghui Shen, Yulong Xidian University School of Computer Science and Technology Xi’an China Shaanxi Key Laboratory of Network and System Security Shaanxi Xi’an710071 China Xidian University School of Computer Science and Technology Shaanxi Xi’an710071 China Xi’an University of Posts and Telecommunications Shaanxi Key Laboratory of Information Communication Network and Security Shaanxi Xi’an710121 China Institute of Science Tokyo Department of Computer Science Tokyo Japan

Federated Learning (FL), a distributed machine learning (ML) framework, is susceptible to Byzantine attacks since the attacker can manipulate clients' local data or models to compromise the performance of the global model. There has been a wealth of defenses developed to mitigate the attacks by limiting the impact of malicious models. Nevertheless, the attacker can easily circumvent these approaches that rely solely on a single server-side defense, stemming from the high dimensionality of models and the variety of Byzantine attacks. Therefore, we propose Basalt, a Byzantine-robust federated learning framework with a server-client joint defense mechanism that enables multiple clients to train a global ML model under Byzantine attacks. On the client side, we design an efficient self-defense approach with model-level penalty loss that restricts local-benign divergence and decreases local-malicious correlation to prevent misclassification. On the server side, we present an efficient defense strategy based on the manifold and maximum clique, further strengthening the FL's resilience against Byzantine attacks. We provide theoretical guarantees for global model convergence in FL with Byzantine attacks. Our extensive experiments demonstrate that Basalt outperforms existing state-of-the-art works. Especially, it achieves nearly 100% accuracy for detecting malicious clients in nonindependent and nonidentically distributed (Non-IID) MNIST datasets under various Byzantine attacks. © 2014 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

FPPNet: Fast Privacy-Preserving Neural network via Three-Party Arithmetic Secret Sharing 15th

FPPNet: Fast Privacy-Preserving Neural Network via Three-Pa...

引用

15th EAI International Conference on Mobile Multimedia Communications, MobiMedia 2022

作者： Bi, Renwan Xiong, Jinbo Li, Qi Liu, Ximeng Tian, Youliang Fujian Provincial Key Laboratory of Network Security and Cryptology College of Computer and Cyber Security Fujian Normal University Fuzhou350117 China School of Computer Science Nanjing University of Posts and Telecommunications Nanjing210023 China Key Laboratory of Cryptography of Zhejiang Province Hangzhou Normal University Hangzhou311121 China Key Laboratory of Information Security of Network Systems College of Mathematics and Computer Science Fuzhou University Fuzhou350108 China State Key Laboratory of Public Big Data College of Computer Science and Technology Guizhou University Guiyang550025 China

ISBN: (纸本)9783031239014

Jointing multi-source data for model training can improve the accuracy of neural network. To solve the raising privacy concerns caused by data sharing, data are generally encrypted and outsourced to a group of cloud servers for computing and processing. In this client-cloud architecture, we propose FPPNet, a fast and privacy-preserving neural network for secure inference on sensitive data. FPPNet is deployed in three cloud servers, who collaboratively execute privacy computing via three-party arithmetic secret sharing. We develop the secure conversion method between additive shares and multiplicative shares, and propose three secure protocols to calculate non-linear functions, such as comparison, exponent and division that are superior to prior three-party works. Some secure modules for running convolutional, ReLU, max-pooling and Sigmoid layers are designed to implement FPPNet. We theoretically analyze the security and complexity of the proposed protocols. With MNIST dataset and two types of neural networks, experimental results validate that our FPPNet is faster than the related works, and the accuracy is the same as that of plaintext neural network. © 2022, ICST Institute for computer Sciences, Social Informatics and Telecommunications Engineering.

关键词： Sensitive data

来源：评论

学校读者我要写书评

暂无评论

Entity Disambiguation Based on UCL Knowledge Space

Entity Disambiguation Based on UCL Knowledge Space

引用

2021 IEEE International Conference on Artificial Intelligence and Industrial Design, AIID 2021

作者： Xinchen, Chang Peng, Yang School of Computer Science and Engineering Key Laboratory of Computer Network and Information Integration Ministry of Education Southeast University Nanjing China

ISBN: (纸本)9780738110837

Named entity disambiguation is an important task in the process of knowledge space construction and improvement, which builds a bridge between entities in text and entities in knowledge space. However, the existing entity disambiguation methods mainly rely on the similar or related entities in the context. For the short text widely appeared in the practical application scenarios, the performance of the existing methods drops sharply. In this paper, we propose an entity disambiguation method based on Uniform Content Label knowledge space (UCLKS-ED). This method uses UCL knowledge space to provide additional knowledge information for the matching task of candidate entities and the source entity, and extends the representation of the source entity by conceptualizing. The experimental results on a large manually annotated short-text dataset and another standard dataset demonstrate that the proposed method achieves significant improvement over the state-of-the-art baselines. © 2021 IEEE.

关键词： Large dataset

来源：评论

学校读者我要写书评

暂无评论

RGBT tracking via reliable feature configuration

引用

Science China(information Sciences) 2022年第4期65卷 128-140页

作者： Zhengzheng TU Wenli PAN Yunsheng DUAN Jin TANG Chenglong LI Anhui Provincial Key Laboratory of Multimodal Cognitive Computation School of Computer Science and Technology Anhui University Network Information Center Anhui University

There is an increasing interest in RGBT tracking recently because of the complementary benefits of RGB and thermal infrared data. However, the reliability of each modality will change over time quite possibly, and the modality with bad reliability will disturb tracking performance. Thus, we propose a novel reliability-based feature configuration approach in the correlation filter framework for robust RGBT tracking. Specifically, we configure a feature set based on RGB, thermal, and RGBT data. To measure the reliabilities of different feature configurations, we equip each feature configuration with a tracker and design a guideline judging whether the tracker is reliable. We use the tracker with the best reliability for *** results show that the proposed tracker achieves promising performance against other RGBT tracking methods.

关键词： RGBT tracking multi-modal reliability guideline feature configuration correlation filter

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：