检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Xie, Yiping Yu, Zitong Wu, Bingjie Xie, Weicheng Shen, Linlin Computer Vision Institute School of Computer Science & Software Engineering Shenzhen Institute of Artificial Intelligence and Robotics for Society Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen518060 China School of Computing and Information Technology Great Bay University Dongguan523000 China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen518060 China Singapore

Remote Photoplethysmography (rPPG) is a non-contact method that uses facial video to predict changes in blood volume, enabling physiological metrics measurement. Traditional rPPG models often struggle with poor generalization capacity in unseen domains. Current solutions to this problem is to improve its generalization in the target domain through Domain Generalization (DG) or Domain Adaptation (DA). However, both traditional methods require access to both source domain data and target domain data, which cannot be implemented in scenarios with limited access to source data, and another issue is the privacy of accessing source domain data. In this paper, we propose the first Source-free Domain Adaptation benchmark for rPPG measurement (SFDA-rPPG), which overcomes these limitations by enabling effective domain adaptation without access to source domain data. Our framework incorporates a Three-Branch Spatio-Temporal Consistency Network (TSTC-Net) to enhance feature consistency across domains. Furthermore, we propose a new rPPG distribution alignment loss based on the Frequency-domain Wasserstein Distance (FWD), which leverages optimal transport to align power spectrum distributions across domains effectively and further enforces the alignment of the three branches. Extensive cross-domain experiments and ablation studies demonstrate the effectiveness of our proposed method in source-free domain adaptation settings. Our findings highlight the significant contribution of the proposed FWD loss for distributional alignment, providing a valuable reference for future research and applications. The source code is available at https://***/XieYiping66/SFDA-rPPG. Copyright © 2024, The Authors. All rights reserved.

关键词： Photoplethysmography

来源：评论

学校读者我要写书评

暂无评论

Partial Deep Domain Adaptation for Non-Intrusive Load Monitoring

Partial Deep Domain Adaptation for Non-Intrusive Load Monito...

引用

IEEE International Conference on Big data and Cloud Computing (BdCloud)

作者： Yuying Li Yang Yang Chen Wang Runqin Liu Hongbo Jiang Wenping Liu Key Laboratory of Intelligent Sensing System and Security (Ministry of Education) School of Artificial Intelligence Hubei University Wuhan China Huazhong University of Science and Technology Wuhan China China Unicom Central South Research Institute Changsha China Hunan University Changsha China Hubei University of Economics Wuhan China

With the widespread deployment of smart meters and the burgeoning integration of the Ubiquitous Power Internet of Things (UPIoT), Non-Intrusive Load Monitoring (NILM) has emerged as an essential technology, providing granular insights into device-level energy consumption. However, NILM model generalization is impeded by user and appliance heterogeneity. Domain adaptation has been leveraged to enhance NILM models, but it typically necessitates consistent appliance categorization across households. Addressing this, our study presents Weighted Adaptation NILM (WeAd-NILM), a partial deep domain adaptation model designed for Partial Domain Adaptation (PDA) scenarios that accommodate diverse appliance categories, aligning with real-world load decomposition tasks. WeAd-NILM introduces a sample weighting mechanism tailored for PDA, mitigating negative transfer from outliers. Through distribution analysis and multi-objective regression, WeAd-NILM effectively performs load decomposition, fostering knowledge transfer. Verified on UK-DALE and REFIT datasets, WeAd-NILM demonstrates exceptional transferability and load decomposition accuracy.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Backdoor Defense with Machine Unlearning

arXiv

引用

arXiv 2022年

作者： Liu, Yang Fan, Mingyuan Chen, Cen Liu, Ximeng Ma, Zhuo Wang, Li Ma, Jianfeng Xi'An China Shaanxi Key Laboratory of Network and System Security Xidian University Xi'An China College of Computer and Data Science Fuzhou University Fuzhou China School of Data Science and Engineering East China Normal University Shanghai China Ant Group Hangzhou China

Backdoor injection attack is an emerging threat to the security of neural networks, however, there still exist limited effective defense methods against the attack. In this paper, we propose BAERASER, a novel method that can erase the backdoor injected into the victim model through machine unlearning. Specifically, BAERASER mainly implements backdoor defense in two key steps. First, trigger pattern recovery is conducted to extract the trigger patterns infected by the victim model. Here, the trigger pattern recovery problem is equivalent to the one of extracting an unknown noise distribution from the victim model, which can be easily resolved by the entropy maximization based generative model. Subsequently, BAERASER leverages these recovered trigger patterns to reverse the backdoor injection procedure and induce the victim model to erase the polluted memories through a newly designed gradient ascent based machine unlearning method. Compared with the previous machine unlearning solutions, the proposed approach gets rid of the reliance on the full access to training data for retraining and shows higher effectiveness on backdoor erasing than existing fine-tuning or pruning methods. Moreover, experiments show that BAERASER can averagely lower the attack success rates of three kinds of state-of-the-art backdoor attacks by 99% on four benchmark datasets. © 2022, CC BY-NC-ND.

关键词： Network security

来源：评论

学校读者我要写书评

暂无评论

Efficient Adaptive Label Refinement for Label Noise Learning

arXiv

引用

arXiv 2025年

作者： Zhang, Wenzhen Cheng, Debo Lu, Guangquan Zhou, Bo Li, Jiaye Zhang, Shichao School of Computer Science and Engineering Guangxi Normal University Guangxi Guilin541004 China Guangxi Key Lab of Multi-Source Information Mining & Security Guangxi Normal University Guangxi Guilin541004 China Key Lab of Education Blockchain and Intelligent Technology Ministry of Education Guangxi Normal University Guangxi Guilin541004 China UniSA STEM University of South Australia AdelaideSA5095 Australia Guangxi Collaborative Innovation Center of Modern Sericulture and Silk Hechi University Guangxi Hechi546300 China The State Key Laboratory of Blockchain and Data Security Zhejiang University Zhejiang Hangzhou310027 China

Deep neural networks are highly susceptible to overfitting noisy labels, which leads to degraded performance. Existing methods address this issue by employing manually defined criteria, aiming to achieve optimal partitioning in each iteration to avoid fitting noisy labels while thoroughly learning clean samples. However, this often results in overly complex and difficult-to-train models. To address this issue, we decouple the tasks of avoiding fitting incorrect labels and thoroughly learning clean samples and propose a simple yet highly applicable method called Adaptive Label Refinement (ALR). First, inspired by label refurbishment techniques, we update the original hard labels to soft labels using the model’s predictions to reduce the risk of fitting incorrect labels. Then, by introducing the entropy loss, we gradually ‘harden’ the high-confidence soft labels, guiding the model to better learn from clean samples. This approach is simple and efficient, requiring no prior knowledge of noise or auxiliary datasets, making it more accessible compared to Copyright © 2025, The Authors. All rights reserved.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Exfiltration-resistant Proxy Re-Encryption for IoT data Sharing in Unreliable Clouds

引用

IEEE Transactions on Dependable and Secure Computing 2025年

作者： Zhou, Yuyang Zhao, Liang Li, Fagen Takagi, Tsuyoshi School of Cyberspace Security Hainan University Haikou570000 China Department of Mathematical Informatics Graduate School of Information Science and Technology The university of Tokyo Tokyo113-8656 Japan School of Cyber Science and Engineering Sichuan University Chengdu610065 China Key Laboratory of Data Protection and Intelligent Management [Sichuan University Ministry of Education China School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu611731 China

The sharing of Internet of Things (IoT) data plays an extensive role in our everyday lives. Exploring secure and efficient methods for data sharing is a prominent area of research. Proxy re-encryption (PRE) in the cloud provides a solution. However, traditional PRE schemes are vulnerable to algorithm substitution attacks (ASA). Moreover, in most PRE schemes, the proxy can know the relevant identity information of the data owner or the data recipient through the re-encryption key, and some current PRE schemes cannot guarantee strong resistance to collision. To address the limitations of traditional PRE schemes and offer a robust solution for secure and efficient data sharing in IoT application, we propose a reverse firewall for proxy re-encryption (PRE-RF) scheme, which we implement using the JPBC library. The security analysis reveals that the PRE-RF scheme offers effective resistance against ASA, while also providing strong collision security, chosen plaintext attack security, and key-private security. Compared to similar PRE schemes with more security features, our scheme reduces the length of the re-encryption keys and ciphertext, thereby reducing the storage cost of the system;also, our scheme’s computational cost is lower, thereby improving the operational efficiency of the system. Furthermore, as security levels rise, the portion of time dedicated to reverse firewall operations within our scheme diminishes. These advantages collectively render it a secure and efficient choice for sharing IoT data in unreliable cloud environments. © 2004-2012 IEEE All rights reserved.

关键词： Ciphertext

来源：评论

学校读者我要写书评

暂无评论

Uplink Precoding Design for Cell-Free Massive MIMO With Iteratively Weighted MMSE

Uplink Precoding Design for Cell-Free Massive MIMO With Iter...

引用

作者： Wang, Zhe Zhang, Jiayi Ngo, Hien Quoc Ai, Bo Debbah, Merouane Frontiers Science Center for Smart High-Speed Railway System The School of Electronic and Information Engineering Beijing Jiaotong University Beijing100044 China Institute of Electronics Communications and Information Technology Queen’s University Belfast BelfastBT3 9DT United Kingdom State Key Laboratory of Rail Traffic Control and Safety Beijing Jiaotong University Beijing100044 China Henan Joint International Research Laboratory of Intelligent Networking and Data Analysis The Frontiers Science Center for Smart High-Speed Railway System Zhengzhou University Zhengzhou450001 China Peng Cheng Laboratory Research Center of Networks and Communications Shenzhen518066 China Technology Innovation Institute Abu Dhabi United Arab Emirates CentraleSupélec University Paris-Saclay Gif-sur-Yvette91192 France

In this paper, we investigate a cell-free massive multiple-input multiple-output system with both access points and user equipments equipped with multiple antennas over the Weichselberger Rayleigh fading channel. We study the uplink spectral efficiency (SE) for the fully centralized processing scheme and large-scale fading decoding (LSFD) scheme. To further improve the SE performance, we design the uplink precoding schemes based on the weighted sum SE maximization. Since the weighted sum SE maximization problem is not jointly over all optimization variables, two efficient uplink precoding schemes based on Iteratively Weighted sum-Minimum Mean Square Error (I-WMMSE) algorithms, which rely on the iterative minimization of weighted Mean Square Error (MSE), are proposed for two processing schemes investigated. Furthermore, with maximum ratio combining applied in the LSFD scheme, we derive novel closed-form achievable SE expressions and optimal precoding schemes. Numerical results validate the proposed results and show that the I-WMMSE precoding schemes can achieve excellent sum SE performance with a large number of UE antennas. © 1972-2012 IEEE.

关键词： MIMO systems

来源：评论

学校读者我要写书评

暂无评论

Raft Consensus Algorithm Based on Credit Model in Consortium Blockchain

引用

Wuhan University Journal of Natural Sciences 2020年第2期25卷 146-154页

作者： CHEN Yunfang LIU Ping ZHANG Wei School of Computer Science Nanjing University of Posts and TelecommunicationsNanjing 210023JiangsuChina Jiangsu Key Laboratory of Big Data Security and Intelligent Processing Nanjing University of Posts and TelecommunicationsNanjing 210023JiangsuChina

As one of the underlying technologies of the blockchain,the consensus algorithm plays a vital role in ensuring security and *** a consensus algorithm for the private blockchain,Raft has better performance than the rest of the consensus algorithms,and it does not cause problems such as the concentrated hashing power,resource waste and ***,Raft can only be used in a non-byzantine environment with a small network *** order to enable Raft to be used in a large-scale network with a certain number of byzantine nodes,this paper combines Raft and credit model to propose a Raft blockchain consensus algorithm based on credit model *** the node credit evaluation phase,RBF-based support vector machine is used as the anomaly detection method,and the node credit evaluation model is *** the Trust Nodes List(TNL)mechanism is introduced to make the consensus phase in a creditable network ***,the common node is synchronized to the consensus node to update the blockchain of the entire *** show that CRaft has better throughput and lower latency than the commonly used consortium blockchain consensus algorithm PBFT(Practical Byzantine Fault Tolerance).

关键词： credit model consensus algorithm consortium blockchain P2P network

来源：评论

学校读者我要写书评

暂无评论

Domain generalization for document authentication against practical recapturing attacks

arXiv

引用

arXiv 2021年

作者： Chen, Changsheng Zhang, Shuzheng Lan, Fengbo Huang, Jiwu The Guangdong Key Laboratory of Intelligent Information Processing Shenzhen Key Laboratory of Media Security National Engineering Laboratory for Big Data System Computing Technology College of Electronics and Information Engineering Shenzhen University Shenzhen China Shenzhen Institute of Artificial Intelligence and Robotics for Society China

Recapturing attack can be employed as a simple but effective anti-forensic tool for digital document images. Inspired by the document inspection process that compares a questioned document against a reference sample, we proposed a document recapture detection scheme by employing Siamese network to compare and extract distinct features in a recapture document image. The proposed algorithm takes advantages of both metric learning and image forensic techniques. Instead of adopting Euclidean distance-based loss function, we integrate the forensic similarity function with a triplet loss and a normalized softmax loss. After training with the proposed triplet selection strategy, the resulting feature embedding clusters the genuine samples near the reference while pushes the recaptured samples apart. In the experiment, we consider practical domain generalization problems, such as the variations in printing/imaging devices, substrates, recapturing channels, and document types. To evaluate the robustness of different approaches, we benchmark some popular off-the-shelf machine learning-based approaches, a state-of-the-art document image detection scheme, and the proposed schemes with different network backbones under various experimental protocols. Experimental results show that the proposed schemes with different network backbones have consistently outperformed the state-of-the-art approaches under different experimental settings. Specifically, under the most challenging scenario in our experiment, i.e., evaluation across different types of documents that produced by different devices, we have achieved less than 5.00% APCER (Attack Presentation Classification Error Rate) and 5.56% BPCER (Bona Fide Presentation Classification Error Rate) by the proposed network with ResNeXt101 backbone at 5% BPCER decision *** Codes 94A08 Copyright © 2021, The Authors. All rights reserved.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

ER: Equivariance Regularizer for Knowledge Graph Completion

arXiv

引用

arXiv 2022年

作者： Cao, Zongsheng Xu, Qianqian Yang, Zhiyong Huang, Qingming State Key Laboratory of Information Security Institute of Information Engineering CAS Beijing China School of Cyber Security University of Chinese Academy of Sciences Beijing China Key Laboratory of Intelligent Information Processing Institute of Computing Technology CAS Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing China Peng Cheng Laboratory Shenzhen China

Tensor factorization and distanced based models play important roles in knowledge graph completion (KGC). However, the relational matrices in KGC methods often induce a high model complexity, bearing a high risk of overfitting. As a remedy, researchers propose a variety of different regularizers such as the tensor nuclear norm regularizer. Our motivation is based on the observation that the previous work only focuses on the "size" of the parametric space, while leaving the implicit semantic information widely untouched. To address this issue, we propose a new regularizer, namely, Equivariance Regularizer (ER), which can suppress overfitting by leveraging the implicit semantic information. Specifically, ER can enhance the generalization ability of the model by employing the semantic equivariance between the head and tail entities. Moreover, it is a generic solution for both distance based models and tensor factorization based models. The experimental results indicate a clear and substantial improvement over the state-of-the-art relation prediction methods. © 2022, CC BY.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Classifying Galaxy Morphologies with Few-Shot Learning

arXiv

引用

arXiv 2022年

作者： Zhang, Zhirui Zou, Zhiqiang Li, Nan Chen, Yanli College of Computer Nanjing University of Posts and Telecommunications Nanjing China Jiangsu Key Laboratory of Big Data Security and Intelligent Processing Jiangsu Nanjing China Key Laboratory of Optical Astronomy National Astronomical Observatories Chinese Academy of Sciences Beijing China University of Chinese Academy of Science Beijing China

The taxonomy of galaxy morphology is critical in astrophysics as the morphological properties are powerful tracers of galaxy evolution. With the upcoming Large-scale Imaging Surveys, billions of galaxy images challenge astronomers to accomplish the classification task by applying traditional methods or human inspection. Consequently, machine learning, in particular supervised deep learning, has been widely employed to classify galaxy morphologies recently due to its exceptional automation, efficiency, and accuracy. However, supervised deep learning requires extensive training sets, which causes considerable workloads;also, the results are strongly dependent on the characteristics of training sets, which leads to biased outcomes potentially. In this study, we attempt Few-shot Learning to bypass the two issues. Our research adopts the dataset from Galaxy Zoo Challenge Project on Kaggle, and we divide it into five categories according to the corresponding truth table. By classifying the above dataset utilizing few-shot learning based on Siamese Networks and supervised deep learning based on AlexNet, VGG 16, and ResNet 50 trained with different volumes of training sets separately, we find that few-shot learning achieves the highest accuracy in most cases, and the most significant improvement is 21% compared to AlexNet when the training sets contain 1000 images. In addition, to guarantee the accuracy is no less than 90%, few-shot learning needs ∼6300 images for training, while ResNet 50 requires ∼13000 images. Considering the advantages stated above, foreseeably, few-shot learning is suitable for the taxonomy of galaxy morphology and even for identifying rare astrophysical objects, despite limited training sets consisting of observational data only. Copyright © 2022, The Authors. All rights reserved.

关键词： Galaxies

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：