检索结果-内蒙古大学图书馆

Aligning enhanced feature representation for generalized zero-shot learning

Science China(Information Sciences) 2025年第2期68卷 74-88页

作者： Zhiyu FANG Xiaobin ZHU Chun YANG Hongyang ZHOU Jingyan QIN Xu-Cheng YIN School of Computer & Communication Engineering University of Science and Technology Beijing

Constructing an effective common latent embedding by aligning the latent spaces of cross-modal variational autoencoders（VAEs） is a popular strategy for generalized zero-shot learning（GZSL）. However, due to the lack of fine-grained instance-wise annotations, existing VAE methods can easily suffer from the posterior collapse problem. In this paper, we propose an innovative asymmetric VAE network by aligning enhanced feature representation（AEFR） for GZSL. Distinguished from general VAE structures, we designed two asymmetric encoders for visual and semantic observations and one decoder for visual reconstruction. Specifically, we propose a simple yet effective gated attention mechanism（GAM） in the visual encoder for enhancing the information interaction between observations and latent variables, alleviating the possible posterior collapse problem effectively. In addition, we propose a novel distributional decoupling-based contrastive learning（D2-CL） to guide learning classification-relevant information while aligning the representations at the taxonomy level in the latent representation space. Extensive experiments on publicly available datasets demonstrate the state-of-the-art performance of our method. The source code is available at https://***/seeyourmind/AEFR.

关键词： generalized zero-shot learning gated attention mechanism contrastive learning multi-modal alignment

来源：评论

学校读者我要写书评

暂无评论

A Novel Certificateless Signature-based Access Control Scheme for Named In-network Computing Service

IAENG International Journal of Computer Science

引用

IAENG International Journal of computer Science 2025年第1期52卷 38-45页

作者： Li, Wanji Liu, Qiangbin Zhu, Yi School of Computer Science and Communication Engineering Jiangsu University Zhenjiang China School of Computer Science and Communication Engineering Jiangsu University Zhenjiang China School of Computer Science and Communication Engineering the Dean of Department of Communication Engineering Jiangsu University Zhenjiang China

Named in-network computing service (NICS) is a potential computing paradigm emerged recently. Benefitted from the characteristics of named addressing and routing, NICS can be flexibly deployed on NDN router side and provide nearby computing service to Internet users. But the NICS feature of dynamic deployment also causes serious security risk of access control. How to independently check out the subscription relationship between requester and requested computing service on NICS side become a challenge. To solve this problem, we propose a novel certificateless signature-based access control scheme (CS-ACS) in this paper. In CS-ACS, the entire user public-private key pairs consist of two parts, user side and source server side. Where, the user public-private key pairs (server side) are generated according to the user ID, service subscription relationship and subscription expiration time. Based on this special design, when authorized user signs the interest packet of invoking specific service using its private key, the NICS can verify the signature then check out whether the requester is a valid subscriber and the subscription is expired or not. Simulation results show that, comparing with fundamental solutions, CS-ACS can avoid extra secret key storage cost on NICS side and markedly shorten authentication delay. © (2025), (International Association of Engineers). All rights reserved.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

Defending Federated Learning System from Poisoning Attacks via Efficient Unlearning

引用

computers, Materials & Continua 2025年第4期83卷 239-258页

作者： Long Cai Ke Gu Jiaqi Lei School of Computer and Communication Engineering Changsha University of Science and TechnologyChangsha410114China

Large-scale neural networks-based federated learning(FL)has gained public recognition for its effective capabilities in distributed ***,the open system architecture inherent to federated learning systems raises concerns regarding their vulnerability to potential *** attacks turn into a major menace to federated learning on account of their concealed property and potent destructive *** altering the local model during routine machine learning training,attackers can easily contaminate the global *** detection and aggregation solutions mitigate certain threats,but they are still insufficient to completely eliminate the influence generated by ***,federated unlearning that can remove unreliable models while maintaining the accuracy of the global model has become a *** some existing federated unlearning approaches are rather difficult to be applied in large neural network models because of their high computational ***,we propose SlideFU,an efficient anti-poisoning attack federated unlearning *** primary concept of SlideFU is to employ sliding window to construct the training process,where all operations are confined within the *** design a malicious detection scheme based on principal component analysis(PCA),which calculates the trust factors between compressed models in a low-cost way to eliminate unreliable *** confirming that the global model is under attack,the system activates the federated unlearning process,calibrates the gradients based on the updated direction of the calibration *** on two public datasets demonstrate that our scheme can recover a robust model with extremely high efficiency.

关键词： Federated learning malicious client detection model recovery machine unlearning

来源：评论

学校读者我要写书评

暂无评论

A Transferable-experience-based Routing Mechanism for Named Computing Power Network

IAENG International Journal of Computer Science

引用

IAENG International Journal of computer Science 2025年第4期52卷 1235-1243页

作者： Dai, Yakai Zhu, Yi School of Computer Science and Communication Engineering Jiangsu University Zhenjiang212013 China

Computing-aware routing is the core technology of Computing Power Network. Through independently determining the forwarding target in each router, computingaware routing aims at scheduling the computing task to an optimal Computing Service Provider (CSP). However, current computing-aware routing schemes only depend on the collected computing and network resource information, do not consider the experience of CSPs in handling similar tasks, resulting in excessive invocation time. Facing this problem, this paper proposes a novel routing mechanism based on transfer learning experience in named computing power network (NRS-TLE). NRS-TLE introduces the accuracy of trained classification models as the experience of CSP, and design a tcce-function to evaluate the task completion capabilities of different CSPs at NDN routers. Based on the evaluation results of the tcce- function, NDN routers further perform a probabilistic routing scheme. The simulation results show that, comparing with traditional routing scheme SAC-NSGA-II, the computing service invocation time under NRS-TLE will decrease by a minimum of 26.42% and a maximum of 40.22%. © 2025 IAENG International Journal of computer Science

关键词： Computing power

来源：评论

学校读者我要写书评

暂无评论

Low-profile,low sidelobe array antenna with ultrawide beam coverage for UAV communication

引用

Chinese Journal of Aeronautics 2025年第1期38卷 444-454页

作者： Mei LI Zhiliang SHANG Lin PU Ming-Chun TANG Lei ZHU School of Microelectronics and Communication Engineering Chongqing UniversityChongqing 400044China Department of Electrical and Computer Engineering University of MacaoMacao SAR 999078China

This paper presents a design method to implement an antenna array characterized by ultra-wide beam coverage,low profile,and low Sidelobe Level(SLL)for the application of Unmanned Aerial Vehicle(UAV)air-to-ground *** array consists of ten broadside-radiating,ultrawide-beamwidth elements that are cascaded by a central-symmetry series-fed network with tapered currents following Dolph-Chebyshev distribution to provide low ***,an innovative design of end-fire Huygens source antenna that is compatible with metal ground is presented.A low-profile,half-mode Microstrip Patch Antenna(MPA)is utilized to serve as the magnetic dipole and a monopole is utilized to serves as the electric dipole,constructing the compact,end-fire,grounded Huygens source ***,two opposite-oriented end-fire Huygens source antennas are seamlessly integrated into a single antenna element in the form of monopole-loaded MPA to accomplish the ultrawide,broadside-radiating *** consideration has been applied into the design of series-fed network as well as antenna element to compensate the adverse coupling effects between elements on the radiation *** indicates an ultrawide Half-Power Beamwidth(HPBW)of 161°and a low SLL of-25 dB with a high gain of 12 d Bi under a single-layer *** concurrent ultrawide beamwidth and low SLL make it particularly attractive for applications of UAV air-to-ground communication.

关键词： Array antenna Broad beam Fan beam Low sidelobe level Chebyshev synthesis UAV communication

来源：评论

学校读者我要写书评

暂无评论

HA-FGOVD: Highlighting Fine-grained Attributes via Explicit Linear Composition for Open-Vocabulary Object Detection

引用

IEEE Transactions on Multimedia 2025年 27卷 3171-3183页

作者： Ma, Yuqi Liu, Mengyin Zhu, Chao Yin, Xu-Cheng University of Science and Technology Beijing School of Computer and Communication Engineering Beijing100083 China

Open-vocabulary object detection (OVD) models are considered to be Large Multi-modal Models (LMM), due to their extensive training data and a large number of parameters. Mainstream OVD models prioritize object coarse-grained category rather than focus on their fine-grained attributes, e.g., colors or materials, thus failed to identify objects specified with certain attributes. Despite being pretrained on large-scale image-text pairs with rich attribute information, their latent feature space does not highlight these fine-grained attributes. In this paper, we introduce HA-FGOVD, a universal and explicit method that enhances the attribute-level detection capabilities of frozen OVD models by highlighting fine-grained attributes in explicit linear space. Our approach uses a LLM to extract attribute words in input text as a zero-shot task. Then, token attention masks are adjusted to guide text encoders in extracting both global and attribute-specific features, which are explicitly composited as two vectors in linear space to form a new attribute-highlighted feature for detection tasks. The composition weight scalars can be learned or transferred across different OVD models, showcasing the universality of our method. Experimental results show that HA-FGOVD achieves state-of-the-art performance on the FG-OVD benchmark and demonstrates promising generalization on the OVDEval benchmark, suggesting that our method addresses significant limitations in fine-grained attribute detection and has potential for broader fine-grained detection applications. © 1999-2012 IEEE.

关键词： Coarse-grained modeling

来源：评论

学校读者我要写书评

暂无评论

A novel feature selection method based on adaptive search particle swarm optimization

引用

Neural Computing and Applications 2025年第12期37卷 7767-7783页

作者： Han, Fei Wang, Yi-Huai Li, Fan-Yu School of Computer Science and Communication Engineering Jiangsu University Jiangsu Zhenjiang212013 China

As an effective method for data dimensionality reduction, feature selection could improve the classification accuracy and reduce the computational cost when dealing with high-dimensional data. Feature selection is essentially a complex optimization search problem. Among many optimization algorithms, particle swarm optimization (PSO) has been widely used due to its good global search ability and easy to implement. However, most feature selection methods based on PSO ignore the correlations between the features of data, which may lead to more redundant features, and the feature selection methods are prone to fall into local minima. This study proposes an improved feature selection method based on adaptive search particle swarm optimization (AS-BPSO-FS). On one hand, AS-BPSO-FS is designed to consider the feature correlation according to the feature correlation information. The particle position adaptive update strategy selects features based on the correlation coefficient between features, ensuring that features with higher correlation are more likely to be culled, so as to obtain a subset of features with less redundancy. On the other hand, AS-BPSO-FS identifies particles trapped in local minima by calculating the update time of individual and global optimal positions, and uses an adaptive particle neighborhood search strategy to help particles escape from local minima. The AS-BPSO-FS has been tested on 10 UCI data and compared with some state-of-the-art feature selection methods. The results verify that the proposed method could obtain feature subsets with better classification performance and less redundancy. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Feature Selection

来源：评论

学校读者我要写书评

暂无评论

Individualized Driving Intention Prediction With Inverse Reinforcement Learning

引用

IEEE Transactions on Intelligent Transportation Systems 2025年第6期26卷 8125-8139页

作者： Liu, Siqi Li, Xinyang Chen, Jiansheng Guo, Chenghao Wu, Jiehui Luo, Qifeng Ma, Huimin University of Science and Technology Beijing School of Computer and Communication Engineering Beijing100083 China

Advanced Driver Assistance Systems (ADAS) are designed to prevent collisions, identify the condition of drivers while operating vehicles, and provide additional information to enhance drivers' awareness of potential hazards on the road. Today, ADAS are capable of predicting drivers' actions several seconds in advance, preparing for potential future hazards to prevent accidents or reduce injuries to occupants. Most previous works have achieved prediction results by analyzing and processing a vast amount of driving data from multiple drivers, based on the macro intention preferences of multiple drivers and external environmental features, collectively referred to as the generalized intention prediction network. This network utilizes extensive driving data to predict the common driving intentions of the overall driving population, without considering individualized driving styles. However, according to our research, different drivers exhibit distinct latent preferences in real-world driving scenarios. The generalized intention prediction network is influenced by these latent preferences, resulting in poor generalization capabilities and inaccurate predictions across different drivers. In this study, we propose a individualized driver intention prediction network. Based on Inverse Reinforcement Learning (IRL), it extracts individualized driving intention feature preferences that influence driving intentions from the driver's historical behavior to improve generalized prediction results and achieve individualized driving intention prediction. We demonstrate that preferences vary among different drivers in the driving domain, leading to biases in model predictions. Upon experimental validation, the method we have proposed demonstrates remarkable efficacy on both the Brain4Cars and IESDD datasets, thereby showcasing its enhanced applicability in real-world scenarios. © 2000-2011 IEEE.

关键词： Advanced driver assistance systems

来源：评论

学校读者我要写书评

暂无评论

Fake Face Detection Based on Fusion of Spatial Texture and High-Frequency Noise

引用

Chinese Journal of Electronics 2025年第1期34卷 212-221页

作者： Dengyong Zhang Feifan Qi Jiahao Chen Jiaxin Chen Rongrong Gong Yuehong Tian Lebing Zhang Hunan Provincial Key Laboratory of Intelligent Processing of Big Data on Transportation School of Computer and Communication Engineering Changsha University of Science and Technology School of Computer and Communication Engineering Changsha University of Science and Technology Changsha Social Work College Changkuangao Beijing Technology Co. Ltd. School of Computer and Artificial Intelligence Huaihua University

The rapid development of the Internet has led to the widespread dissemination of manipulated facial images, significantly impacting people's daily lives. With the continuous advancement of Deepfake technology, the generated counterfeit facial images have become increasingly challenging to distinguish. There is an urgent need for a more robust and convincing detection method. Current detection methods mainly operate in the spatial domain and transform the spatial domain into other domains for analysis. With the emergence of transformers, some researchers have also combined traditional convolutional networks with transformers for detection. This paper explores the artifacts left by Deepfakes in various domains and, based on this exploration, proposes a detection method that utilizes the steganalysis rich model to extract high-frequency noise to complement spatial features. We have designed two main modules to fully leverage the interaction between these two aspects based on traditional convolutional neural networks. The first is the multi-scale mixed feature attention module, which introduces artifacts from high-frequency noise into spatial textures, thereby enhancing the model's learning of spatial texture features. The second is the multi-scale channel attention module, which reduces the impact of background noise by weighting the features. Our proposed method was experimentally evaluated on mainstream datasets, and a significant amount of experimental results demonstrate the effectiveness of our approach in detecting Deepfake forged faces, outperforming the majority of existing methods.

关键词： Deepfakes Adaptation models Attention mechanisms Noise Transforms Transformers Feature extraction Internet Convolutional neural networks Faces

来源：评论

学校读者我要写书评

暂无评论

Privacy-preserving explainable AI: a survey

引用

Science China(Information Sciences) 2025年第1期68卷 23-56页

作者： Thanh Tam NGUYEN Thanh Trung HUYNH Zhao REN Thanh Toan NGUYEN Phi Le NGUYEN Hongzhi YIN Quoc Viet Hung NGUYEN School of Information and Communication Technology Griffith University School of Computer and Communication Sciences Ecole Polytechnique Federale de Lausanne Faculty of Mathematics and Computer Science University of Bremen Faculty of Information Technology HUTECH University Department of Computer Science Hanoi University of Science and Technology School of Electrical Engineering and Computer Science The University of Queensland

As the adoption of explainable AI(XAI) continues to expand, the urgency to address its privacy implications intensifies. Despite a growing corpus of research in AI privacy and explainability, there is little attention on privacy-preserving model explanations. This article presents the first thorough survey about privacy attacks on model explanations and their countermeasures. Our contribution to this field comprises a thorough analysis of research papers with a connected taxonomy that facilitates the categorization of privacy attacks and countermeasures based on the targeted explanations. This work also includes an initial investigation into the causes of privacy leaks. Finally, we discuss unresolved issues and prospective research directions uncovered in our analysis. This survey aims to be a valuable resource for the research community and offers clear insights for those new to this domain. To support ongoing research, we have established an online resource repository, which will be continuously updated with new and relevant findings.

关键词： privacy-preserving explainable AI privacy attacks privacy defences PrivEx PPXAI

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：