检索结果-内蒙古大学图书馆

8th International Conference on computer Science and Artificial Intelligence, CSAI 2024

作者： Duan, Lijuan Zhang, Zichen Gong, Zhi Beijing Key Laboratory of Trusted Computing Beijing University of Technology Beijing China School of Computer Science Beijing University of Technology Beijing China National Engineering Laboratory for Key Technologies of Information Security Level Protection Beijing China

ISBN: (纸本)9798400718182

Recent deep learning models have advanced object detection capabilities, but their reliance on labeled data limits scalability. Fine-grained zero-shot detection remains challenging due to the need to generalize to unseen classes and distinguish subtle features. To address this, we propose Fine-Grained Zero-Shot Object Detection via Semantic Decoupling (ZSD-SD). Our approach introduces a semantic decoupling module to separate visual features into semantic-related and semantic-unrelated components, facilitating alignment between visual and semantic spaces. A semantic-visual learning module further decouples these features, enhancing visual representations relevant to external semantic knowledge. This semantic-related representation significantly improves zero-shot performance. Experiments on two fine-grained object detection datasets demonstrate that ZSD-SD achieves state-of-the-art results. © 2024 Copyright held by the owner/author(s).

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

Reflectance Recovery Guided Learning of Illumination-Invariant Features for Person Re-Identification 18th

Reflectance Recovery Guided Learning of Illumination-Invari...

引用

18th Chinese Conference on Biometric Recognition, CCBR 2024

作者： Chen, Xianbiao Xie, Xiaohua School of Computer Science and Engineering Sun Yat-sen University Guangzhou China Guangdong Province Key Laboratory of Information Security Technology Guangzhou China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education Guangzhou China

ISBN: (纸本)9789819610679

In real-world scenarios, the changes of illumination are noticeable and can significantly impact the performance of re-identification (ReID) algorithms. However, the existing person ReID methods predominantly concentrate on tackling challenges in scenarios with minimal illumination fluctuations. The key to tackling this issue is to extract illumination-invariant features. So we propose a joint learning framework which combines the recovery of reflectance map and extraction of illumination-invariant feature. By sharing parameters, the proposed module, which can be seamlessly detached during the inference phase, contributes to a reduction in inference computation time. We also introduce an adversarial learning mechanism, utilizing illumination category and person identity to facilitate the extraction of features that are invariant to illumination. Besides, due to the lack of person ReID dataset containing images under diverse lighting conditions, we construct a real-world dataset called ICReID in which images have drastic illumination changes. Extensive experiments demonstrate the effectiveness of the proposed method, which achieves significant performance on both synthetic and real datasets. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

A Byzantine Client Detection Method for Federated Learning Based on Encrypted Repeated Median Linear Regression 24

A Byzantine Client Detection Method for Federated Learning B...

引用

5th International Conference on computer Science and Management Technology, ICCSMT 2024

作者： Guo, Jinlong Yang, Ming Li, Huijuan Wu, Xiaoming He, Yunpeng Wang, Xin Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Qilu University of Technology Shandong Academy of Sciences Shandong Jinan China Shandong Evayinfo Technology Co. Ltd. Shandong Jinan China

ISBN: (纸本)9798400709999

Federated learning is an emerging distributed machine learning technology that allows participants to jointly train machine learning models locally without the need for large-scale data transmission and sharing, thereby greatly improving data security. However, some Byzantine clients may intentionally tamper with local model parameter updates with the intention of manipulating the global model's update direction, which can lead to a decline in the overall performance of federated learning. Besides, existing Byzantine client detection research is conducted in plain text, which will lead to the leakage of private information. To solve the above issues, we propose a Byzantine client detection method for federated learning based on encrypted repeated median linear regression. Specifically, it combines the repeated median linear regression algorithm with homomorphic encryption, which can detect and eliminate clients with Byzantine behavior in the ciphertext state, ensuring the security and reliability of the parameters in the entire federated learning process. Additionally, we also designed an adaptive gradient clipping method based on historical iteration to clip the gradient to a reasonable range, which can not only reduce communication and computing overhead, but also improve the convergence speed and stability of the model. Experiments show that the proposed method can maintain high accuracy under the influence of malicious behavior of Byzantine clients. © 2024 Copyright held by the owner/author(s). Publication rights licensed to ACM.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

CurMIM: Curriculum Masked Image Modeling

CurMIM: Curriculum Masked Image Modeling

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Liu, Hao Wang, Kun Han, Yudong Wang, Haocong Hu, Yupeng Wang, Chunxiao Nie, Liqiang School of Software Shandong University Jinan China Key Laboratory of Computing Power Network and Information Security Ministry of Education Qilu University of Technology Shandong Academy of Sciences Jinan China School of Computer Science and Technology Harbin Institute of Technology Shenzhen China

ISBN: (纸本)9798350368741

Masked Image Modeling (MIM), following "mask-and-reconstruct" scheme, is a promising self-supervised method to learn scalable visual representation. Studies indicate that selecting an effective mask strategy is vital for MIM. However, existing approaches often rely on static pre-defined priors, which limit their ability to adapt mask strategies dynamically for network optimization. In this paper, we focus on the learning process of the network and introduce human-like curriculum into MIM for dynamic representation refinement, and propose an end-to-end framework Curriculum Masked Image Modeling (CurMIM). CurMIM consists of two components: Mask Priority Measurer, which acts as a curriculum learner to determine mask priority values using the network's intrinsic state information, and Dual Adaptive Selector, which serves as a curriculum scheduler to create effective masks based on these values. With negligible extra parameters, our curriculum-based method consistently establishes noticeable improvements across varying model sizes and benchmarks, showing effectiveness and generalization. © 2025 IEEE.

关键词： Curriculum Learning Image Representation Masked Image Modeling Visual Pre-training

来源：评论

学校读者我要写书评

暂无评论

Fine-grained Personalized Hierarchical Federated Learning towards Heterogeneous Internet of Vehicles

引用

IEEE Internet of Things Journal 2025年第11期12卷 16349-16362页

作者： Zhang, Puning Shao, Shuman Wu, Chao Yang, Zhigang Zhang, Ruoying Chongqing University of Posts and Telecommunications School of Communications and Information Engineering Chongqing400065 China Chongqing Key Laboratory of Ubiquitous Sensing and Networking Advanced Network and Intelligent Connection Technology Key Laboratory of Chongqing Education Commission of China Chongqing400065 China Chongqing Innovation Center of Industrial Big-Data Co. Ltd National Engineering Laboratory for Industrial Big-data Application Technology Chongqing400707 China China Merchants Testing Vehicle Technology Research Institute Co. Ltd Chongqing404100 China Chongqing University of Posts and Telecommunications School of Cyber Security and Information Law Chongqing400065 China Chongqing Key Laboratory of Ubiquitous Sensing and Networking Advanced Network and Intelligent Connection Technology Key Laboratory of Chongqing Education Commission of China China China Academy of Information and Communications Beijing100083 China

High mobility and non-independent and identically distributed (non-iid) data in the Internet of Vehicles (IoV) pose challenges for the convergence speed and accuracy of federated learning model training. Traditional federated learning approaches fail to account for the unique characteristics of local vehicle data, limiting the model performances. To address this, we propose a personalized hierarchical federated learning method tailored for heterogeneous IoV. Our approach customizes models for each vehicle, enhancing their performance on local data. We introduce a network-aware client selection method that dynamically chooses vehicle clients based on their spatiotemporal distribution and changing channel conditions. Additionally, our fine-grained personalized learning method leverages frequency domain analysis to extract and retain both fundamental and personalized knowledge from local model parameters. This allows us to build highly accurate personalized models suited to each vehicle's data characteristics. Experimental results show that our method improves model accuracy by up to 10.31% and reduces training time by up to 24.93% compared to the latest personalized federated learning algorithms. © 2025 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

PyionNet: Pyramid Progressive Cross-Fusion network for Joint Classification of Hyperspectral and LiDAR Data

引用

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 2025年 18卷 12042-12058页

作者： Pan, Haizhu Zhang, Quanxiu Ge, Haimiao Liu, Moqi Shi, Cuiping Qiqihar University College of Computer and Control Engineering Qiqihar161000 China Qiqihar University Heilongjiang Key Laboratory of Big Data Network Security Detection and Analysis Qiqihar161000 China Xi'an Jiaotong University School of Information and Communications Engineering Shanxi Xi'an710049 China Huzhou University College of Information Engineering Huzhou313000 China

Joint hyperspectral (HS) and Light Detection and Ranging (LiDAR) data for land cover classification have received widespread attention. Nevertheless, existing methods often struggle with multi-scale feature extraction and multi-source feature fusion. To address these issues, this paper proposes a pyramid progressive cross-fusion network, named PyionNet, for joint classification of HS and LiDAR data. Technically, the proposed PyionNet incorporates a pyramid multi-scale extraction (PME) module cascaded with a progressive cross-fusion (PCF) module, which are designed to extract multi-scale features and fuse multi-source features, respectively. Specifically, the PME module employs pyramid spectral and spatial convolutional blocks to extract and aggregate features from HS and LiDAR data, respectively, then uses an expansion-compression strategy to eliminate redundant information, and thus achieve a compact multi-scale feature representation. Moreover, the PCF module utilizes the transformer architecture and introduces two innovative feature fusion blocks, i.e., the discrepancy feature fusion (DFF) block and the common feature fusion (CFF) block, to progressively integrate multi-source and multi-scale features extracted by the PME module. The DFF block is designed to integrate discrepancy features between HS and LiDAR data to enhance complementary information. Subsequently, the CFF block focuses on fusing common features to progressively enrich the fused representation of the DFF block and further enhance the representation power. Experiments on three real-world datasets demonstrate that the proposed PyionNet outperforms state-of-the-art methods in both qualitative and quantitative results. © 2008-2012 IEEE.

关键词： Feature Selection

来源：评论

学校读者我要写书评

暂无评论

A two-path fiber-optic AE demodulation algorithm based on Numerically Stable Direct Least Squares Fitting of Ellipses

引用

Journal of Lightwave Technology 2025年

作者： Li, Xinhao Zhang, Faxiang Sun, Zhihui Jiang, Shaodong Jinan China Shandong Fundamental Research Center for Computer Science Shandong Provincial Key Laboratory of Industrial Network and Information System Security Jinan China

The 3 × 3 coupler demodulation algorithm commonly employs ellipse fitting algorithms (EFAs) to eliminate coupler asymmetry. In the detection scenario of fiber-optic acoustic emission (AE) sensor arrays, the amount of data increases significantly due to the high sampling rate and multi-channel characteristics. Traditional EFAs require substantial computational resources and involve complex calculations, which severely hinder demodulation efficiency. To address these issues, We propose a two-path demodulation algorithm based on Numerically Stable Direct Least Squares Fitting of Ellipses (NSDLS). The algorithm only two input signals and divides the fitting process into linear and quadratic components, reducing computational complexity. The triggered ellipse fitting judgment method is introduced to mitigate background noise impact on fitting results and enhance demodulation efficiency. Experimental results demonstrate that the proposed two-path demodulation algorithm based on NSDLS reduces time consumption by approximately 40 times and the CPU utilization by 40% compared with traditional EFAs demodulation algorithm, improves SINAD by 18.93 dB compared with the improved Naval Postgraduate School (NPS) method. The algorithm achieves a dynamic range of 126.04 dB @ 1 kHz, 0.075% THD, and 99.999% response linearity. This method maintains high demodulation accuracy while significantly reducing computational resource demands, lowering hardware costs, and improving overall demodulation efficiency. © 1983-2012 IEEE.

关键词： Acoustic emission testing

来源：评论

学校读者我要写书评

暂无评论

A Fast recognition method for DVS perimeter security intrusion signals based on transfer learning

引用

Optical Fiber Technology 2025年 93卷

作者： Shen, Yongxu Wang, Chang Sun, Zhihui Zhang, Faxiang Jiang, Shaodong Liu, Xu Gao, Fengxia Jinan China Shandong Provincial Key Laboratory of Industrial Network and Information System Security Shandong Fundamental Research Center for Computer Science Jinan China

In the perimeter security intrusion signal monitoring based on the Distributed Optical Fiber Vibration Sensing (DVS) system, the common approach for identifying intrusion signals in new scenarios is to collect large amounts of data and perform large-scale, long-term retraining of the initial network. However, this process consumes a significant amount of human resources and computational power each time. To address this issue, this paper proposes a transfer learning method. Using 53,000 sample data from six types of events collected in the laboratory, an SE-Densenet model was trained for 300 epochs on three NVIDIA A100 Tensor Core GPUs at the National Supercomputing Center in Jinan. Then, through the transfer learning approach, fine-tuning was performed on the new scenario by freezing 1/2 and 1/4 of the network layers and applying a feature extractor method. The fine-tuning training was carried out on a laptop equipped with 16 GB of memory and an Intel Core i7-12700 CPU. Experimental results show that, after 19.81 min of retraining using 600 data points from the new scenario, the feature extractor method achieved a test accuracy of 97.53 %. Compared to the other two methods, the training time was reduced by 20.87 min and 9.34 min, respectively, while the test accuracy increased by 13.76 % and 3.83 %. Compared to retraining with 6000 sufficient data, the transfer learning method improved training time by 6 to 13 times while achieving similar recognition accuracy. This study provides a new, convenient, and efficient method for perimeter security intrusion signal recognition, enabling quick adaptation to new scenarios and application in common engineering upper-level computer systems. © 2025

关键词： network intrusion

来源：评论

学校读者我要写书评

暂无评论

Non-deterministic symmetric encryption communication system based on generative adversarial networks

引用

China Communications 2025年第5期22卷 273-284页

作者： Wu Xuguang Han Yiliang Zhang Minqing Zhu Shuaishuai Li Yu College of Cryptography Engineering Engineering University of People's Armed Police Xi'an 710086 China Key Laboratory of Network and Information Security Under the People's Armed Police Xi'an 710086 China

Symmetric encryption algorithms learned by the previous proposed end-to-end adversarial network encryption communication systems are deterministic. With the same key and same plaintext, the deterministic algorithm will lead to the same ciphertext. This means that the key in the deterministic encryption algorithm can only be used once, thus the encryption is not practical. To solve this problem, a nondeterministic symmetric encryption end-to-end communication system based on generative adversarial networks is proposed. We design a nonce-based adversarial neural network model, where a “nonce” standing for “number used only once” is passed to communication participants, and does not need to be secret. Moreover, we optimize the network structure through adding Batch Normalization (BN) to the CNNs (Convolutional Neural networks), selecting the appropriate activation functions, and setting appropriate CNNs parameters. Results of experiments and analysis show that our system can achieve non-deterministic symmetric encryption, where Alice encrypting the same plaintext with the key twice will generate different ciphertexts, and Bob can decrypt all these different ciphertexts of the same plaintext to the correct plaintext. And our proposed system has fast convergence and the correct rate of decryption when the plaintext length is 256 or even longer.

关键词： Encryption Cryptography Generative adversarial networks Neural networks security Communication systems Training Software algorithms Measurement Ice

来源：评论

学校读者我要写书评

暂无评论

VFLMonitor: Defending One-Party Hijacking Attacks in Vertical Federated Learning

引用

IEEE Transactions on information Forensics and security 2025年 20卷 4828-4843页

作者： Xu, Xiangrui Zhao, Yiwen Han, Yufei Zhu, Yongsheng Han, Zhen Xu, Guangquan Wang, Bin Ji, Shouling Wang, Wei Qingdao University of Science and Technology School of Information Science and Technology Qingdao266061 China University of Southern California Thomas Lord Department of Computer Science Los AngelesCA90007 United States INRIA Brittany Rennes35042 France Institute of Computing Technologies China Academy of Railway Sciences Corporation Ltd. Beijing100081 China Beijing Jiaotong University Beijing Key Laboratory of Security and Privacy in Intelligent Transportation Beijing100044 China College of Intelligence and Computing Tianjin300072 China Network and Data Security Hangzhou310053 China Zhejiang University College of Computer Science and Technology Zhejiang 310058 China Xi’an Jiaotong University Ministry of Education Key Laboratory for Intelligent Networks and Network Security Xi’an710049 China

Vertical Federated Learning (VFL) is susceptible to various one-party hijacking attacks, such as Replay and Generation attacks, where a single malicious client can manipulate the model to produce attacker-specified results, thereby compromising its reliability in real-world deployments. In this paper, we first uncover the underlying mechanisms of these attacks and observe that successful attacks induce significant discrepancies in the embedding-label associations across different clients. We establish a theoretical framework demonstrating how these discrepancies can serve as reliable indicators for detecting hijacking attempts. Building upon this insight, we propose VFLMonitor, a robust defense mechanism that leverages these embedding-label discrepancies to detect and mitigate hijacking attacks. Specifically, VFLMonitor identifies suspicious queries by analyzing differences in label estimations from multiple clients and applies a majority voting rule to correct or filter out these malicious queries. Moreover, VFLMonitor introduces a novel regularization strategy during training to reduce intra-class variance in embeddings, thereby enhancing their discriminative power and improving defense effectiveness. Extensive experiments were conducted on 5 real-world datasets against 2 different attack types under 3 attack scenarios. The results demonstrate that VFLMonitor can effectively identify and exclude potential hijacked requests in all types of one-party hijacking attacks, while maintaining a meager false positive rate for legitimate queries. © 2005-2012 IEEE.

关键词： Training Servers Electronic mail Artificial intelligence Reliability theory Predictive models Federated learning Data models Computational modeling Collaboration

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：