检索结果-内蒙古大学图书馆

IEEE International Conference on Multimedia and Expo (ICME)

作者： Zhenqiang Zhang Chuantao Li Jian Song Jialiang Lv Chunxiao Wang Zhigang Zhao Jidong Huo Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center (National Supercomputer Center in Jinan) Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China China University of Petroleum (East China) Qingdao China

ISBN: (数字)9798350390155

ISBN: (纸本)9798350390162

Underwater Image Restoration technology (UIRT) constitutes a pivotal base for subsequent tasks yet confronts obstacles like data scarcity and image distortion in practical deployments. To optimize the use of scarce annotated and copious unlabeled data, we introduce an avant-garde semi-supervised method for underwater image restoration, named STUI-Net. Concurrently, we develop a novel teacher-student architecture utilizing Transformer technology, named GFT-Net. Initially, GFT-Net employs a tripartite branch network—comprising Gradient, Feature Extraction, and Transformer modules to thoroughly extract features from underwater images. This method then amalgamates multi-source features, encompassing edge, gradient, local, and global data, addressing underwater image deterioration in multifaceted environments. Additionally, we engineer a Supervisor role to rectify potential misdirection by the teacher network in the semi-supervised model, thereby enhancing training stability on unlabeled datasets. Empirical studies affirm the robust generalization competence of STUI-Net in authentic underwater environments.

关键词： Measurement Training Image quality Transformers Feature extraction Stability analysis Robustness

来源：评论

学校读者我要写书评

暂无评论

On the Effectiveness of Function-Level Vulnerability Detectors for Inter-Procedural Vulnerabilities

On the Effectiveness of Function-Level Vulnerability Detecto...

引用

International Conference on Software Engineering (ICSE)

作者： Zhen Li Ning Wang Deqing Zou Yating Li Ruqian Zhang Shouhuai Xu Chao Zhang Hai Jin National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security Cluster and Grid Computing Lab School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan China Jin YinHu Laboratory Wuhan China Department of Computer Science University of Colorado Colorado Springs Colorado Springs Colorado USA Institute for Network Sciences and Cyberspace Tsinghua University Beijing China School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China

ISBN: (数字)9798400702174

ISBN: (纸本)9798350382143

Software vulnerabilities are a major cyber threat and it is important to detect them. One important approach to detecting vulnerabilities is to use deep learning while treating a program function as a whole, known as function-level vulnerability detectors. However, the limitation of this approach is not understood. In this paper, we investigate its limitation in detecting one class of vulnerabilities known as inter-procedural vulnerabilities, where the to-be-patched statements and the vulnerability-triggering statements belong to different functions. For this purpose, we create the first Inter -Procedural Vulnerability Dataset (InterPVD) based on C/C++ open-source software, and we propose a tool dubbed VulTrigger for identifying vulnerability-triggering statements across functions. Experimental results show that VulTrigger can effectively identify vulnerability-triggering statements and inter-procedural vulnerabilities. Our findings include: (i) inter-procedural vulnerabilities are prevalent with an average of 2.8 inter-procedural layers; and (ii) function-level vulner-ability detectors are much less effective in detecting to-be-patched functions of inter-procedural vulnerabilities than detecting their counterparts of intra-procedural vulnerabilities.

关键词： Deep learning Detectors Open source software Software engineering

来源：评论

学校读者我要写书评

暂无评论

Contrastive Learning for Chest X-ray Classification: A Fusion of Topological Data Analysis and ResNet

Contrastive Learning for Chest X-ray Classification: A Fusio...

引用

IEEE International Conference on Data Science in Cyberspace (DSC)

作者： Hao Ren Zeyu Luo Fengshi Jing Xinyue Zhang Han He Yonghao Yu Dawei Zhao Faculty of Data Science City University of Macau China Minzu University of China Beijing China Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China

ISBN: (数字)9798350391367

ISBN: (纸本)9798350391374

Lung diseases such as pneumonia and tuberculosis present significant global health challenges, leading to millions of deaths annually. Chest X-ray imaging is crucial for diagnosing these conditions, but interpretation often relies on specialized radiologists, creating barriers in resource-limited areas. This study introduces a novel framework integrating topological data analysis (TDA), deep learning with ResNet-50, and contrastive learning to enhance the accuracy and computational efficiency of chest X-ray analysis. TDA captures global topological structures, while ResNet-50 extracts detailed local features. Contrastive learning then optimizes the feature space, enhancing the model’s discriminative power and generalization capabilities. Comprehensive evaluations on multiple datasets demonstrate the framework’s robustness and effectiveness, showing substantial improvements in diagnostic performance and computational efficiency. These findings suggest that the proposed approach is well-suited for real-time clinical applications, especially in resource-limited settings. Future work will focus on further optimizing the model and exploring its application to other medical imaging modalities, broadening its clinical utility.

关键词： Deep learning Accuracy Computational modeling Contrastive learning Feature extraction Robustness Real-time systems Computational efficiency X-ray imaging Biomedical imaging

来源：评论

学校读者我要写书评

暂无评论

Enhancing Small Object Detection in Aerial Imagery Based on Strong Feature Extraction and Batch Dimension

Enhancing Small Object Detection in Aerial Imagery Based on ...

引用

International Joint Conference on Neural networks (IJCNN)

作者： Bingnan Cao Di Wang Ying Guo Hu Zhang Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center (National Supercomputer Center in Jinan) Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China The Institute of Data Science City University of Macau Macau China

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

Object detection is a fundamental component of computer vision, playing a pivotal role in various applications. However, the accurate detection of small and densely distributed objects remains a challenging problem in this field. This challenge is particularly exacerbated in the context of aerial imagery, characterized by its distinctive bird’s-eye view, intricate backgrounds, and the variability in object appearances. This paper addresses these persistent challenges in object detection, with a focus on the specific difficulties posed by aerial images. We propose a deformable end-to-end object detection with transformers (DETR)-based framework to enhance small object detection accuracy, ultimately contributing to improved computer vision capabilities in domains like remote sensing, surveillance, and autonomous aerial systems. Firstly, in order to aggregate the entire input sequence information in the backbone network and improve the detection accuracy of small objects, we propose DMCA based on deformable features and attention mechanisms. Secondly, in order to capture and model the relationships between samples for dense pixel-level representations in small objects and improve the detection accuracy of small objects, we try to introduce BatchEncoder by implementing an encoder in the batch dimension. Experimental results show that, compared to the baseline, our method significantly improves the accuracy of small object detection in aerial images. The processing and analysis of a large amount of remote sensing data require powerful computing power. The computing power Internet can integrate the scattered computing resources to provide flexible and scalable computing power to meet the computing needs of different sizes and types.

关键词： Computer vision Accuracy Surveillance Object detection Detectors Transformers Feature extraction

来源：评论

学校读者我要写书评

暂无评论

A Short-Term Electric Load Forecasting Method Based on the Fusion of Global and Local Features

A Short-Term Electric Load Forecasting Method Based on the F...

引用

IEEE International Conference on Data Science in Cyberspace (DSC)

作者： Haozhan Gu Hangwei Tian Jingchun Wang Yumei Li Shandong University Of Arts Academy of Fine Arts China Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center (National Supercomputer Center in Jinan) Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China

ISBN: (数字)9798350391367

ISBN: (纸本)9798350391374

Accurate short-term electric load forecasting is crucial for ensuring the stability and efficiency of the power grid. This study proposes an innovative dual-branch electric load forecasting model that enhances the accuracy of predictions by processing global and local features in parallel. Global features are extracted through the Savitzky-Golay filter and a linear model to capture the overall trends of the load data. Local features are identified using the Convolutional Self-Attention Module, which integrates the local perception capabilities of Convolutional neural network with the self-attention mechanism of Transformers. By employing a Weighted Feature Fusion network, we effectively integrate global and local information to enhance the performance of load forecasting. Experimental results demonstrate that the proposed model significantly outperforms existing models in predictive performance. The model presented in this study offers a new perspective on electric load forecasting and has the potential to become an effective tool for power system planning and scheduling.

关键词： Accuracy Load forecasting Electricity Nonlinear filters Predictive models Power system stability Feature extraction Transformers Data models Load modeling

来源：评论

学校读者我要写书评

暂无评论

Local Differential Privacy is Not Enough: A Sample Reconstruction Attack against Federated Learning with Local Differential Privacy

arXiv

引用

arXiv 2025年

作者： You, Zhichao Dong, Xuewen Li, Shujun Liu, Ximeng Ma, Siqi Shen, Yulong School of Computer Science & Technology Xidian University China Shaanxi Key Laboratory of Network and System Security Xi’an China University of Kent Canterbury United Kingdom College of Computer and Data Science Fuzhou University Fuzhou China School of System and Computing University of New South Wales CanberraACT2612 Australia

Reconstruction attacks against federated learning (FL) aim to reconstruct users’ samples through users’ uploaded gradients. Local differential privacy (LDP) is regarded as an effective defense against various attacks, including sample reconstruction in FL, where gradients are clipped and perturbed. Existing attacks are ineffective in FL with LDP since clipped and perturbed gradients obliterate most sample information for reconstruction. Besides, existing attacks embed additional sample information into gradients to improve the attack effect and cause gradient expansion, leading to a more severe gradient clipping in FL with LDP. In this paper, we propose a sample reconstruction attack against LDP-based FL with any target models to reconstruct victims’ sensitive samples to illustrate that FL with LDP is not flawless. Considering gradient expansion in reconstruction attacks and noise in LDP, the core of the proposed attack is gradient compression and reconstructed sample denoising. For gradient compression, an inference structure based on sample characteristics is presented to reduce redundant gradients against LDP. For reconstructed sample denoising, we artificially introduce zero gradients to observe noise distribution and scale confidence interval to filter the noise. Theoretical proof guarantees the effectiveness of the proposed attack. Evaluations show that the proposed attack is the only attack that reconstructs victims’ training samples in LDP-based FL and has little impact on the target model’s accuracy. We conclude that LDP-based FL needs further improvements to defend against sample reconstruction attacks effectively. Copyright © 2025, The Authors. All rights reserved.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Optimization Strategy for Remote Differential Upgrade of IoT Firmware

Optimization Strategy for Remote Differential Upgrade of IoT...

引用

IEEE Joint International Information technology and Artificial Intelligence Conference (ITAIC)

作者： Wenkang Ding Ruirui Sun Qinglong Meng Zhong Wan Guanghe Cheng Huijuan Hao Jinqiang Bai Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center (National Supercomputer Center in Jinan) Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China

With the continuous increase of IoT devices, the management and optimization of devices become particularly important. The update cycle of device functions is short, and in order to facilitate management and optimize device performance, a fast and convenient upgrade method is needed to solve this problem. Remote upgrade technology is mainly divided into full package upgrade and differential upgrade. Compared to full package upgrade, differential upgrade has obvious advantages in remote upgrade of large files. The main problem with current differential upgrade is the problem of slow generation speed while ensuring a certain size range of differential packages. This article proposes an improved Bsdiff algorithm to solve the problem of slow generation speed of differential packages. Experimental verification shows that the efficiency of remote upgrade has been improved, Improved the speed of differential packet generation and upgrade efficiency while ensuring the size of differential packets.

关键词：

来源：评论

学校读者我要写书评

暂无评论

CA-STCNN: An Attention-based Hybrid Deep Learning Model for Encrypted Traffic Classification

CA-STCNN: An Attention-based Hybrid Deep Learning Model for ...

引用

Asia-Pacific network Operations and Management Symposium (APNOMS)

作者： Hongyang Sun Huiling Shi Lei Zhang Lei Huang Wei Zhang Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center (National Supercomputer Center in Jinan) Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China

With the increasing trend of network traffic encryption, both normal and abnormal traffic have begun to utilize encryption techniques to conceal their behavior, making accurate identification of encrypted traffic an essential prerequisite for network management and security. Current traffic classification methods generally suffer from inadequate feature extraction and lower multi-classification accuracy. This paper proposes a multiclassification hybrid deep learning model for encrypted traffic, called channel attention-based spatiotemporal convolutional neural network (CA-STCNN). The model extracts spatial features by convolutional neural network (CNN) and then introduces temporal convolutional neural network (TCN) to extract the temporal features. Using the convolution structure with more stable gradients can ensure the robustness of spatiotemporal feature extraction. Furthermore, the model also introduces the channel attention mechanism to assign weights to features in the channel dimension according to their contributions to classification. In the multi-classification experiments conducted using the ISCXVPN dataset, CA-STCNN outperforms existing methods in terms of accuracy, precision, recall, and F1 score.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Felix: A Model of Detecting Off-chain Abnormal States in Decentralized Applications

Felix: A Model of Detecting Off-chain Abnormal States in Dec...

引用

IEEE International Conference on Trust, security and Privacy in computing and Communications (TrustCom)

作者： Lianhai Wang Qihao Huang Wei Shao Jinpeng Wang Xiaoqian Liu Fansheng Wang Ministry of Education Shandong Computer Science Center (National Supercomputer Center in Jinan) Key Laboratory of Computing Power Network and Information Security Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China

ISBN: (数字)9798350381993

ISBN: (纸本)9798350382006

With the rapid development of blockchain technology, the use of decentralized applications (DApps) has experienced significant growth. However, current testing methods for DApps primarily focus on testing the smart contracts on the blockchain, which are the foundation of DApps, but lack a comprehensive approach to effectively detect off-chain abnormal states. To address this issue, this paper proposes a generic abnormal state detection model based on off-chain transaction data. The model leverages the DApp program code logic to set up test oracles to analyze off-chain transaction data. Experimental results demonstrate that the model achieves high accuracy in detecting off-chain abnormal states, with a prediction accuracy as high as 96.3%. Furthermore, a comparison with other related vulnerability detection methods shows the advantages of the proposed approach.

关键词： Analytical models Technological innovation Privacy Smart contracts Decentralized applications Data models Blockchains

来源：评论

学校读者我要写书评

暂无评论

Continuous Verification of Catastrophic Recalling in Machine Unlearning via Adversarial Testing

Continuous Verification of Catastrophic Recalling in Machine...

引用

IEEE International Conference on Data Science in Cyberspace (DSC)

作者： Y. Neil Qu Zonghao Ji Lei Cui Chong Zhang Lei Liu Zhiyi Tian Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China School of IT Deakin University VIC Australia Guangzhou Institute of Technology Xidian University Guangzhou China School of Computer Science University of Technology Sydney NSW Australia

ISBN: (数字)9798350391367

ISBN: (纸本)9798350391374

Throughout the process of machine unlearning, in order to fulfill the requirements of machine unlearning and to comply with the rules of the right to be forgotten, it is natural to verify whether the unlearning model actually removes data points. Therefore, machine unlearning verification plays a crucial role. However, existing validation methods only perform one validation, and it is still challenging to determine whether subsequent updates of the model still maintain the unlearning effect. To address this challenge, we propose a novel continuous verification of catastrophic recalling in machine unlearning framework that aims to continuously evaluate whether a machine learning model effectively forgets specified data after an update. In this work, we first introduce adversarial testing as a crucial part of the overall framework. Verification then continues as the unlearned model is updated (adding or continuing to forget data points). We also analyzed the possibility that learning new data after unlearning may diminish the effect. Overall, our continuous unlearning verification framework provides a proactive approach to protecting individual privacy in the machine learning domain, thus facilitating the generation of more robust unlearning algorithms.

关键词： Privacy Machine learning algorithms Cyberspace Machine learning Data science Data models Testing

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：