检索结果-内蒙古大学图书馆

International Joint Conference on Neural networks (IJCNN)

作者： Qiaobin Wang Haiyan Jin Haonan Su Zhaolin Xiao Department of Computer Science and Engineering Engineering Research Center Shaanxi Key Laboratory for Network Computing and Security Technology Human-Machine Integration Intelligent Robot Shaanxi University Xi'an University of Technology

In the low-light conditions, images are corrupted by low contrast and severe noise, but event cameras can capture event streams with clear edge structures. Therefore, we propose an Event-Guided Attention network for Low-light Image Enhancement (EGAN) using a dual branch network and recover clear structure with the guide of events. To overcome the lack of paired training datasets, we first synthesize the dataset containing low-light event streams, low-light images, and the ground truth (GT) normal-light images. Then, we develop an end-to-end dual branch network consisting of a Image Enhancement Branch (IEB) and a Gradient Reconstruction Branch (GRB). The GRB branch reconstructs image gradients using events, and the IEB enhances low-light images using reconstructed gradients. Moreover, we develops the Attention based Event-Image Feature Fusion Module (AEIFFM) which selectively fuses the event and low-light image features using the spatial and channel attention mechanism, and the fused features are concatenated into the IEB and GRB, which respectively generate the enhanced images with clear structure and more accurate gradient images. Extensive experiments on synthetic and real datasets demonstrate that the proposed EGAN produces visually more appealing enhancement images, and achieves a good performance in structure preservation and denoising over state-of-the-arts.

关键词：

来源：评论

学校读者我要写书评

暂无评论

FedBT: Effective and Robust Federated Unlearning via Bad Teacher Distillation for Secure Internet of Things

引用

IEEE Internet of Things Journal 2025年

作者： Wang, Fangwei Huo, Jiashuai Wang, Wei Zhang, Xi Liu, Yan Tan, Zhiyuan Wang, Changguang Hebei Normal University Key Laboratory of Network and Information Security of Hebei Province College of Computer and Cyber Security Shijiazhuang China Xidian University Hangzhou Institute of Technology Hangzhou China Edinburgh Napier University School of Computing Engineering and the Built Environment EdinburghEH10 5DT United Kingdom

Smart Internet of Things (IoT) devices generate vast, distributed data, and their limited computational and storage capacities complicate data protection. Federated Learning (FL) enables collaborative model training across clients, enhancing performance and protecting data privacy. The Right to be Forgotten (RTBF) raises the demand for precise data removal. Federated Unlearning (FU) offers a solution for accurate data deletion in FL systems. Existing FU methods often struggle to simultaneously ensure effective data forgetting and preserve model generalization. To mitigate these challenges, an effective and robust FU framework has been proposed, which is based on the "Bad Teacher" knowledge distillation (KD), termed FedBT. First, the "Bad Teacher" KD guides the trained model to eliminate specific client contributions from the global model. Next, the frequency domain extracts the global model’s generalization components. Finally, orthogonal constraints are applied to the KD-generated gradients within the orthogonal subspace of these components, ensuring the gradients preserve the trained model’s generalization ability. FedBT eliminates the need to store historical records of parameter updates. Using orthogonal space constraints, the generalization ability of the trained model is safeguarded during unlearning. Extensive experiments on three datasets with various metrics show our method reduces accuracy by only 0.53% on MNIST, 0.26% on Fashion-MNIST, and 4.67% on CIFAR10, surpassing the best approach. Furthermore, FedBT obtains an unlearning performance that most closely approximates the results obtained from retraining from scratch. FedBT boosts IoT security by enabling the "forgetting" of certain client data, crucial for protecting user privacy and ensuring secure device interactions. © 2014 IEEE.

关键词： Sensitive data

来源：评论

学校读者我要写书评

暂无评论

Analysis of Eavesdropping Region in Hybrid mmWave-Microwave Wireless Systems

引用

Wireless Communications and Mobile computing 2023年第1期2023卷

作者： Qu, Qianyue Zhang, Yuanyu Kasahara, Shoji Graduate School of Information Science Nara Institute of Science and Technology Ikoma Japan School of Computer Science and Technology Xidian University Xi’an China Shannxi Key Laboratory of Network and System Security Beijing Sunwise Information Technology Ltd Beijing China

Hybrid communication systems, where millimeter-wave (mmWave) links coexist with microwave links, have been an essential component in the fifth-generation (5G) wireless networks. Nevertheless, the open feature of the wireless medium makes hybrid systems vulnerable to eavesdropping attacks. Eavesdroppers in hybrid communication systems can enhance their attack performance by opportunistically eavesdropping on mmWave or microwave links. This paper, therefore, aims to answer a natural question: in which region do eavesdroppers prefer the mmWave links? To this end, we first formulate this question as an eavesdropping region characterization problem from the physical layer security perspective, where eavesdroppers select the link to eavesdrop based on the ratio between the security performances of the mmWave and microwave links. To model the security performances of both the mmWave and microwave links, we derive closed-form expressions for the secrecy outage probabilities and lower bounds/exact expressions for the secrecy rates of both links. Finally, we provide numerical results to validate our theoretical analysis and also illustrate the mmWave eavesdropping region under various network parameter settings. Copyright © 2023 Qianyue Qu et al.

关键词： Millimeter waves

来源：评论

学校读者我要写书评

暂无评论

GHTO: Improving Byzantine Robustness in Distributed Machine Learning Through Gradient Heterogeneity Twofold Optimization

GHTO: Improving Byzantine Robustness in Distributed Machine ...

引用

Frontiers technology of Information and Computer (ICFTIC), IEEE International Conference on

作者： Caiyun Li Ming Yang Jian Cao Xiaoming Wu Yunpeng He Xin Wang 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 Industrial Network and Information System Security Shandong Fundamental Research Center for Computer Science Jinan China Shandong Evayinfo Technology Co. Ltd Jinan P. R. China

ISBN: (数字)9798331541750

ISBN: (纸本)9798331541767

Heterogeneous datasets induce local gradient variance and global gradient variance in distributed learning, collectively referred to as gradient heterogeneity. Gradient heterogeneity increases the system's vulnerability to Byzantine attacks, affecting performance. To address this issue, the paper proposes a Gradient Heterogeneity Twofold Optimization (GHTO) algorithm to enhance the Byzantine robustness of the system in non-independent and identically distributed environments. Specifically, a Local Gradient Correction (LGC) algorithm is proposed, which aims to reduce the local gradient variance. By further integrating LGC with momentum and bucketing techniques to achieve dual optimization of local and global gradient variance. Experimental results demonstrate the proposed LGC algorithm diminishes local gradient variance, and the GHTO method optimizes both local and global gradient variance, which further strengthens the robustness of the system against Byzantine attacks.

关键词： Computer aided instruction Machine learning algorithms Distance learning Machine learning Robustness Optimization Resilience

来源：评论

学校读者我要写书评

暂无评论

FortisAVQA and MAVEN: a Benchmark Dataset and Debiasing Framework for Robust Multimodal Reasoning

arXiv

引用

arXiv 2025年

作者： Ma, Jie Gao, Zhitao Chai, Qi Liu, Jun Wang, Pinghui Tao, Jing Su, Zhou Ministry of Education of Key Laboratory for Intelligent Networks and Network Security School of Cyber Science and Engineering Xi’an Jiaotong University Shaanxi Xi’an710049 China Shannxi Provincial Key Laboratory of Big Data Knowledge Engineering School of Computer Science and Technology Xi’an Jiaotong University Shaanxi Xi’an710049 China Guangdong Guangzhou510000 China

Audio-Visual Question Answering (AVQA) is a challenging multimodal reasoning task requiring intelligent systems to answer natural language queries based on paired audio-video inputs accurately. However, existing AVQA approaches often suffer from overfitting to dataset biases, leading to poor robustness. Moreover, current datasets may not effectively diagnose these methods. To address these challenges, we first introduce a novel dataset, FortisAVQA, constructed in two stages: (1) rephrasing questions in the test split of the public MUSIC-AVQA dataset and (2) introducing distribution shifts across questions. The first stage expands the test space with greater diversity, while the second enables a refined robustness evaluation across rare, frequent, and overall question distributions. Second, we introduce a robust Multimodal Audio-Visual Epistemic network (MAVEN) that leverages a multifaceted cycle collaborative debiasing strategy to mitigate bias learning. Experimental results demonstrate that our architecture achieves state-of-the-art performance on FortisAVQA, with a notable improvement of 7.81%. Extensive ablation studies on both datasets validate the effectiveness of our debiasing components. Additionally, our evaluation reveals the limited robustness of existing multimodal QA methods. We also verify the plug-and-play capability of our strategy by integrating it with various baseline models across both datasets. Our dataset and code are available at https://***/reml-group/fortisavqa. Copyright © 2025, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Reversible Data Hiding Simultaneously Using Substitution of MSB and Compression of LSB of Encrypted Image 14

Reversible Data Hiding Simultaneously Using Substitution of ...

引用

14th International Conference on Digital Image Processing, ICDIP 2022

作者： Sui, Liansheng Liu, Jie Cheng, Ying Xiao, Zhaolin Tian, Ailing School of Computer Science and Engineering Xi’an University of Technology Xi’an710048 China Shaanxi Key Laboratory for Network Computing and Security Technology Xi’an710048 China Student’s Affairs Division Xi’an University of Technology Xi’an710048 China Shaanxi Province Key Lab of Thin Film Technology and Optical Test Xi’an Technological University Xi’an710048 China

ISBN: (纸本)9781510657564

With the development of privacy protection, reversible data hiding methods in encrypted image have drawn extensive research interest. Among them, a new method is proposed based on embedding prediction errors, i.e., EPE-based method, where secret information is embedded in the encrypted most significant bit plane. Not only the original image can be recovered with high quality but also the payload can reach close to 1 bit per pixel (bpp). However, there are potential errors in the process of extracting secret data, because most significant bits of a part of pixels are used as flags to mark prediction error location. In this paper, a reversible data hiding method in encrypted image with high capacity is proposed by combining most significant bit prediction with least significant bit compression. At first, most significant bit of each pixel is predicted and a location map of prediction errors in the original image is generated. In the same time, the original image is encrypted using a stream cipher method. Then, the location map is embedded into the vacated space generated with compressing least significant bits and the secret data is embedded into most significant bits of a part of pixels without prediction errors. In this way, the marked encrypted image is obtained. Finally, the original image can be recovered without any error and the secret information can be extracted correctly from the marked encrypted image. Experimental results show that the proposed method has better performance than EPE-based and other methods. © 2022 SPIE.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

A Multiple-Image Authentication Method Based on Phase-Only Hologram and Logistic Map

SSRN

引用

SSRN 2024年

作者： Liansheng, Sui Zishan, Jiang Haiwei, Lu Zhaolin, Xiao Tianyu, Zeng School of Computer Science and Engineering Xi’an University of Technology Xi’an710048 China Shaanxi Key Laboratory for Network Computing and Security Technology Xi’an710048 China Hebei Normal University Shijiazhuang050024 China Hebei Provincial Key Laboratory of Information Fusion and Intelligent Control Shijiazhuang050024 China

An interesting security method for multiple-image authentication scheme is proposed based on computer-generated holograms and logistic map. First, each original image is encoded as the complex-valued hologram under the point light source model. The resulting hologram is then converted to a phase-only hologram using the Floyd-Steinberg dithering algorithm. Second, each phase-only hologram is randomly sampled by the aid of a binary mask. Through the catenation of all selected pixels, a phase-only pixel sequence is formed. Finally, a non-periodic and non-converging sequence generated with logistic map is used to scramble this sequence. After only preserving the phase data of the scrambled sequence, the real-valued ciphertext carrying the information of all original images is obtained. In the process of authentication, although no valid information can be discerned from noisy reconstructed images at a small sampling rate, the verification of original images can be efficiently accomplished using the nonlinear correlation maps. Besides binary masks, the parameters of logistic map are served as secret keys. Due to their high sensitivity, the security of the proposed method is greatly enhanced. The proposed authentication mechanism has been demonstrated to be effective and robust through experiments. To our best knowledge, it is first time to implement multiple-image authentication using phase-only holograms, which can provide a new perspective for optical information security. © 2024, The Authors. All rights reserved.

关键词： Holograms

来源：评论

学校读者我要写书评

暂无评论

Neural network Driven by Density and Parallel Features for Field-Road Mode Mining

Neural Network Driven by Density and Parallel Features for F...

引用

International Conference on Computer Supported Cooperative Work in Design

作者： Fengqi Hao Xiyuan Zhao Cunxiang Bian Jinqiang Bai Qingyan Ding Faculty of Data Science City University of Macau Macau 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 Industrial Network and Information System Security Shandong Fundamental Research Center for Computer Science Jinan China

ISBN: (数字)9798331513054

ISBN: (纸本)9798331513061

Field-road mode mining (FRMM) has gained increasing attention because of its crucial role in machinery management. As the Global Navigation Satellite System (GNSS) is widely applied in agricultural machinery, many methods based on motion and spatial-temporal features of GNSS trajectory data have been proposed for FRMM. However, these methods ignore the density and parallel features of GNSS points. The two features are useful for FRMM because field points usually have a higher density and more parallel points than road points. Therefore, a neural network driven by density and parallel features is proposed for accurate FRMM. Firstly, a statistical method is designed to extract the density feature (i.e., the number of its neighbor points) and parallel feature (i.e., the number of approximately parallel points in its neighbors) of each point. Then, the two features and eight motion features (e.g., speed, direction, etc.) are fed into a neural network to extract valuable latent features. Finally, a linear classifier is used to identify the field and road categories of GNSS points based on the latent features. Experimental results show that our method outperforms state-of-the-art methods and achieves the accuracy of 91.69% and 86.44% on public Wheat and Paddy datasets, respectively.

关键词： Global navigation satellite system Accuracy Statistical analysis Federated learning Roads Neural networks Time series analysis Feature extraction Trajectory Data mining

来源：评论

学校读者我要写书评

暂无评论

TSF-Net:Abnormal Video Behavior Detection Framework Based on Two-Stream Appearance Motion Semantic Fusion 23

TSF-Net:Abnormal Video Behavior Detection Framework Based on...

引用

Proceedings of the 2023 International Conference on Information Education and Artificial Intelligence

作者： Bonan Li Rui Cao Xingang Wang Hong Zhang Jinyan Zhou China Radio and Television Shandong Network Co Ltd 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) China

ISBN: (纸本)9798400716157

Video anomalous behavior detection aims to detect rare and random anomalous events, which usually deviate from expectations. Existing detection methods do not consider the appearance semantics and motion semantics of the events in conjunction, so they lead to poor detection results. Since the appearance semantics and motion semantics of normal events are highly consistent and correspond, while the semantic consistency of abnormal events is low. Based on this, this paper proposes a two-stream fusion hybrid network for abnormal behavior detection. The appearance semantics and motion semantics of events are recorded separately using a multi-scale fused self-encoder to generate corresponding reconstructed appearance frames and reconstructed motion frames. Afterwards, the two frames are fused to generate the final prediction frame. We introduce temporal attention to enhance the model's ability to represent motion semantics and capture normal behavior with effective regular motion. Experiments on three standard public datasets show that the method proposed in this paper can accurately detect anomalous events with a performance comparable to state-of-the-art methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multi-Label Text Classification for Judicial Texts via Dual Graph and Label Feature Fusion

Multi-Label Text Classification for Judicial Texts via Dual ...

引用

Smart World Congress (SWC), IEEE

作者： Qiliang Gu Qin Lu Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Qilu University of Technology (Shandong Academy of Sciences) Jinan 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 Industrial Network and Information System Security Shandong Fundamental Research Center for Computer Science Jinan China

ISBN: (数字)9798331520861

ISBN: (纸本)9798331520878

The legal judgement prediction (LJP) of judicial texts represents a multi-label text classification (MLTC) problem, which in turn involves three distinct tasks: the prediction of charges, legal articles, and terms of penalty. Nevertheless, extant multi-label text classification models tend to eschew the consideration of multiple correlations and semantic information between labels when predicting judicial texts, which may result in the loss of pertinent information. Furthermore, these models do not take full advantage of the local and overall information of the labels in the process of selecting appropriate labels for the text using the multi-head attention mechanism. To address these issues, we propose a new model, BGFLFF, which explores label correlation and semantics among the three tasks by employing Graph Convolutional network (GCN) and multi-head attention mechanisms. In particular, we propose a Bi-Graph Fusion GCN (BGF-GCN), which fuses the co-occurrence matrix of labels with the cosine similarity matrix, thereby fully exploiting the multiple correlations between labels. Furthermore, prior to embedding the tags, the interpretations of the labels are obtained via Google in order to enhance the semantic information between the labels. To further reinforce the interconnections between labels and text and more effectively comprehend the interrelationships between the three tasks, we propose a Multi-Head Label Feature Fusion Attentional Mechanism (MH-LFFAtt), which assigns distinct weights to the pertinent label information in the text by fusing the local and overall features of the labels. The experimental results demonstrate that the F1 score exhibits an improvement of up to ${2. 2 8 \%}$ and a minimum of ${1. 2 9 \%}$ across the various tasks of the two datasets. This evidence substantiates the assertion that BGFLFF outperforms the existing baseline model.

关键词： Attention mechanisms Correlation Law Graph convolutional networks Fuses Text categorization Semantics Predictive models Multitasking Internet

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：