检索结果-内蒙古大学图书馆

29th IEEE International Conference on Parallel and Distributed Systems, ICPADS 2023

作者： Qiu, Ran Liang, Hu Liu, Yuchen Zhao, Shengrong Qilu University of Technology Shandong Academy of Sciences Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Jinan China Qilu University of Technology Shandong Academy of Sciences Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Jinan China Shandong Fundamental Research Center for Computer Science Shandong Provincial Key Laboratory of Computer Networks Jinan China

ISBN: (纸本)9798350330717

Image inpainting, which aims to reconstruct reasonably clear and realistic images from known pixel information, is one of the core problems in computer vision. However, due to the complexity and variability of the underwater environment, the inability to extract valid pixel points and insufficient correlation between feature information in existing image inpainting techniques lead to blurring in the generated images. Therefore, a novel gated attention feature fusion image inpainting network based on generative adversarial networks (GAF-GAN) is proposed. The accuracy of feature similarity matching depends heavily on the validity of the information contained in the features. On the one hand, gating values are dynamically generated by gated convolution to reduce the interference of invalid information. On the other hand, semantic information at distant locations in an image is accurately acquired by the attention mechanism. For these reasons, we designed an improved gated attention mechanism. Gated attention mechanism make the network focus on effective information such as high-frequency texture and color fidelity of restored images. In addition, the dense feature fusion module is added to expand the overall receptive field of the network to fully learn the image features. Experimental results show that the proposed method can effectively repair defective images with complex texture structures and improve the reality and integrity of image details and structures. © 2023 IEEE.

关键词： Dense feature fusion module Gated attention mechanism Image inpainting Underwater environment

来源：评论

学校读者我要写书评

暂无评论

Vulnerability knowledge extraction method based on joint extraction model 9

Vulnerability knowledge extraction method based on joint ext...

引用

9th International Conference on Advanced Cloud and Big Data, CBD 2021

作者： Liu, Zhen Di, XiaoQiang Song, Wei Ren, WeiWu Jilin Key Laboratory of Network and Information Security Changchun University of Science and Tecchnology Changchun China School of Computer Science and Technology Changchun University of Science of Technology Changchun China Information Center Changchun University of Science and Technology Changchun China

ISBN: (纸本)9781665407458

information extraction is an important semantic processing task to construct network security knowledge graph. Extracting entities and relationships in vulnerability description from public data sets will inevitably lead to waste of manpower and difficulty in accurate positioning. Another challenge is that there are multiple relationships among vulnerable descriptors. This paper proposes a framework for the common vulnerabilities and exposures (CVE) analysis, which consists of entity annotation algorithm and relational classification model. In particular, we apply the model to CVE dataset to solve the problem of information extraction and relationship classification in the CVE vulnerability analysis. Moreover, the predicted relationship is used to construct vulnerability security knowledge graph. The experimental results show that the framework can deal with the CVE vulnerability description effectively, and has good relationship classification performance. © 2022 IEEE.

关键词： network security

来源：评论

学校读者我要写书评

暂无评论

network security Situation Prediction Implemented by Attention and BiLSTM

Network Security Situation Prediction Implemented by Attenti...

引用

2022 International Conference on networking and network Applications, NaNA 2022

作者： Zhao, Dongmei Wu, Yaxing Li, Qingru Hebei Normal University Hebei Provincial Key Laboratory of Network and Information Security Shijiazhuang China Hebei Normal University College of Computer and Cyberspce Security Shijiazhuang China Hebei Normal University Hebei Supply Chain Big Data Analysis Data Security Engineering Research Center Shijiazhuang China

ISBN: (数字)9781665461313

ISBN: (纸本)9781665461313

With the increasing diversification and complexity of network security attacks, it is becoming more and more difficult to predict the network situation. In order to improve the effect of situation prediction, this paper constructs a network security situation prediction model for a Improved Particle Swarm Optimization and Attention fusion Bidirectional Long Short-Term Memory (IPSO-ABiLSTM). First, there is no real situation value for the UNSW-NB15 data set, and a situation value is generated based on the impact of the attack. Secondly, the particle swarm algorithm is improved. The IPSO algorithm makes the algorithm's global and local search capabilities more balanced and faster to converge. Finally, optimizing the hyperparameters of the BiLSTM network fused with the attention mechanism to obtain the final model, and combined with PSO-BiLSTM network, PSO-LSTM network, BiLSTM model for performance comparison. The experimental results show that the IPSO-ABiLSTM in this paper has a fitting degree of up to 0.9922, and the error value is relatively smaller, which verifies the effectiveness of the model proposed in this paper in the network security situation prediction problem. © 2022 IEEE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

OpenViewer: Openness-Aware Multi-View Learning

arXiv

引用

arXiv 2024年

作者： Du, Shide Fang, Zihan Tan, Yanchao Wang, Changwei Wang, Shiping Guo, Wenzhong College of Computer and Data Science Fuzhou University Fuzhou China Fujian Provincial Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou University Fuzhou China Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Qilu University of Technology Jinan China

Multi-view learning methods leverage multiple data sources to enhance perception by mining correlations across views, typically relying on predefined categories. However, deploying these models in real-world scenarios presents two primary openness challenges. 1) Lack of Interpretability: The integration mechanisms of multi-view data in existing black-box models remain poorly explained;2) Insufficient Generalization: Most models are not adapted to multi-view scenarios involving unknown categories. To address these challenges, we propose OpenViewer, an openness-aware multi-view learning framework with theoretical support. This framework begins with a Pseudo-Unknown Sample Generation Mechanism to efficiently simulate open multi-view environments and previously adapt to potential unknown samples. Subsequently, we introduce an Expression-Enhanced Deep Unfolding network to intuitively promote interpretability by systematically constructing functional prior-mapping modules and effectively providing a more transparent integration mechanism for multi-view data. Additionally, we establish a Perception-Augmented Open-Set Training Regime to significantly enhance generalization by precisely boosting confidences for known categories and carefully suppressing inappropriate confidences for unknown ones. Experimental results demonstrate that OpenViewer effectively addresses openness challenges while ensuring recognition performance for both known and unknown samples. Copyright © 2024, The Authors. All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

An Active Learning Framework for Continuous Rapid Rumor Detection in Evolving Social Media

An Active Learning Framework for Continuous Rapid Rumor Dete...

引用

International Joint Conference on Neural networks (IJCNN)

作者： Zhejie Shao Guoyong Cai Qinghua Liu Yunxian Shang College of Computer and Information Security Guilin University of Electronic Technology Guangxi China Guangxi Key Lab of Trusted Software Guangxi China

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

The widespread of social media has led to the propagation of rumors, resulting in detrimental effects on society. Existing rumor detection methods rely on labeled data and face challenges in obtaining sufficient data, particularly in the early stages of rumor propagation. Active learning has been proposed as a solution to reduce labeling costs by selecting significant samples for training. However, applying active learning to rumor detection presents challenges, such as sensitivity to initial sets and performance loss due to sample reduction. Inspired by Active learning, Contrastive learning, and Prompt tuning, we propose a novel Rumor Detection framework named ACP-RD in this paper. ACP-RD addresses the limitations of active learning by leveraging the benefits of contrastive learning and prompt tuning. Our framework reduces labeling costs, improves rumor detection performance in zero-shot scenarios, aligns active query criteria with downstream tasks through unsupervised contrastive learning, and optimizes word embeddings using supervised contrastive learning. Experimental results demonstrate that ACP-RD achieves superior performance compared to fine-tuning with the whole labeled dataset, using only 10% of the labeled data. Overall, our proposed framework presents a novel and efficient approach to rumor detection, with potential for broader applications in natural language classification tasks.

关键词： Training Costs Sensitivity Social networking (online) Natural languages Neural networks Contrastive learning

来源：评论

学校读者我要写书评

暂无评论

Distributionally robust optimization based chance-constrained energy management for hybrid energy powered cellular networks

引用

Digital Communications and networks 2023年第3期9卷 797-808页

作者： Pengfei Du Hongjiang Lei Imran Shafique Ansari Jianbo Du Xiaoli Chu The Engineering Research Center of Intelligent Air-ground Integrated Vehicle and Traffic Control Ministry of EducationXihua UniversityChengdu610039China Chongqing Key Lab of Mobile Communications Technology Chongqing University of Posts and TelecommunicationsChongqing400065China James Watt School of Engineering University of GlasgowGlasgowG128QQUK Shaanxi Key Laboratory of Information Communication Network and Security Xi'an University of Posts and TelecommunicationsXi'an710121China Electronic and Electrical Engineering University of SheffieldSheffieldS102TNUK

Energy harvesting has been recognized as a promising technique with which to effectively reduce carbon emis-sions and electricity expenses of base ***,renewable energy is inherently stochastic and inter-mittent,imposing formidable challenges on reliably satisfying users'time-varying wireless traffic *** addition,the probability distribution of the renewable energy or users’wireless traffic demand is not always fully known in *** this paper,we minimize the total energy cost of a hybrid-energy-powered cellular network by jointly optimizing the energy sharing among base stations,the battery charging and discharging rates,and the energy purchased from the grid under the constraint of a limited battery size at each base *** solving the formulated non-convex chance-constrained stochastic optimization problem,a new ambiguity set is built to characterize the uncertainties in the renewable energy and wireless traffic demands according to interval sets of the mean and *** this ambiguity set,the original optimization problem is transformed into a more tractable second-order cone programming problem by exploiting the distributionally robust optimization ***,a low-complexity distributionally robust chance-constrained energy management algo-rithm,which requires only interval sets of the mean and covariance of stochastic parameters,is *** results of extensive simulation are presented to demonstrate that the proposed algorithm outperforms existing methods in terms of the computational complexity,energy cost,and reliability.

关键词： Cellular networks Energy harvesting Energy management Chance-constrained Distributionally robust optimization

来源：评论

学校读者我要写书评

暂无评论

KGAPG: Knowledge-Aware Neural Group Representation Learning for Attentive Prescription Generation of Traditional Chinese Medicine

KGAPG: Knowledge-Aware Neural Group Representation Learning ...

引用

2021 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2021

作者： Li, Shuchen Wang, Wei He, Jieyue MOE Southeast University Key Lab of Computer Network Information Integration Nanjing China

ISBN: (纸本)9781665401265

Prescriptions play an essential role in the process of Traditional Chinese Medicine (TCM) diagnosis and treatment. Prescription generation is to generate a set of herbs to treat the symptoms of a patient by analyzing the relationship between symptoms and herbs. Although there have been a couple of studies to generate prescriptions, they have ignored the implicit relationship between the different symptoms of the patients. In addition, abundant semantic information and interpretability of the knowledge graph can help to portray the complicated relationships between the various modules of TCM. Therefore, this paper proposes a Knowledge-Aware neural Group representation learning model for Attentive Prescription Generation of Traditional Chinese Medicine (KGAPG), which regards the prescription generation task as a group recommendation problem. More specifically, multiple symptoms of a patient are considered as a symptom group and the complicated semantic information between symptoms and herbs can be captured by the knowledge graph. The syndrome information of multiple symptoms which is summarized by a group aggregation method based on the attention mechanism is applied to simulate the actual process of TCM diagnosis and treatment. The experiment results demonstrate that KGAPG is effective on a TCM prescription benchmark dataset, and its evaluation indicators of Precision, Recall and NDCG exceed other state-of-the-art methods. © 2021 IEEE.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

A study of watermarking techniques for data publishing

引用

Multimedia Tools and Applications 2025年 1-30页

作者： Yuan, Shuguang Yu, Jing Yang, Ke Wang, Yuyang Li, Zhaochen Qiu, Jiabao Yang, Tengfei Chen, Chi Institute of Information Engineering Chinese Academy of Science Beijing China State Key Laboratory of Cyberspace Security Defense Beijing China School of Cyber Security University of Chinese Academy of Sciences Beijing China National Computer Network Emergency Response Technical Team/Coordination Center of China Beijing China

In today’s digital era, data sharing is becoming an emerging trend. However, copying, manipulating, and distributing multimedia data over an open channel is easy. Watermarking is one of the most promising methods for copyright protection, tamper detection, and traitor tracing tasks. In the past decades, many diversified watermarking techniques have been created and are still developing, which entails various requirements and challenges. In this paper, we survey recent watermarking techniques on data publishing scenarios. The main contributions of this paper include: 1) We explain the classification methods and background knowledge of watermarking techniques, such as types of function, watermarking process, and basic concepts;2) We primarily survey watermarking techniques for data publishing on different carriers, i.e., relational database, text, print and social media;3) We give representation figures and detailed analysis tables for the essential researches;4) Finally, it provides a discussion of future work according to analysis and observation of existing works. This survey allows researchers, users, and engineers to use efficient watermarking tools to secure published data. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2025.

关键词： Watermarking

来源：评论

学校读者我要写书评

暂无评论

Calibration bottleneck: over-compressed representations are less calibratable 24

Calibration bottleneck: over-compressed representations are ...

引用

Proceedings of the 41st International Conference on Machine Learning

作者： Deng-Bao Wang Min-Ling Zhang School of Computer Science and Engineering Southeast University Nanjing China and Key Lab. of Computer Network and Information Integration (Southeast University) MOE China

Although deep neural networks have achieved remarkable success, they often exhibit a significant deficiency in reliable uncertainty calibration. This paper focus on model calibratability, which assesses how amenable a model is to be well recalibrated post-hoc. We find that the widely used weight decay regularizer detrimentally affects model calibratability, subsequently leading to a decline in final calibration performance after post-hoc calibration. To identify the underlying causes leading to poor calibratability, we delve into the calibratability of intermediate features across the hidden layers. We observe a U-shaped trend in the calibratability of intermediate features from the bottom to the top layers, which indicates that over-compression of the top representation layers significantly hinders model calibratability. Based on the observations, this paper introduces a weak classifier hypothesis, i.e., given a weak classification head that has not been over-trained, the representation module can be better learned to produce more calibratable features. Consequently, we propose a progressively layer-peeled training (PLP) method to exploit this hypothesis, thereby enhancing model calibratability. Our comparative experiments show the effectiveness of our method, which improves model calibration and also yields competitive predictive performance.

关键词：

来源：评论

学校读者我要写书评

暂无评论

AdvAD: Exploring Non-Parametric Diffusion for Imperceptible Adversarial Attacks

arXiv

引用

arXiv 2025年

作者： Li, Jin He, Ziqiang Luo, Anwei Hu, Jian-Fang Wang, Z. Jane Kang, Xiangui Guangdong Key Lab of Information Security School of Computer Science and Engineering Sun Yat-Sen University China Electrical and Computer Engineering Dept University of British Columbia Canada

Imperceptible adversarial attacks aim to fool DNNs by adding imperceptible perturbation to the input data. Previous methods typically improve the imperceptibility of attacks by integrating common attack paradigms with specifically designed perception-based losses or the capabilities of generative models. In this paper, we propose Adversarial Attacks in Diffusion (AdvAD), a novel modeling framework distinct from existing attack paradigms. AdvAD innovatively conceptualizes attacking as a non-parametric diffusion process by theoretically exploring basic modeling approach rather than using the denoising or generation abilities of regular diffusion models requiring neural networks. At each step, much subtler yet effective adversarial guidance is crafted using only the attacked model without any additional network, which gradually leads the end of diffusion process from the original image to a desired imperceptible adversarial example. Grounded in a solid theoretical foundation of the proposed non-parametric diffusion process, AdvAD achieves high attack efficacy and imperceptibility with intrinsically lower overall perturbation strength. Additionally, an enhanced version AdvAD-X is proposed to evaluate the extreme of our novel framework under an ideal scenario. Extensive experiments demonstrate the effectiveness of the proposed AdvAD and AdvAD-X. Compared with state-of-the-art imperceptible attacks, AdvAD achieves an average of 99.9% (+17.3%) ASR with 1.34 (-0.97) l2 distance, 49.74 (+4.76) PSNR and 0.9971 (+0.0043) SSIM against four prevalent DNNs with three different architectures on the ImageNet-compatible dataset. Code is available at https://***/XianguiKang/AdvAD. Copyright © 2025, The Authors. All rights reserved.

关键词： HTTP

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：