检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Yan, Yuanjie Zhao, Jian Shen, Furao State Key Laboratory for Novel Software Technology Nanjing University China Department of Computer Science and Technology Nanjing University China School of Electronic Science and Engineering Nanjing University Nanjing China School of Artificial Intelligence Nanjing University Nanjing China

Image manipulation on the latent space of the pre-trained StyleGAN can control the semantic attributes of the generated images. Recently, some studies have focused on detecting channels with specific properties to directly manipulate the latent code, which is limited by the entanglement of the latent space. To detect the attribute-specific channels, we propose a novel detection method in the context of pre-trained classifiers. We analyse the gradients layer by layer on the style space. The intensities of the gradients indicate the channel’s responses to specific attributes. The latent style codes of channels control separate attributes in the layers. We choose channels with the top-k gradients to control specific attributes in the maximum response layer. We implement single-channel and multi-channel manipulations with a certain attribute. Our methods can accurately detect relevant channels for a large number of face attributes. Extensive qualitative and quantitative results demonstrate that the proposed methods outperform state-of-the-art methods in generalization and scalability. © 2023, CC BY.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

DLUE: Benchmarking Document Language Understanding

arXiv

引用

arXiv 2023年

作者： Xu, Ruoxi Lin, Hongyu Guan, Xinyan Han, Xianpei Sun, Yingfei Sun, Le Chinese Information Processing Laboratory Institute of Software Chinese Academy of Sciences Beijing China State Key Laboratory of Computer Science Institute of Software Chinese Academy of Sciences Beijing China School of Electronic Electrical and Communication Engineering University of Chinese Academy of Sciences Beijing China

Understanding documents is central to many real-world tasks but remains a challenging topic. Unfortunately, there is no well-established consensus on how to comprehensively evaluate document understanding abilities, which significantly hinders the fair comparison and measuring the progress of the field. To benchmark document understanding researches, this paper summarizes four representative abilities, i.e., document classification, document structural analysis, document information extraction, and document transcription. Under the new evaluation framework, we propose Document Language Understanding Evaluation – DLUE, a new task suite which covers a wide-range of tasks in various forms, domains and document genres. We also systematically evaluate six well-established transformer models on DLUE, and find that due to the lengthy content, complicated underlying structure and dispersed knowledge, document understanding is still far from being solved, and currently there is no neural architecture that dominates all tasks, raising requirements for a universal document understanding architecture. © 2023, CC BY.

关键词： Information retrieval systems

来源：评论

学校读者我要写书评

暂无评论

Breaking Barriers in Physical-World Adversarial Examples: Improving Robustness and Transferability via Robust Feature 39

Breaking Barriers in Physical-World Adversarial Examples: Im...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Wang, Yichen Chou, Yuxuan Zhou, Ziqi Zhang, Hangtao Wan, Wei Hu, Shengshan Li, Minghui National Engineering Research Center for Big Data Technology and System China Services Computing Technology and System Lab China Cluster and Grid Computing Lab China Hubei Engineering Research Center on Big Data Security China Hubei Key Laboratory of Distributed System Security China School of Cyber Science and Engineering Huazhong University of Science and Technology China School of Computer Science and Technology Huazhong University of Science and Technology China School of Software Engineering Huazhong University of Science and Technology China

ISBN: (纸本)157735897X

As deep neural networks (DNNs) are widely applied in the physical world, many researches are focusing on physical-world adversarial examples (PAEs), which introduce perturbations to inputs and cause the model's incorrect outputs. However, existing PAEs face two challenges: unsatisfactory attack performance (i.e., poor transferability and insufficient robustness to environment conditions), and difficulty in balancing attack effectiveness with stealthiness, where better attack effectiveness often makes PAEs more perceptible. In this paper, we explore a novel perturbation-based method to overcome the challenges. For the first challenge, we introduce a strategy Deceptive RF injection based on robust features (RFs) that are predictive, robust to perturbations, and consistent across different models. Specifically, it improves the transferability and robustness of PAEs by covering RFs of other classes onto the predictive features in clean images. For the second challenge, we introduce another strategy Adversarial Semantic Pattern Minimization, which removes most perturbations and retains only essential adversarial patterns in AEs. Based on the two strategies, we design our method Robust Feature Coverage Attack (RFCoA), comprising Robust Feature Disentanglement and Adversarial Feature Fusion. In the first stage, we extract target class RFs in feature space. In the second stage, we use attention-based feature fusion to overlay these RFs onto predictive features of clean images and remove unnecessary perturbations. Experiments show our method's superior transferability, robustness, and stealthiness compared to existing state-of-the-art methods. Additionally, our method's effectiveness can extend to Large Vision-Language Models (LVLMs), indicating its potential applicability to more complex tasks. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Flat U-Net: An Efficient Ultralightweight Model for Solar Filament Segmentation in Full-disk Hα Images

arXiv

引用

arXiv 2025年

作者： Zhu, GaoFei Lin, GangHua Yang, Xiao Zeng, Cheng School of Computer and Software Engineering Xihua University Chengdu610039 China National Astronomical Observatories Chinese Academy of Sciences Beijing100101 China State Key Laboratory of Solar Activity and Space Weather National Space Science Center Chinese Academy of Sciences Beijing100190 China

Solar filaments are one of the most prominent features observed on the Sun, and their evolutions are closely related to various solar activities, such as flares and coronal mass ejections. Real-time automated identification of solar filaments is the most effective approach to managing large volumes of data. Existing models of filament identification are characterized by large parameter sizes and high computational costs, which limit their future applications in highly integrated and intelligent ground-based and space-borne observation devices. Consequently, the design of more lightweight models will facilitate the advancement of intelligent observation equipment. In this study, we introduce Flat U-Net, a novel and highly efficient ultralightweight model that incorporates simplified channel attention (SCA) and channel self-attention (CSA) convolutional blocks for the segmentation of solar filaments in full-disk Hα images. Feature information from each network layer is fully extracted to reconstruct interchannel feature representations. Each block effectively optimizes the channel features from the previous layer, significantly reducing parameters. The network architecture presents an elegant flattening, improving its efficiency, and simplifying the overall design. Experimental validation demonstrates that a model composed of pure SCAs achieves a precision of approximately 0.93, with dice similarity coefficient (DSC) and recall rates of 0.76 and 0.64, respectively, significantly outperforming the classical U-Net. Introducing a certain number of CSA blocks improves the DSC and recall rates to 0.82 and 0.74, respectively, which demonstrates a pronounced advantage, particularly concerning model weight size and detection effectiveness. The data set, models, and code are available as open-source resources. Copyright © 2025, The Authors. All rights reserved.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Accelerating MUS enumeration by inconsistency graph partitioning

引用

Science China(Information Sciences) 2019年第11期62卷 70-80页

作者： Jie LUO Shaofan LIU State Key Laboratory of Software Development Environment School of Computer Science and EngineeringBeihang University

The problem of finding minimal unsatisfiable subsets(MUSes) has been studied frequently because of its theoretical importance and wide range of applications in domains such as electronic design automation, software, and integrated circuit verification. In this paper, a method for accelerating the enumeration of MUSes based on inconsistency graph partitioning is proposed. First, an inconsistency graph of a set of clauses is constructed by extracting the inconsistency relations between literals of different clauses. In this paper, we show that by partitioning the inconsistency graph into small connected components through a vertex cut, the enumeration of MUSes in different components becomes independent and it is possible to compute them separately. Moreover, the MUSes of the original clause set can be constructed by merging the unit clauses in the MUSes of these connected components back into the clauses in the vertex cut. Experiments show that by integrating the acceleration method into the MARCO MUSes enumerator, there is a 2–3 times improvement in the average runtime of solved instances for randomly generated benchmarks. By integrating the acceleration method into itself as an MUS enumerator, there is another 3–4 times improvement when compared with the accelerated MARCO.

关键词： minimal unsatisfiable subsets inconsistency graph graph partition SAT UNSAT

来源：评论

学校读者我要写书评

暂无评论

Detecting Backdoors During the Inference Stage Based on Corruption Robustness Consistency

Detecting Backdoors During the Inference Stage Based on Corr...

引用

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Xiaogeng Liu Minghui Li Haoyu Wang Shengshan Hu Dengpan Ye Hai Jin Libing Wu Chaowei Xiao School of Cyber Science and Engineering Huazhong University of Science and Technology 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 School of Software Engineering Huazhong University of Science and Technology School of Cyber Science and Engineering Wuhan University School of Computer Science and Technology Huazhong University of Science and Technology Cluster and Grid Computing Lab Arizona State University

Deep neural networks are proven to be vulnerable to backdoor attacks. Detecting the trigger samples during the inference stage, i.e., the test-time trigger sample detection, can prevent the backdoor from being triggered. However, existing detection methods often require the defenders to have high accessibility to victim models, extra clean data, or knowledge about the appearance of backdoor triggers, limiting their practicality. In this paper, we propose the test-time corruption robustness consistency evaluation (TeCo) 1 1 https://***/CGCL-codes/TeCo, a novel test-time trigger sample detection method that only needs the hard-label outputs of the victim models without any extra information. Our journey begins with the intriguing observation that the backdoor-infected models have similar performance across different image corruptions for the clean images, but perform discrepantly for the trigger samples. Based on this phenomenon, we design TeCo to evaluate test-time robustness consistency by calculating the deviation of severity that leads to predictions' transition across different corruptions. Extensive experiments demonstrate that compared with state-of-the-art defenses, which even require either certain information about the trigger types or accessibility of clean data, TeCo outperforms them on different backdoor attacks, datasets, and model architectures, enjoying a higher AUROC by 10% and 5 times of stability.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Breaking Barriers in Physical-World Adversarial Examples: Improving Robustness and Transferability via Robust Feature

arXiv

引用

arXiv 2024年

作者： Wang, Yichen Chou, Yuxuan Zhou, Ziqi Zhang, Hangtao Wan, Wei Hu, Shengshan Li, Minghui National Engineering Research Center for Big Data Technology and System China Services Computing Technology and System Lab China Cluster and Grid Computing Lab China Hubei Engineering Research Center on Big Data Security China Hubei Key Laboratory of Distributed System Security China School of Cyber Science and Engineering Huazhong University of Science and Technology China School of Computer Science and Technology Huazhong University of Science and Technology China School of School of Software Engineering Huazhong University of Science and Technology China

As deep neural networks (DNNs) are widely applied in the physical world, many researches are focusing on physical-world adversarial examples (PAEs), which introduce perturbations to inputs and cause the model’s incorrect outputs. However, existing PAEs face two challenges: unsatisfactory attack performance (i.e., poor transferability and insufficient robustness to environment conditions), and difficulty in balancing attack effectiveness with stealthiness, where better attack effectiveness often makes PAEs more perceptible. In this paper, we explore a novel perturbation-based method to overcome the challenges. For the first challenge, we introduce a strategy Deceptive RF injection based on robust features (RFs) that are predictive, robust to perturbations, and consistent across different models. Specifically, it improves the transferability and robustness of PAEs by covering RFs of other classes onto the predictive features in clean images. For the second challenge, we introduce another strategy Adversarial Semantic Pattern Minimization, which removes most perturbations and retains only essential adversarial patterns in AEs. Based on the two strategies, we design our method Robust Feature Coverage Attack (RFCoA), comprising Robust Feature Disentanglement and Adversarial Feature Fusion. In the first stage, we extract target class RFs in feature space. In the second stage, we use attention-based feature fusion to overlay these RFs onto predictive features of clean images and remove unnecessary perturbations. Experiments show our method’s superior transferability, robustness, and stealthiness compared to existing state-of-the-art methods. Additionally, our method’s effectiveness can extend to Large Vision-Language Models (LVLMs), indicating its potential applicability to more complex tasks. Copyright © 2024, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Learning Fair and Efficient Multiple Access Schemes with Decomposed MADDPG

Learning Fair and Efficient Multiple Access Schemes with Dec...

引用

Future Communications and Networks (FCN), International Conference on

作者： Zhaoyang Liu Haoxin Lin Xijun Wang Jie Gong Xiang Chen School of Electronics and Information Technology Sun Yat-sen University Guangzhou China Guangxi Key Laboratory of Wireless Wideband Communication and Signal Processing Guilin China State Key Lab of Novel Software Technology Nanjing University Nanjing China Guangdong Key Laboratory of Information Security Technology School of Computer Science and Engineering Sun Yat-sen University Guangzhou China

ISBN: (数字)9798350396034

ISBN: (纸本)9798350396041

With the growing demand for wireless communication networks, achieving efficient and equitable channel access schemes has become paramount. In this paper, we delve into the realm of distributed channel access in homogeneous wireless networks, focusing on both fairness and efficiency. We introduce a media access control protocol, named Fair and Efficient Multiple Access (FEMA), by leveraging decomposed Multi-Agent Deep Deterministic Policy Gradient (MADDPG). FEMA decouples the dual objectives into self-oriented efficiency reward and team-oriented fairness reward. Correspondingly, local critic networks and global critic networks target self-oriented reward and team-oriented reward, respectively. Extensive simulations demonstrate FEMA’s superiority over conventional MAC protocols and other multiple access techniques based on deep reinforcement learning, showcasing its ability to simultaneously enhance fairness and efficiency.

关键词： Protocols Wireless networks Focusing Media Access Protocol Dynamic scheduling Deep reinforcement learning Resource management

来源：评论

学校读者我要写书评

暂无评论

基于边缘计算的软件定义云制造和柔性资源调度研究

引用

engineering 2023年第3期22卷 60-70页

作者：杨晨廖方茵兰舒琳王力翚沈卫明黄国全 School of Cyberspace Science and Technology Beijing Institute of TechnologyBeijing 100081China School of Computer Science and Technology Beijing Institute of TechnologyBeijing 100081China School of Mathematics and Computer Science Yan'an UniversityYan'an 716000China School of Economics and Management University of Chinese Academy of SciencesBeijing 100190China Department of Production Engineering KTH Royal Institute of TechnologyStockholm 10044Sweden State Key Lab of Digital Manufacturing Equipment and Technology Huazhong University of Science and TechnologyWuhan 430074China Department of Industrial and Manufacturing Systems Engineering The University of Hong KongHong Kong 999077China

本研究的重点是在云制造环境中实现快速重构、实现灵活的资源调度、开发资源潜力以应对各种变化。因此,本文首先提出了一种新的基于云和软件定义网络(SDN)的制造模型——软件定义云制造(SDCM),该模型将控制逻辑从自动化硬件转移到软件... 详细信息

本研究的重点是在云制造环境中实现快速重构、实现灵活的资源调度、开发资源潜力以应对各种变化。因此,本文首先提出了一种新的基于云和软件定义网络(SDN)的制造模型——软件定义云制造(SDCM),该模型将控制逻辑从自动化硬件转移到软件上。这种转变意义重大,因为软件可以充当制造系统的“大脑”,并且可以轻松更改或更新以支持快速系统重新配置、运营和演进。随后,边缘计算被引入,以接近终端的计算和存储能力来补充云。另一个关键问题是管理由不同服务质量(QoS)要求的大量物联网(IoT)数据传输而导致的严重网络拥塞。基于SDCM的虚拟化和灵活的网络能力,本研究形式化了面向复杂制造任务集的时间敏感性数据流量控制问题,并考虑了子任务分配和数据路由路径选择。为了解决这一优化问题,提出了一种将遗传算法(GA)、Dijkstra最短路径算法和排队算法相结合的方法。实验结果表明,该方法能有效地防止网络拥塞,减少SDCM中的总通信延迟。

关键词： Cloud manufacturing Edge computing software-defined networks Industrial Internet of Things Industry 4.0

来源：评论

学校读者我要写书评

暂无评论

Research on key Word Information Retrieval Based on Inverted Index 8th

Research on Key Word Information Retrieval Based on Inverted...

引用

8th International Conference on Artificial Intelligence and Security , ICAIS 2022

作者： Qi, Meihan Fang, Wei Zhao, Yongming Sha, Yu Sheng, Victor S. School of Computer and Software Engineering Research Center of Digital Forensics Ministry of Education Nanjing University of Information Science and Technology Nanjing210044 China State Key Laboratory of Severe Weather Chinese Academy of Meteorological Sciences Beijing100081 China China Meteorological Administration Training Center Beijing China Department of Computer Texas Tech University LubbockTX79409 United States

ISBN: (纸本)9783031067600

With the advent of the era of big data, data has penetrated into every aspect of social life and become an important production factor in various industries. However, while providing convenience to our life, massive information also brings difficulties to information retrieval, which has problems of low retrieval efficiency and poor retrieval accuracy. Therefore, how to improve the efficiency and accuracy of information retrieval has become a key technical problem to be solved. In this paper, we propose a key word information retrieval scheme based on inverted index, which uses the inverted index segmentation algorithm based on keywords to realize the block retrieval of information, improves the efficiency of information retrieval, and improves the accuracy of retrieval content through reasonable error correction of keywords. The results of evaluation indicate that compared with the mainstream information retrieval methods, the keyword information retrieval scheme based on inverted index can carry out faster and more accurate information retrieval. Experimental results show that the keyword information retrieval scheme with inverted index can further improve the efficiency and accuracy of information retrieval. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Information retrieval

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：