检索结果-内蒙古大学图书馆

Joint 30th International Conference on computational Linguistics and 14th International Conference on Language Resources and Evaluation, LREC-COLING 2024

作者： Yang, Yuting Huang, Pei Ma, Feifei Cao, Juan Li, Jintao China University of Chinese Academy of Sciences China Department of Computer Science Stanford University United States State Key Laboratory of Computer Science Institute of Software CAS China Laboratory of Parallel Software and Computational Science Institute of Software CAS China

ISBN: (纸本)9782493814104

Deep neural networks can be vulnerable to adversarial attacks, even for the mainstream Transformer-based models. Although several robustness enhancement approaches have been proposed, they usually focus on some certain type of perturbation. As the types of attack can be various and unpredictable in practical scenarios, a general and strong defense method is urgently in require. We notice that most well-trained models can be weakly robust in the perturbation space, i.e., only a small ratio of adversarial examples exist. Inspired by the weak robust property, this paper presents a novel ensemble method for enhancing robustness. We propose a lightweight framework PAD to save computational resources in realizing an ensemble. Instead of training multiple models, a plugin module is designed to perturb the parameters of a base model which can achieve the effect of multiple models. Then, to diversify adversarial example distributions among different models, we promote each model to have different attention patterns via optimizing a diversity measure we defined. Experiments on various widely-used datasets and target models show that PAD can consistently improve the defense ability against many types of adversarial attacks while maintaining accuracy on clean data. Besides, PAD also presents good interpretability via visualizing diverse attention patterns. © 2024 ELRA Language Resource Association: CC BY-NC 4.0.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Differentiable Deformation Graph-Based Neural Non-rigid Registration

引用

Communications in Mathematics and Statistics 2023年第1期11卷 151-167页

作者： Wanquan Feng Hongrui Cai Junhui Hou Bailin Deng Juyong Zhang School of Mathematical Sciences University of Science and Technology of ChinaHefei 230026People’s Republic of China School of Data Science University of Science and Technology of ChinaHefei 230026People’s Republic of China Department of Computer Science City University of Hong KongHong KongPeople’s Republic of China School of Computer Science and Informatics Cardiff UniversityCardiffUK

The traditional pipeline for non-rigid registration is to iteratively update the correspondence and alignment such that the transformed source surface aligns well with the target *** the pipeline,the correspondence construction and iterative manner are key to the results,while existing strategies might result in local *** this paper,we adopt the widely used deformation graph-based representation,while replacing some key modules with neural learning-based ***,we design a neural network to predict the correspondence and its reliability confidence rather than the strategies like nearest neighbor search and pair ***,we adopt the GRU-based recurrent network for iterative refinement,which is more robust than the traditional *** model is trained in a self-supervised manner and thus can be used for arbitrary datasets without *** experiments demonstrate that our proposed method outperforms the state-of-the-art methods by a large margin.

关键词： Differentiable deformation graph Non-rigid registration

来源：评论

学校读者我要写书评

暂无评论

Constructing Multiple CISTs on BCube-Based data Center Networks in the Occurrence of Switch Failures

引用

IEEE Transactions on computers 2023年第7期72卷 1971-1984页

作者： Lin, Wanling Li, Xiao-Yan Chang, Jou-Ming Jia, Xiaohua Fuzhou University College of Computer and Data Science Fuzhou350108 China National Taipei University of Business Institute of Information and Decision Sciences Taipei10051 Taiwan City University of Hong Kong Department of Computer Science Hong Kong

The scale of data center networks (DCNs) has grown rapidly with the increasing popularity of cloud computing, data explosion, and the dramatic drop in setup costs. Thus, inevitable component failures (including switches and servers) will become more frequent. A DCN requires maintaining regular and reliable operation and providing efficient routing algorithms for transmitting data between servers. Particularly, fault-tolerant routing is necessary. Recently, constructing completely independent spanning trees (CISTs) on DCNs has received much attention as a dual-CIST (i.e., two CISTs) suffices to configure protection routing, which is a fault-tolerant routing. Moreover, the protection routing can additionally realize a secure mechanism if it is configured by more CISTs. BCube is a server-centric DCN with many advantages, and many variations were deformed from BCube with application requirements, such as RCube and RRect. In this paper, we provide a unified framework called BCube-based DCN (BDCN) that integrates the representation of the logic graphs of DCNs mentioned above, facilitating consistent algorithms' design. Then, we develop efficient algorithms to construct multiple CISTs on BDCN under the consideration of switch failures. Note that this is the first study that constructs multiple CISTs in DCNs with switch failures. Finally, using standard metrics, such as average path length (APL) and transmission failure rate (TFR), we evaluate the performance of the fault-tolerant routing through experiments. © 1968-2012 IEEE.

关键词： Fault tolerance

来源：评论

学校读者我要写书评

暂无评论

Automated AI-Powered Fruit Identification Using Convolutional Neural Network

Automated AI-Powered Fruit Identification Using Convolutiona...

引用

2025 International Conference on Multi-Agent Systems for Collaborative Intelligence, ICMSCI 2025

作者： Sai Tejasree, K. Surendran, R. Rajakumar, B. Gomathi, R.M. Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Computer Science and Engineering Chennai India J.N.N Institute of Engineering Department of Artificial Intelligence and Data Science Chennai India School of Computing Sathyabama Institute of Science and Technology Department of Computer Science and Engineering Chennai India

ISBN: (数字)9798331509828

ISBN: (纸本)9798331509828

Clever system that can look at pictures of fruits and figure out what kind of fruit each picture shows. AI algorithms like deep learning, which is like giving the Machine learning model a crash course in fruit recognition. This method teaches the ML Model we clearly explained the Model using application's agent using PEAS and the application's task environment using the 6 dimensions by showing it tons of fruit images, so over time, it gets really good at spotting the differences and similarities between, say, a banana and a grape. We also used another technique called pattern recognition, which helps the computer pay attention to specific details like the fruit's color, shape, size and texture. Overcoming multiple obstacles in order to automatically identify the type of fruit from the picture. The variety of images is influencing the color, texture, and shape of many different types of fruits. When it came to fruit picture detection, Convolutional Neural Network (CNN) Algorithm outperformed standard support-vector-machine-based approaches using handcrafted features in terms of accuracy also, it is a lot faster to implement for new fruits. By integrating deep learning and pattern recognition techniques such as Convolutional Neural Network Algorithm we have got the accuracy of 84%, our system efficiently identified different fruit types from images, demonstrating the power and effectiveness of our methods. The goal of our project is to create a tool that can quickly and correctly identify many types of fruits in photos, which could be useful for things like sorting fruits in a grocery store or helping people learn about different fruits by using Convolutional Neural Network Algorithm. This is not just about teaching a computer to recognize fruits;it is about making technology that can understand and interact with the world in a way that is helpful to us. © 2025 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Enhancing identity and access management using Hyperledger Fabric and OAuth 2.0: A block-chain-based approach for security and scalability for healthcare industry

引用

Internet of Things and Cyber-Physical Systems 2024年第1期4卷 49-67页

作者： Sutradhar, Shrabani Karforma, Sunil Bose, Rajesh Roy, Sandip Djebali, Sonia Bhattacharyya, Debnath Department of Computational Sciences Brainware University West Bengal India Department of Computer Sciences The University of Burdwan West Bengal India Department of Computer Science & Engineering JIS University West Bengal India Pôle universitaire Léonard De Vinci Research Center Paris La Défense 92 916 France Koneru Lakshmaiah Education Foundation Vaddeswaram Andhra Pradesh522302 India

Block-chain-based Identity and access management framework is a promising solution to privacy and security issues raised during the exchange of patient data in the healthcare industry. This technology ensures the confidentiality and integrity of sensitive information by providing a decentralized and immutable ledger. In our research, we propose an identity and access management system that employs Hyper-ledger Fabric and OAuth 2.0 for improved security and scalability. This combination allows for transparency and immutability of user transactions and minimizes the risk of fraud and unauthorized access. Additionally, Hyper-ledger Fabric's privacy, security, and scalability features enable granular access control to sensitive information, while OAuth 2.0 authorizes only trusted third-party applications to access specific data on the Fabric network. The proposed approach can handle large volumes of data and support multiple applications, thus providing a secure and scalable solution for managing access to the Fabric network. Moreover, our solution employs Role-based access control based on the patient's role, ensuring privacy and confidentiality. Our statistical analysis demonstrates that the proposed approach can efficiently and securely manage patient identity and access, potentially transforming the healthcare industry by enhancing data interoperability, reducing fraud and errors, and improving patient privacy and security. Furthermore, our solution can facilitate compliance with regulatory requirements such as HIPAA and GDPR. © 2023 The Authors

关键词： Scalability

来源：评论

学校读者我要写书评

暂无评论

Overview of Mobile Attack Detection and Prevention Techniques Using Machine Learning

International Journal of Interactive Mobile Technologies

引用

International Journal of Interactive Mobile Technologies 2024年第10期18卷 125-157页

作者： Al Hwaitat, Ahmad K. Fakhouri, Hussam N. Alawida, Moatsum Atoum, Mohammed S. Abu-Salih, Bilal Salah, Imad K. M. Al-Sharaeh, Saleh Alassaf, Nabil King Abdullah II School of Information Technology The University of Jordan Amman1142 Jordan Department of Data Science and Artificial Intelligence University of Petra Amman Jordan Department of Computer Sciences Abu Dhabi University Abu Dhabi59911 United Arab Emirates

In light of the increasing sophistication and frequency of mobile attacks, there is a growing demand for advanced intelligent techniques capable of offering comprehensive mobile attack detection and prevention. This paper aims to critically evaluate the landscape of mobile security, outlining the evolution of mobile attack vectors and pinpointing the deficiencies in traditional security methods. The text embarks on a journey to understand the connection between machine learning (ML) and its promising applications in enhancing mobile security. First, we outline the current state of mobile attacks and the traditional methods used for their detection, emphasizing the clear limitations and the necessity for an innovative approach. Following this, we will elucidate the fundamentals of ML and its implications in cybersecurity, exploring the benefits it can provide to mobile attack detection frameworks. We delve into discussing various ML algorithms, such as decision trees, random forests, and support vector machines, highlighting their effectiveness and the metrics used to evaluate ML models in security tasks. Moreover, the paper sheds light on novel approaches such as semi-supervised and unsupervised learning in anomaly detection, as well as the applications of transfer learning in security. Addressing the pressing challenges faced in artificial intelligence (AI)-driven mobile attack detection, we delve deep into the intricacies of data collection, labeling, and the prevailing issues of imbalance and overfitting. Furthermore, we explore contemporary adversarial attacks and defenses, scrutinizing the real-world adaptability of AI models and the pivotal role of human-AI collaboration in enhancing attack detection mechanisms. © 2024 by the authors of this article.

关键词： Cybersecurity

来源：评论

学校读者我要写书评

暂无评论

UNCERTAINTY-AWARE GRAPH-BASED HYPERSPECTRAL IMAGE CLASSIFICATION 12

UNCERTAINTY-AWARE GRAPH-BASED HYPERSPECTRAL IMAGE CLASSIFICA...

引用

12th International Conference on Learning Representations, ICLR 2024

作者： Yu, Linlin Lou, Yifei Chen, Feng Department of Computer Science University of Texas Dallas United States Department of Mathematics School of Data Sciences and Society University of North Carolina Chapel Hill United States

Hyperspectral imaging (HSI) technology captures spectral information across a broad wavelength range, providing richer pixel features compared to traditional color images with only three channels. Although pixel classification in HSI has been extensively studied, especially using graph convolution neural networks (GCNs), quantifying epistemic and aleatoric uncertainties associated with the HSI classification (HSIC) results remains an unexplored area. These two uncertainties are effective for out-of-distribution (OOD) and misclassification detection, respectively. In this paper, we adapt two advanced uncertainty quantification models, evidential GCNs (EGCN) and graph posterior networks (GPN), designed for node classifications in graphs, into the realm of HSIC. We first reveal theoretically that a popular uncertainty cross-entropy (UCE) loss function is insufficient to produce good epistemic uncertainty when learning EGCNs. To mitigate the limitations, we propose two regularization terms. One leverages the inherent property of HSI data where each feature vector is a linear combination of the spectra signatures of the confounding materials, while the other is the total variation (TV) regularization to enforce the spatial smoothness of the evidence with edge-preserving. We demonstrate the effectiveness of the proposed regularization terms on both EGCN and GPN on three real-world HSIC datasets for OOD and misclassification detection tasks. The code is available at GitHub. © 2024 12th International Conference on Learning Representations, ICLR 2024. All rights reserved.

关键词： Hyperspectral imaging

来源：评论

学校读者我要写书评

暂无评论

Brain-inspired artificial intelligence research: A review

引用

science China(Technological sciences) 2024年第8期67卷 2282-2296页

作者： WANG GuoYin BAO HuaNan LIU Qun ZHOU TianGang WU Si HUANG TieJun YU ZhaoFei LU CeWu GONG YiHong ZHANG ZhaoXiang HE Sheng Chongqing Key Laboratory of Computational Intelligence Chongqing University of Posts and TelecommunicationsChongqing 400065China Key Laboratory of Cyberspace Big Data Intelligent Security Chongqing University of Posts and TelecommunicationsChongqing 400065China College of Computer and Information Science Chongqing Normal UniversityChongqing 401331China State Key Laboratory of Brain and Cognitive Science Institute of BiophysicsChinese Academy of SciencesBeijing 100101China School of Psychological and Cognitive Sciences Peking UniversityBeijing 100871China State Key Laboratory of Multimedia Information Processing School of Computer SciencePeking UniversityBeijing 100871China Department of Computer Science School of ElectronicsInformation and Electrical EngineeringShanghai Jiao Tong UniversityShanghai 200240China Faculty of Electronic and Information Engineering Xi’an Jiaotong UniversityXi’an 710049China The Center for Research on Intelligent Perception and Computing Institute of AutomationChinese Academy of SciencesBeijing 100190China Institute of Biophysics Chinese Academy of SciencesBeijing 100101China

Artificial intelligence(AI) systems surpass certain human intelligence abilities in a statistical sense as a whole, but are not yet the true realization of these human intelligence abilities and behaviors. There are differences, and even contradictions, between the cognition and behavior of AI systems and humans. With the goal of achieving general AI, this study contains a review of the role of cognitive science in inspiring the development of the three mainstream academic branches of AI based on the three-layer framework proposed by David Marr, and the limitations of the current development of AI are explored and analyzed. The differences and inconsistencies between the cognition mechanisms of the human brain and the computation mechanisms of AI systems are analyzed. They are found to be the cause of the differences and contradictions between the cognition and behavior of AI systems and humans. Additionally, eight important research directions and their scientific issues that need to focus on braininspired AI research are proposed: highly imitated bionic information processing, a large-scale deep learning model that balances structure and function, multi-granularity joint problem solving bidirectionally driven by data and knowledge, AI models that simulate specific brain structures, a collaborative processing mechanism with the physical separation of perceptual processing and interpretive analysis, embodied intelligence that integrates the brain cognitive mechanism and AI computation mechanisms,intelligence simulation from individual intelligence to group intelligence(social intelligence), and AI-assisted brain cognitive intelligence.

关键词： artificial intelligence cognitive science brain science intelligence science large language model

来源：评论

学校读者我要写书评

暂无评论

A Unified Characterization of Private Learnability via Graph Theory 37

A Unified Characterization of Private Learnability via Graph...

引用

37th Annual Conference on Learning Theory, COLT 2024

作者： Alon, Noga Moran, Shay Schefler, Hilla Yehudayoff, Amir Department of Mathematics Princeton University United States Departments of Mathematics Computer Science and Data and Decision Sciences Technion Google Research Israel Department of Mathematics Technion Israel

We provide a unified framework for characterizing pure and approximate differentially private (DP) learnability. The framework uses the language of graph theory: for a concept class H, we define the contradiction graph G of H. Its vertices are realizable datasets and two datasets S, S′ are connected by an edge if they contradict each other (i.e., there is a point x that is labeled differently in S and S′). Our main finding is that the combinatorial structure of G is deeply related to learning H under DP. Learning H under pure DP is captured by the fractional clique number of G. Learning H under approximate DP is captured by the clique number of G. Consequently, we identify graph-theoretic dimensions that characterize DP learnability: the clique dimension and fractional clique dimension. Along the way, we reveal properties of the contradiction graph which may be of independent interest. We also suggest several open questions and directions for future research. © 2024 N. Alon, S. Moran, H. Schefler & A. Yehudayoff.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

Hybrid Deep Learning Models with Genetic Algorithm Optimization for Enhanced Kidney Tumor Detection 5

Hybrid Deep Learning Models with Genetic Algorithm Optimizat...

引用

5th International Conference on Electronics and Sustainable Communication Systems, ICESC 2024

作者： Rajagopal, K. Kumari, V. Sheeja Saraswathy, S. Kumar, V. Suresh Ponmaniraj, S. Deepa, A. Saveetha Institute of Medical and Technical Sciences Simats University Computer Science and Engineering Chennai Thandalam India Saveetha Institute of Medical and Technical Sciences Simats University Department of Computer Science and Engineering Chennai Thandalam India Sri Sairam Engineering College Department of Computer Science and Business Systems Chennai India Institute of Ece Saveetha Institute of Medical and Technical Sciences Simats University Department of Computational Intelligence Chennai Thandalam India Saveetha Engineering College Department of Computer Science and Engineering Chennai Thandalam India

ISBN: (纸本)9798350379945

Accurate and timely segmentation of kidney tumors from medical images is crucial for effective treatment and prognosis. This research study proposes a novel hybrid deep learning framework incorporating Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) for enhanced kidney tumor segmentation. To optimize model performance, Genetic Algorithms (GA) are employed to fine-tune hyperparameters and network architecture. The proposed method effectively captures both local and global image features, leading to improved segmentation accuracy compared to existing techniques. Experimental results on a publicly available dataset demonstrate the superiority of our approach in terms of recall, F1-score, and precision. This research contributes to the advancement of computer-aided diagnosis for kidney cancer. © 2024 IEEE.

关键词： Convolutional neural networks

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：