检索结果-内蒙古大学图书馆

您好，读者！请登录

内蒙古大学图书馆

首页
概况
党建
资源
服务
科研支持
- 论文收录引用证明
- 科技查新
知识产权
档案馆
帮助

咨询与建议

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

您的常用邮箱：*

您的手机号码：*

问题描述：

当前已输入0个字，您还可以输入200个字

全部搜索
期刊论文
图书
学位论文
标准
纸本馆藏
外文资源发现
数据库导航
超星发现

高级检索

时间限定

出版年份：

文献类型

图书期刊文献学位论文多媒体

馆藏选择

电子馆藏纸本馆藏

核心期刊

全部期刊 SCI 收录期刊 SSCI 收录期刊 EI 收录期刊 CSCD 收录期刊 CSSCI 收录期刊

语言

中文英文

文献类型

期刊文献图书学位论文标准纸本馆藏

帮助

文字说明：

T=题名（书名、题名），A=作者（责任者），K=主题词，P=出版物名称，PU=出版社名称，O=机构（作者单位、学位授予单位、专利申请人），L=中图分类号，C=学科分类号，U=全部字段，Y=年（出版发行年、学位年度、标准发布年）

检索规则说明：

AND代表“并且”；OR代表“或者”；NOT代表“不包含”；(注意必须大写,运算符两边需空一格)

检索范例：

范例一：(K=图书馆学 OR K=情报学) AND A=范并思 AND Y=1982-2016
范例二：P=计算机应用与软件 AND (U=C++ OR U=Basic) NOT K=Visual AND Y=2011-2016

分类表

所选分类

>> <<

限定检索结果

文献类型

575 篇 会议
15 册 图书
4 篇 期刊文献

馆藏范围

594 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

480 篇 工学
- 454 篇 计算机科学与技术...
- 127 篇 软件工程
- 85 篇 电气工程
- 45 篇 信息与通信工程
- 30 篇 控制科学与工程
- 15 篇 机械工程
- 15 篇 生物工程
- 10 篇 光学工程
- 7 篇 化学工程与技术
- 7 篇 航空宇航科学与技...
- 7 篇 生物医学工程（可授...
- 6 篇 建筑学
- 5 篇 土木工程
- 5 篇 安全科学与工程
- 4 篇 材料科学与工程（可...
153 篇 理学
- 113 篇 物理学
- 23 篇 数学
- 15 篇 生物学
- 11 篇 统计学（可授理学、...
- 5 篇 系统科学
- 4 篇 化学
40 篇 管理学
- 21 篇 管理科学与工程(可...
- 20 篇 图书情报与档案管...
- 6 篇 工商管理
15 篇 医学
- 9 篇 基础医学(可授医学...
- 9 篇 临床医学
14 篇 教育学
- 14 篇 教育学
13 篇 法学
- 7 篇 社会学
- 6 篇 法学
4 篇 经济学
- 4 篇 应用经济学
4 篇 农学
4 篇 军事学

主题

144 篇 machine learning
105 篇 artificial intel...
65 篇 deep learning
28 篇 adversarial mach...
24 篇 reinforcement le...
16 篇 object detection
15 篇 learning systems
14 篇 neural networks
14 篇 federated learni...
13 篇 computer vision
12 篇 cybersecurity
12 篇 security
12 篇 accuracy
12 篇 machine learning...
12 篇 training
11 篇 computer applica...
10 篇 multi-domain ope...
9 篇 ai
9 篇 explainable arti...
9 篇 unsupervised lea...

机构

6 篇 marwadi universi...
6 篇 national univers...
5 篇 us army engineer...
5 篇 us army res lab ...
4 篇 college of compu...
4 篇 siemens corporat...
4 篇 univ maryland co...
4 篇 carnegie mellon ...
4 篇 foundation for r...
3 篇 mcmaster univ 12...
3 篇 korea univ dept ...
3 篇 us mil acad army...
3 篇 ibm tj watson re...
2 篇 johns hopkins un...
2 篇 penn state univ ...
2 篇 the high school ...
2 篇 howard univ wash...
2 篇 wroclaw universi...
2 篇 univ southern ca...
2 篇 shanghai ai lab ...

作者

8 篇 rawat danda b.
6 篇 divyakant meva
6 篇 kalpesh popat
6 篇 sunil bajeja
6 篇 pankaj mudholkar
6 篇 sridaran rajagop...
4 篇 surucu onur
4 篇 giuliano alessan...
4 篇 alsadi naseem
4 篇 helmut degen
4 篇 hilal waleed
4 篇 stavroula ntoa
4 篇 raglin adrienne
4 篇 asher derrik e.
4 篇 yawney john
4 篇 markowitz jared
3 篇 bastian nathanie...
3 篇 schutte klamer
3 篇 kwak heon-gyu
3 篇 price stanton r.

语言

564 篇 英文
30 篇 其他
2 篇 中文

检索条件"任意字段=Conference on Artificial Intelligence and Machine Learning in Defense Applications IV"

共 594 条记录，以下是11-20 订阅

全选清除本页清除全部题录导出标记到"检索档案"

详细简洁

排序：

A Simple and Yet Fairly Effective defense for Graph Neural Networks 38

A Simple and Yet Fairly Effective Defense for Graph Neural N...

引用

38th AAAI conference on artificial intelligence (AAAI) / 36th conference on Innovative applications of artificial intelligence / 14th Symposium on Educational Advances in artificial intelligence

作者： Ennadir, Sofiane Abbahaddou, Yassine Lutzeyer, Johannes F. Vazirgiannis, Michalis Bostrom, Henrik KTH Royal Inst Technol EECS Stockholm Sweden Inst Polytech Paris Ecole Polytech LIX DaSciM Paris France

ISBN: (纸本)1577358872

Graph Neural Networks (GNNs) have emerged as the dominant approach for machine learning on graph-structured data. However, concerns have arisen regarding the vulnerability of GNNs to small adversarial perturbations. Existing defense methods against such perturbations suffer from high time complexity and can negatively impact the model's performance on clean graphs. To address these challenges, this paper introduces NoisyGNNs, a novel defense method that incorporates noise into the underlying model's architecture. We establish a theoretical connection between noise injection and the enhancement of GNN robustness, highlighting the effectiveness of our approach. We further conduct extensive empirical evaluations on the node classification task to validate our theoretical findings, focusing on two popular GNNs: the GCN and GIN. The results demonstrate that NoisyGNN achieves superior or comparable defense performance to existing methods while minimizing added time complexity. The NoisyGNN approach is model-agnostic, allowing it to be integrated with different GNN architectures. Successful combinations of our NoisyGNN approach with existing defense techniques demonstrate even further improved adversarial defense results. Our code is publicly available at: https://***/Sennadir/NoisyGNN.

关键词： Network architecture

来源：评论

学校读者我要写书评

暂无评论

VQUNet: Vector Quantization U-Net for Defending Adversarial Attacks by Regularizing Unwanted Noise 7

VQUNet: Vector Quantization U-Net for Defending Adversarial ...

引用

7th International conference on machine Vision and applications (ICMVA)

作者： He, Zhixun Singhal, Mukesh Univ Calif Merced Merced CA 95343 USA

ISBN: (纸本)9798400716553

Deep Neural Networks (DNN) have become a promising paradigm when developing artificial intelligence (AI) and machine learning (ML) applications. However, DNN applications are vulnerable to fake data that are crafted with adversarial attack algorithms. Under adversarial attacks, the prediction accuracy of DNN applications suffers, making them unreliable. In order to defend against adversarial attacks, we introduce a novel noise-reduction procedure, Vector Quantization U-Net (VQUNet), to reduce adversarial noise and reconstruct data with high fidelity. VQUNet features a discrete latent representation learning through a multi-scale hierarchical structure for both noise reduction and data reconstruction. The empirical experiments show that the proposed VQUNet provides better robustness to the target DNN models, and it outperforms other state-of-the-art noise-reduction-based defense methods under various adversarial attacks for both Fashion-MNIST and CIFAR10 datasets. When there is no adversarial attack, the defense method has less than 1% accuracy degradation for both datasets.

关键词： Adversarial defense Noise Reduction Vector Quantization U-Net

来源：评论

学校读者我要写书评

暂无评论

Fast and Adversarial Robust Kernelized SDU learning 27

Fast and Adversarial Robust Kernelized SDU Learning

引用

27th International conference on artificial intelligence and Statistics (AISTATS)

作者： Fan, Yajing Shi, Wanli Chang, Yi Gu, Bin Nanjing Univ Informat Sci & Technol Nanjing Peoples R China MBZUAI Abu Dhabi U Arab Emirates Jilin Univ Sch Artificial Intelligence Jilin Jilin Peoples R China

SDU learning, a weakly supervised learning problem with only pairwise similarities, dissimilarities data points and unlabeled data available, has many practical applications. However, it is still lacking in defense against adversarial samples, and its learning process can be expensive. To address this gap, we propose a novel adversarial training framework for SDU learning. Our approach reformulates the conventional minimax problem as an equivalent minimization problem based on the kernel perspective, departing from traditional confrontational training methods. Additionally, we employ the random gradient method and random features to accelerate the training process. Theoretical analysis shows that our method can converge to a stationary point at a rate of O(1/T-1/4). Our experimental results show that our algorithm is superior to other adversarial training methods in terms of generalization, efficiency and scalability against various adversarial attacks.

关键词： Gradient methods

来源：评论

学校读者我要写书评

暂无评论

A Voting Approach for Explainable Classification with Rule learning 20th

A Voting Approach for Explainable Classification with Rule L...

引用

20th International conference on artificial intelligence applications and Innovations (AIAI)

作者： Noessig, Albert Hell, Tobias Moser, Georg Univ Innsbruck Dept Comp Sci Tyrol Austria Data Lab Hell GmbH Europastr 2a A-6170 Tyrol Austria

ISBN: (纸本)9783031632259;9783031632235;9783031632228

State-of-the-art results in typical classification tasks are mostly achieved by unexplainable machine learning methods, like deep neural networks, for instance. Contrarily, in this paper, we investigate the application of rule learning methods in such a context. Thus, classifications become based on comprehensible (first-order) rules, explaining the predictions made. In general, however, rule-based classifications are less accurate than state-of-the-art results (often significantly). As main contribution, we introduce a voting approach combining both worlds, aiming to achieve comparable results as (unexplainable) state-of-the-art methods, while still providing explanations in the form of comprehensible rules. Considering a variety of benchmark data sets including a use case of significant interest to insurance industries, we prove that our approach not only clearly outperforms ordinary rule learning methods, but also yields results on a par with state-of-the-art outcomes.

关键词： Rule learning Explainable artificial intelligence Ensemble learning Voting machine learning

来源：评论

学校读者我要写书评

暂无评论

Exploring the Feasibility of Event-Related Potentials in Visual Surveillance applications 12

Exploring the Feasibility of Event-Related Potentials in Vis...

引用

12th International Winter conference on Brain-Computer Interface (BCI)

作者： Kwon, Byoung-Hee Han, Dong-Kyun Ahn, Hyung-Ju Korea Univ Dept Brain & Cognit Engn Seoul South Korea Korea Univ Dept Artificial Intelligence Seoul South Korea

ISBN: (纸本)9798350309430

This study investigates the feasibility of leveraging Event-Related Potentials (ERP) within the realm of military surveillance, utilizing non-invasive brain-computer interface (BCI) technologies. Focused on enhancing static image target recognition capabilities, especially in the domain of satellite imagery, our research involved the creation of an extensive EEG database to foster advanced ERP classification through deep learning methodologies. ERPs, known for their association with sensory, cognitive, or motor event processing, are pivotal in the effective deployment of BCI for practical applications. Our approach entailed an in-depth analysis of EEG data, derived from personnel engaged in simulated surveillance tasks, to discern nuanced ERP classifications crucial for military surveillance operations. The cornerstone of our study was the real-time analysis of single-trial ERP data, employing sophisticated deep learning algorithms, with the objective of validating the practical applicability of EEG-based systems in military surveillance contexts. The outcomes of this research have the potential to inaugurate a new frontier in military surveillance, synergizing human cognitive prowess with advanced computational techniques. This integration of human cognitive processes with machine learning algorithms in military surveillance and target recognition is a significant contribution to the burgeoning field of BCI, offering novel solutions for bolstering national security and defense mechanisms.

关键词： event related potential surveillance deep learning electroencephalogram

来源：评论

学校读者我要写书评

暂无评论

Collaborative defense Strategies: AI, ML, and Cybersecurity: A Comprehensive Study 12th

Collaborative Defense Strategies: AI, ML, and Cybersecurity:...

引用

12th International conference on Frontiers of Intelligent Computing: Theory and applications, FICTA 2024

作者： Borah, Samarjeet Dhabliya, Dharmesh Dhage, Prashant Shukla, Jyoti Rai, Sumit Kumar Bhattacharya, Saurabh Department of Computer Applications Sikkim Manipal Institute of Technology Sikkim Manipal University Sikkim India Department of Information Technology Vishwakarma Institute of Information Technology Maharashtra Pune India Nagpur Campus Pune India Computer Science and Engineering Arya College of Engineering Jaipur India Department of Mechanical Engineering Dr. D. Y. Patil Institute of Technology Maharashtra Pimpri Pune India Assistant Professor SCSE Galgotias University Uttar Pradesh Greater Noida India

ISBN: (纸本)9789819601462

In the fast-changing field of cybersecurity, the rise of advanced threats requires new and creative defense strategies. This study thoroughly examines collaborative defense strategies, focusing on the utilization of artificial intelligence (AI) and machine learning (ML) techniques. The study aims to evaluate the effectiveness of five prominent machine learning algorithms (random forest, support vector machine (SVM), gradient boosting, isolation forest, and one-class SVM) in the field of cybersecurity. The assessment is carried out utilizing the NSL-KDD dataset, which is a standard in the industry. The study commences by investigating the origins of collaborative defense, analyzing its historical development and fundamental principles. The text explains the importance of AI in collaborative defense, highlighting machine learning algorithms and natural language processing as essential elements. The study explores the uses of artificial intelligence, specifically in identifying, averting, and reacting to threats. A substantial part of the research focuses on evaluating the effectiveness of the five chosen machine learning algorithms. The evaluation includes predictive analysis to forecast cyber threats and proactive defense measures. The study examines how machine learning improves the sharing of threat intelligence by facilitating real-time information exchange between collaborating entities. The challenges and considerations related to incorporating AI and ML into cybersecurity are examined, emphasizing ethical implications, bias, fairness, transparency, and accountability. Case studies and success stories from real-world scenarios showcase examples of successful collaborative defense strategies applied in various industries and sectors. The study evaluates and contrasts the random forest, SVM, gradient boosting, isolation forest, and one-class SVM algorithms based on performance metrics like accuracy, precision, recall, and F1 score, utilizing the NSL-KDD dataset. T

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

artificial intelligence in Portfolio Selection Problem: A Review and Future Perspectives 19th

Artificial Intelligence in Portfolio Selection Problem: A Re...

引用

19th International conference on Hybrid artificial intelligence Systems

作者： Sanchez-Fernandez, Alvaro Diez-Gonzalez, Javier Perez, Hilde Univ Leon Dept Mech Comp & Aerosp Engn Leon 24071 Spain

ISBN: (纸本)9783031741852;9783031741869

Portfolio selection, the process of selecting the optimal combination of securities to achieve investors objectives, is a leading problem in finance. Ever since its inception, the problem has been widely addressed theoretically but its practical applications in portfolio management have seen few changes, with new technologies like artificial intelligence (AI) having limited impact in practice. The present study addresses this gap by identifying six main areas of the portfolio selection process and analyzing literature trends and gaps in AI methods within these areas. Additionally, it proposes four primary research avenues where AI can enhance portfolio selection in both theory and practice: i) utilizing alternative datasets and big-data analysis, ii) implementing robust predictive portfolio optimization techniques, iii) applying Reinforcement learning (RL) methods for dynamic portfolio optimization, and iv) leveraging AI to make portfolio optimization more applicable in real-world scenarios.

关键词： artificial intelligence machine learning Metaheuristics Portfolio Optimization Portfolio Selection

来源：评论

学校读者我要写书评

暂无评论

2nd International conference on artificial intelligence and machine learning applications: Healthcare and Internet of Things, AIMLA 2024

2nd International Conference on Artificial Intelligence and ...

引用

2nd International conference on artificial intelligence and machine learning applications, AIMLA 2024

ISBN: (纸本)9798350349221

The proceedings contain 220 papers. The topics discussed include: unmasking pneumothorax: deep learning strategies for precise classification and segmentation;CNN-enabled generation of comprehensive reports from chest and orthopedic radiographs;smart aeroponic farms with IoT-enabled efficient automation and monitoring;health data tracking for effective health care monitoring system using fog computing;a smart automated roller clamp for iv therapy;harnessing deep learning for precise diagnosis of 6 types of cancers;load sharing autonomous hybrid micro-grid interlinking converter;cyber sleuth: harnessing NLP and blockchain for twitter based fake news detection;identifying rocks and mineral resources using hyper spectral analysis;and RESNET-101 and faster R-CNN fusion accurate brain tumor detection and categorization.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Toward an adaptive deep reinforcement learning agent for maritime platform defense 5

Toward an adaptive deep reinforcement learning agent for mar...

引用

conference on artificial intelligence and machine learning for Multi-Domain Operations applications V

作者： Markowitz, Jared Staley, Edward W. Johns Hopkins Univ Appl Phys Lab Laurel MD 20723 USA

ISBN: (数字)9781510661936

ISBN: (纸本)9781510661929;9781510661936

We explore strategies for improving the versatility of deep reinforcement learning (DRL) agents trained for maritime platform defense, in an effort to avoid impractical retraining when conditions change. DRL platform defense agents must be able to effectively schedule countermeasures, with constraints and against incoming raids of threats of uncertain type. Here we provide methods, centered on domain randomization, threat representation, and neural network architecture modification, for addressing changes in the relative locations and orientations of ships in the fleet, the number of ships and their inventories, and the distribution of threats. Testing our interventions in a realistic simulator, we show that a base DRL agent may be extended to account for a wide variety of changes in the operational scenario, with little degradation of performance.

关键词： Deep Reinforcement learning Maritime Platform defense AI Safety Continual learning

来源：评论

学校读者我要写书评

暂无评论

defense Method Challenges Against Backdoor Attacks in Neural Networks 6

Defense Method Challenges Against Backdoor Attacks in Neural...

引用

6th International conference on artificial intelligence in Information and Communication, ICAIIC 2024

作者： Shamshiri, Samaneh Sohn, Insoo Dongguk University Division of Electronics and Electrical Engineering Seoul Korea Republic of

ISBN: (纸本)9798350344349

Open-source machine-learning models demon-strated promising performance in a wide range of applications. However, they have been proved to be fragile against backdoor attacks. Backdoor attack, as a cyber-Threat, results in targeted or not-Targeted mis-classification of the neural networks without effecting the accuracy of the benign data samples. This happens through inserting imperceptible malicious triggers to the small part of datasets to change the prediction of the model based on attacker desired results. Therefore, a big part of researches focused on improving the robustness of the neural networks using different kind of detection and mitigation algorithms. In this paper, we discussed the challenges of the defense methods against backdoor attacks in machine learning models. Furthermore, we explored three state-of-The art defense algorithms against BDs including DB-COVIDNet, fine-pruning, LPSF and delve into the evolving landscape of backdoor attacks and the inherent difficulties in developing robust defense mechanisms. © 2024 IEEE.

关键词： machine learning

来源：评论

学校读者我要写书评

暂无评论

没有更多数据了...

全选清除本页清除全部题录导出标记到“检索档案”

共60页 << < 1 2 3 4 5 6 7 8 9 10 > >>

检索报告对象比较合并检索0

隐藏清空

合并搜索

回到顶部

执行限定条件

内容：

评分：

请选择保存的检索档案：

请选择收藏分类：

订阅名称：

通借通还

温馨提示：

图书名称：

借书校区：

取书校区：

手机号码：

邮箱地址：

一卡通帐号：

电话和邮箱必须正确填写，我们会与您联系确认。

联系人：

所在院系：

联系邮箱：

联系电话：

内蒙古自治区呼和浩特市赛罕区大学西街235号邮编: 010021

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：