检索结果-内蒙古大学图书馆

International Symposium on Digital Forensic and Security (ISDFS)

作者： Arafat Asim Peter J. Hawrylak School of Cyber Studies College of Engineering and Computer Science The University of Tulsa Tulsa OK USA Electrical & Computer Engineering College of Engineering and Computer Science The University of Tulsa Tulsa OK USA

ISBN: (数字)9798331509934

ISBN: (纸本)9798331509941

Internet of Things (IoT) devices are a fast-growing market, but they also possess a great challenge in terms of cyber-security, and therefore need a strong intrusion detection system (IDS). We present a machine learning-based IDS that improves attack classification through effective Feature engineering and optimized Model Selection. Whereas traditional methods rely on static and well-known features, our approach offers novel ones tcp. payload and tcp. options to improve your detection of injection and vulnerability attacks. Our results demonstrate that Random Forest outperforms the convolutional models while achieving the highest accuracy of 99.07% (6-class) and 98.53% (I5-class) in five models evaluated on the Edge-IIoTset dataset. Using SMOTE to handle class im-balance and incorporating network features related to behavior, the method is able to better detect minority class general attacks. Building upon that foundation, we utilized behavioral feature extraction, data balancing, and deep learning optimization techniques that top centralized IDS models use to improve accuracy and resilience across our framework.

关键词： Deep learning Accuracy Image edge detection Intrusion detection Feature extraction Internet of Things Security Random forests Optimization Payloads

来源：评论

学校读者我要写书评

暂无评论

NVMS-Net: A Novel Constrained Noise-View Multiscale Network for Detecting General Image Processing Based Manipulations

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2025年第5期6卷 1233-1247页

作者： Singh, Gurinder Rana, Kapil Goyal, Puneet Kumar, Sathish Cleveland State University Electrical Engineering and Computer Science ClevelandOH44115 United States Indian Institute of Technology Ropar Punjab Rupnagar140001 India Thapar Institute of Engineering and Technology Punjab Patiala147004 India NIMS University Rajasthan Jaipur303121 India

Ensuring the authenticity and integrity of digital images is a major concern in multimedia forensics, driving research on universal schemes for detecting diverse image manipulations (or processing operations). Although some prior works have addressed general-purpose image manipulation detection, they have been evaluated under constrained environments. Developing an approach that effectively identifies multiple manipulations in real-world scenarios remains a challenge. To address this issue, in this article, we have designed a novel constrained noise-view based multiscale network (NVMS-Net) that jointly exploits constrained noise-view and multiscale feature learning for multiple image processing operation detection. Our NVMS-Net includes four stages: constrained noise-view, generalizable feature learning, multiscale feature learning, and classification. First, a noise extraction layer (NEL) is employed to suppress the image content information for the extraction of noise features. The statistical modeling of these noise features is further improved by statistical modeling layer (SML) to achieve a better noise-view of image tampering artifacts. Then, we use multiple convolution-batch normalization-ReLU (CBR) blocks to learn generalizable noise features that are sensitive to image manipulations. Further, a multiscale aggregation module (MSAM) is proposed that leverages image tampering features at multiple scales through the aggregation of low and high-level features. The extensive experimental results show that the NVMS-Net consistently outperforms the existing approaches on different dataset settings. Importantly, NVMS-Net shows better performance in real-world scenarios, particularly against antiforensic techniques and adversarial attacks. The proposed NVMS-Net provides an overall accuracies of 98.21% and 98.60% on BOSSBase and Dresden datasets, respectively. © 2020 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Introduction to the Special Issue on PADS 2023

引用

ACM Transactions on Modeling and computer Simulation 2025年第2期35卷 1-3页

作者： Dong Jin Christopher Carothers Electrical Engineering and Computer Science University of Arkansas Fayetteville Fayetteville United States Computer Science Rensselaer Polytechnic Institute Troy United States

来源：评论

学校读者我要写书评

暂无评论

Energy-Efficient Multi-Path Selection to Achieve Hard Reliability for Mission-Critical Data Transmission in Industrial IoT

Energy-Efficient Multi-Path Selection to Achieve Hard Reliab...

引用

International Communication Systems and Networks and Workshops, COMSNETS

作者： Soumya Nandan Mishra Manas Khatua Computer Science and Engineering IIT Guwahati India

ISBN: (数字)9798331531195

ISBN: (纸本)9798331531201

Industry 4.0 applications demand strict reliability guarantee of 99%. For example, repeated packet losses can cause communication failures in supply chain systems. Now-a-days, many such industrial applications use the benefits of Internet of Things (IoT) for data transmission by forming Mission-critical IoT (MC-IoT) networks. However, the IoT networks are resource constraint in nature, and thus, the data transmissions are lossy by default. This contradictory feature imposes severe challenges on the traditional routing protocol RPL designed for IoT networks. As a solution to that issue, several multi-path based solutions have been proposed. Specifically, the Reliable Multi-Path RPL (RMP-RPL) was designed focusing on hard reliability requirement. However, the solutions either cannot achieve the goal on hard reliability requirement or achieves the goal by sacrificing energy consumption. Therefore, this paper introduces an energy-efficient multi-path selection strategy in RPL called EEMP-RPL which is designed to achieve the hard reliability goal in mission-critical applications. The proposed protocol EEMP-RPL achieves the desired reliability requirement by strategically transmitting a data packet multiple times to multiple parents so that at least one of them can receive the data packet successfully. On the other hand, it saves energy by allowing only a few nodes among the receiving parents to forward the data packets further. Limited forwarding is achieved by assigning a data packet forwarding probability (P D ) to each receiving node of a data packet. This paper also proposes a method to calculate the probability P D of a node dynamically. Execution results on Cooja simulator show that EEMP-RPL achieves the hard reliability requirement goal of 99% up to a certain limit in reference to the size of the network while reducing energy consumption of the network by 25.74% compared to the RMP-RPL. EEMP-RPL also shows an improvement of 40.23% and 33.75% in terms of end-to-end

关键词： Energy consumption Mission critical systems Supply chains Reliability engineering Routing Energy efficiency Fourth Industrial Revolution Delays Reliability Data communication

来源：评论

学校读者我要写书评

暂无评论

Brain-Conditional Multimodal Synthesis: A Survey and Taxonomy

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2025年第5期6卷 1080-1099页

作者： Mai, Weijian Zhang, Jian Fang, Pengfei Zhang, Zhijun South China University of Technology School of Automation Science and Engineering Guangzhou510640 China Southeast University School of Computer Science and Engineering Nanjing210096 China South China University of Technology Key Library of Autonomous Systems and Network Control Ministry of Education The School of Automation Science and Engineering Guangzhou510640 China Institute for Super Robotics Huangpu Guangzhou510555 China Nanchang University Jiangxi Thousand Talents Plan Nanchang330031 China Jishou University College of Computer Science and Engineering Jishou416000 China Guangdong Artificial Intelligence and Digital Economy Laboratory Pazhou Lab Guangzhou510335 China Shaanxi University of Technology Shaanxi Provincial Key Laboratory of Industrial Automation School of Mechanical Engineering Hanzhong723001 China Changsha Normal University School of Information Science and Engineering Changsha410100 China Guangdong University of Petrochemical Technology School of Automation Science and Engineering Institute of Artificial Intelligence and Automation Maoming525000 China

In the era of artificial intelligence generated content (AIGC), conditional multimodal synthesis technologies (e.g., text-to-image) are dynamically reshaping the natural content. Brain signals, serving as potential reflections of how the brain interprets external information, exhibit a distinctive one-to-many correspondence with various external modalities. This correspondence makes brain signals emerge as a promising guiding condition for multimodal synthesis (e.g., image, text, and audio), which is crucial for developing practical brain–computer interface systems and unraveling complex mechanisms underlying human perception. This survey comprehensively examines the emerging field of brain-conditional multimodal synthesis, termed AIGC-brain, to delineate the current landscape and future directions. To begin, related neuroimaging datasets and generative models are introduced as the foundation of AIGC-brain decoding and analysis. Next, we present a comprehensive taxonomy according to AIGC-brain methodologies, followed by task-specific representative work and implementation details to facilitate in-depth comparison and analysis. Quality assessments are then introduced for both qualitative and quantitative evaluation. Finally, this survey explores insights gained, outlining current challenges and prospects of AIGC-brain. As a pioneering survey, this article paves the way for future advances in AIGC-brain research. © 2020 IEEE.

关键词： Taxonomies

来源：评论

学校读者我要写书评

暂无评论

Relationships Among Organizational-Level Maturities in Artificial Intelligence, Cybersecurity, and Digital Transformation: A Survey-Based Analysis

引用

IEEE Access 2025年 13卷 88399-88411页

作者： Burak Kubilay Baris Celiktas Computer Science Engineering Department Işik University Istanbul Türkiye

The rapid development of digital technology across industries has highlighted the growing need for enhanced competencies in Artificial Intelligence (AI), Cyber security (CS), and Digital Transformation (DT). While there is extensive research on each of these domains in isolation, few studies have investigated their relationship and joint impact on organizational maturity. This study aims to address this gap by analyzing the relationships among the maturity levels of AI, CS, and DT at the organizational level using Structural Equation Modeling (SEM) and descriptive statistical methods. A mixed-methods design combines quantitative survey data with synthetic modeling techniques to assess organizational preparedness. The findings demonstrate significant bidirectional correlations among AI, CS, and DT, with technology and finance being more advanced than government and education. The research highlights the necessity of an integrated AI-CS strategy and provides actionable recommendations to increase investments in these domains. In contrast to the preceding fragmented evaluations, the current research establishes a comprehensive, empirically grounded framework that acts as a strategic reference point for digital resilience. Follow-up studies will involve collecting real-world industry data in support of empirical validation and predictive ability in measuring AI and CS maturity. This research adds to the existing literature by filling the gaps among fragmented digital maturity models and providing a consistent empirical base for organizations to thrive in an evolving technological environment.

关键词： Artificial intelligence Industries Organizations ISO Standards Biological system modeling Surveys Automation Systematics Smart manufacturing Risk management

来源：评论

学校读者我要写书评

暂无评论

Reconstruction of a realistic 3D human model from a single 2D image

引用

Procedia computer science 2025年 260卷 701-707页

作者： Mohit Kushwaha Jaytrilok Choudhary Dhirendra Pratap Singh Department of Computer Science & Engineering MANIT Bhopal Madhya Pradesh INDIA-462003

Generation of human 3D models has become one of the most interesting topics in the domain of computer vision. This is because the process of reconstructing 3D human body models from 2D images has of course attracted a lot of attention in the present days because of the potential importance of the same in several different application areas. Such are the virtual trial rooms for online shopping clothes, virtual reality for general and sporting activities and diagnostic assessment of neurological diseases. The ever increasing relevance of 3D models in fields like e-commerce underlines the requirements of converting 2D images into 3D reconstructions. In this study, a new method is presented to animating various human models from single images employing advanced mesh deformer and volume renderer. The effectiveness of the proposed method is tested on the THuman4.0 and DeepCap datasets, where the evaluation indicators include PSNR, SSIM, LPIPS, and FID. The proposed approach is shown to be more effective than the current state of the art methods, enhancing the existing methods of 3D human model reconstruction.

关键词： 3D human reconstruction 3D model Realistic human model Volume rendering Mesh deformation

来源：评论

学校读者我要写书评

暂无评论

Evaluating climate adaptation strategies for coastal resilience using multi-criteria decision-making framework

引用

Marine Pollution Bulletin 2025年 217卷 118060页

作者： Teng, Meng Zhang, Fuli Gong, Zhi Park, Jong Hyuk School of Computer Science and Engineering Hunan University of Information Technology Changsha410151 China Department of Computer Science and Engineering Seoul National University of Science and Technology Seoul01811 Korea Republic of

Coastal regions face significant challenges due to climate change, requiring effective adaptation strategies to protect ecosystems, infrastructure, and communities. Selecting appropriate strategies remains complex due to the need to balance ecological, economic, and social factors. This study introduces a novel AHP-based Multi-Criteria Decision-Making (MCDM) framework that systematically integrates empirical evidence and expert judgment to evaluate and prioritize coastal adaptation strategies. The framework incorporates inputs from 20 experts and evaluates alternatives across four key criteria: Environmental Impact (weight = 0.533), Cost-Effectiveness (0.255), Social Acceptance (0.149), and Long-Term Sustainability (0.063). Among the evaluated strategies, mangrove restoration received the highest priority score of 0.70, highlighting its superior performance across environmental, social, and sustainability dimensions. The proposed methodology offers a transparent and replicable approach to assess trade-offs, supporting informed and context-specific coastal adaptation planning aligned with sustainable development goals. © 2025 Elsevier Ltd

关键词： Climate change

来源：评论

学校读者我要写书评

暂无评论

Flexible Hybrid Electronics for Printing of Nano and Chip Scale Structures 1

Flexible Hybrid Electronics for Printing of Nano and Chip Sc...

引用

1st International Conference on Advances in computer science, Electrical, Electronics, and Communication Technologies, CE2CT 2025

作者： Singh, Neelima Gupta, Radha Singh, Rakesh Kumar Shruthi, T.S. Gupta, Parbhat Singhal, Abhinav Uttaranchal University Department of Computer Science and Engineering Dehradun India Dayananda Sagar College of Engineering Department of Mathematics Bangalore560078 India IIMT College of Engineering U.P. Greater Noida India Nitte Meenakshi Institute of Technology Department of Mathematics Karnataka Bangalore India SRM Institute of Science and Technology Delhi NCR Campus Ghaziabad Modinagar India Tula's Institute Department of Computer Science and Engineering Dehradun248197 India

ISBN: (纸本)9798331518578

Adaptable sensors, circuits, and substrates are joined with unbending electronic parts to make adaptable flexible hybrid electronics (FHE). The printing of nanomaterials has benefits over the costly, multi-step, and blunder inclined cleanroom-based nano-microfabrication process, like expense adequacy, high-throughput, steadfastness, and adaptability. FHE usually consists of devices that range in size from nano to chip, and it might be difficult to integrate them using a standard procedure. The mix of ultrathin chips and nanowires (NWs) based electronic layers on a solitary substrate is shown here utilizing printed gadgets. The performance of the transistors on UTCs (ultrathin chips) is thoroughly studied in order to optimise the printing process. The adequacy of the printing system is affirmed by electrical information accumulated from 14 semiconductors on 3 unmistakable chips, which uncover next to no adjustment of execution following exchange printing. Building UV photodetectors utilizing DIW printing further exhibits the unrivaled grade nature of ZnO-NWs-put together electronic layers delivered with respect to a similar substrate. © 2025 IEEE.

关键词： Substrates

来源：评论

学校读者我要写书评

暂无评论

A Novel Remote Desktop Protocol Data Security Approach Using Hybrid Cryptographic Algorithm and Unsupervised Neural Network

A Novel Remote Desktop Protocol Data Security Approach Using...

引用

Computing and Information Technology (ICCIT-1441), 2020 International Conference on

作者： Most. Mazriha Akter Mohua Ali Ameen Abdu Saif Nishita Aktar Md.Nazmus Sakib Computer Science and Engineering World University of Bangladesh Dhaka Bangladesh Computer Science Lincoln University Petaling Jaya Malaysia Communication and Computer Engineering Taiz University Taiz Yemen

ISBN: (数字)9798350353839

ISBN: (纸本)9798350353846

An empirical investigation uses AES, RSA, and a character replacement approach, along with the unsupervised neural network RBM, to enhance the security of Remote Desktop Protocol communication. It was discovered that Remote Access Trojans, such as PlugX, are used to establish control through remote access to compromised systems. Unauthorized access is obtained by an intruder to a system, resulting in the theft of sensitive data and the exploitation of a vulnerable workstation for malicious activities using a Remote Access Trojan (RAT). The proposed hybrid model is combined with RBM to ensure data transaction security between nodes. In addition, a comparative classification algorithm is integrated to further enhance the model. This study evaluates key size, data size, execution time, and memory usage of the algorithm. Cryptography is essentially a resource-intensive approach to computing security. Competitive and comparative analyses are being conducted to investigate the performance measures of the proposed model. In most cases, it was found that resource utilization was correlated with the key lengths of the AES and RSA algorithms. Due to the use of multiple categorical attacks on the remote desktop protocol, researchers have limited focus on secure data transaction of the remote desktop protocol. Therefore, the study limits the analysis of advanced security technologies that are used to gain a deeper understanding of the threats. This suggests that proposed algorithm is more reliable compared to AES and RSA when considering both security and efficacy. The research introduces a cutting-edge hybrid cryptographic model, enhanced with an unsupervised neural network, to outsmart potential intruders and protect sensitive data. By employing a Restricted Boltzmann Machine (RBM) for smart, autonomous threat recognition, the study assesses performance metrics crucial for real-world application and achieves a remarkable 98.75% accuracy, setting a new standard in RDP security

关键词： Protocols Computational modeling Neural networks Data models Encryption Classification algorithms Workstations Security Trojan horses S Box

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：