检索结果-内蒙古大学图书馆

10th IEEE World Forum on Internet of Things, WF-IoT 2024

作者： Du, Yao Wang, Zehua Leung, Cyril Leung, Victor C.M. The University of British Columbia Department of Electrical and Computer Engineering VancouverBCV6T 1Z4 Canada China University of Mining and Technology School of Computer Science and Technology Xuzhou221116 China Shenzhen University College of Computer Science and Software Engineering Shenzhen518060 China

ISBN: (纸本)9798350373011

Intelligent Internet of Things (IIoT), a network paradigm, is an interconnection of intelligent edge devices, empowered by machine learning models. The recent emergence of large language models (LLMs) opens a new path towards IIoT. Although device models are generally lightweight and suitable for edge devices with limited processing power, their performance is less impressive compared to LLMs running on large servers. Server models offer superior performance with the cost of significant computational resources for model inference. To realize cost-effective IIoT, we introduce a novel collaborative inference framework: the online speculative inference enabled by device collaboration and time divisions. We aim to find the minimum number of servers required for the immediate processing of arrived inference requests. To solve the problem, we propose an evolving directed acyclic graph along with a Proof-of-Deletion mechanism for cost reduction and privacy protection. Based on computer simulations using heterogeneous LLMs, it is found that time-division online speculative inference is a promising approach towards cost-effective IIoT. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Comparative Study On Breast Cancer Classification Using Multiple Convolution Neural Network Architectures 3

Comparative Study On Breast Cancer Classification Using Mult...

引用

3rd International Conference on Smart Electronics and Communication, ICOSEC 2022

作者： Hossinq, Md. Murad Molla, Shourav Javed Mehedi Shamrat, F.M. Samia, Mahsuba Meherunnessa Saha, Rakhi Moni Khater, Ankit Daffodil International University Department of Computer Science and Engineering Dhaka Bangladesh Daffodil International University Department of Software Engineering Dhaka Bangladesh Jadavpur University Department of Computer Science and Engineering India

ISBN: (数字)9781665497640

ISBN: (纸本)9781665497640

Cancer of the breast is one of the primary causes of mortality of women across the globe. Breast abnormalities may often be diagnosed and classified with the use of ultrasound imaging. To better pinpoint health issues, radiologist diagnosis have been supported by a variety of CAD technologies created in recent decades. Using Automatic Breast Ultrasound (ABUS) scans, this research employed CNN models to differentiate between benign tumor, malignant tumor, and Normal breast tissue. Pre-processing the data is crucial in data classification since it helps the learning model function more effectively. The implemented dataset contains unprocessed image data where classes have data imbalance issue. So, it is important to resolve this imbalance problem. To resolve this issue data augmentation approach is applied on the minority class. Before the learning models are employed to the preprocessed data, the data is first partitioned into two subsets: a training set and a test set. This study's deep learning models for breast ultrasound classification are MobileNetV2, VGG16, AlexNet, ResNet, Inception V3, and Xception. Each model is trained and then evaluated at different epochs to keep track of its progress. The study found that as the epochs go higher, data loss lowers and accuracy rises. The accuracy of MobileNetV2, VGG16, AlexNet, ResNet, Inception V3, and Xception is 98.82%, 94.70%, 95.96%, 93.50%, 92.72%, and 93.65%, respectively. MobileNetV2 outperforms with 98.82% accuracy rate the comparative to other applied models. Finally, breast cancer is classified using the MobileNetV2 model with significant accuracy and precision. © 2022 IEEE.

关键词： Ultrasonic imaging

来源：评论

学校读者我要写书评

暂无评论

A Real-Time Hand Sign Language Recognition System for Threatening Situations Using Deep Learning 12

A Real-Time Hand Sign Language Recognition System for Threat...

引用

12th International Symposium on Digital Forensics and Security, ISDFS 2024

作者： Shwany, Zardasht Abdulaziz Abdulkarim Ismail, Shayda Khudhur Khoshnaw, Karwan Hoshyar Khalid Mustafa, Twana Saeed Karabatak, Murat Othman, Nashwan Adnan Erbil Polytechnic University Physiotherapy Department Erbil Iraq Ministry of Higher Education and Scientific Research Network Department Erbil Iraq Erbil Polytechnic University Department of Information and Communication Technology Engineering Erbil Iraq Firat University Department of Software Elazig Turkey College of Science Knowledge University Department of Computer Science Erbil Iraq Knowledge University Department of Computer Engineering Erbil Iraq Al-Kitab University Department of Computer Engineering Altun Kupri Iraq

ISBN: (纸本)9798350330366

Hand sign language has been done as physical movements in natural languages that humans have used since ancient times, along with letters, words, and spoken language. This paper presents a real-time method to identify threatening signs by criminals during interrogation, which increases their criminal rank and helps to reach conclusions. The proposed method is to install a camera of appropriate quality in front of the offender, record hand gestures in a specific area of the hand, apply some image processing techniques, such as contrast enhancement techniques, to the image to facilitate recognition as input, and then classify the images using a convolutional neural network (CNN) for a specific problem with high specifications for that topic by and using AlexNet. The accuracy of the presented method is more than 94.2% in real-time testing. © 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

Penetration Testing Operating Systems: Exploiting Vulnerabilities

Penetration Testing Operating Systems: Exploiting Vulnerabil...

引用

Communications, Computing, Cybersecurity, and Informatics (CCCI), International Conference on

作者： Evan Gardner Gurmeet Singh Weihao Qu Department of Computer Science Software Engineering Monmouth University USA

ISBN: (数字)9798350349832

ISBN: (纸本)9798350349849

The safeguarding of critical data stored on devices such as phones, computers, and tablets against unauthorized access has emerged as a central concern in modern society. Along with the increasing reliance on these devices for both productivity and personal affairs, the protection of the vast collections of sensitive information becomes crucial. Information safety against unauthorized access is a critical area in cybersecurity which is addressed through the discipline of penetration testing. This practice involves security researchers simulating adversarial attacks to evaluate the defenses of various technological systems, including web applications, operating systems, and networks, with the goal of protecting sensitive data from malicious actors. This research specifically focuses on the study of penetration testing operating systems without requiring login credentials, employing techniques such as command combinations in languages like BASH within the terminal to gain access to administrative accounts. Our further studies explore the performance of emulating keystrokes when these command combinations are used in conjunction with penetration testing devices, such as a USB Rubber Ducky, focusing on optimizing speed and efficiency. This research uncovers significant security vulnerabilities that, if exploited, could result in severe consequences not only for individual devices but also for entire networks and critical infrastructures, including core businesses, healthcare systems, schools, and government agencies. By identifying and mitigating these vulnerabilities, we contribute to strengthening security protocols, such as implementing system administration enhancements that prevent unauthorized access to the root terminal. In this way, our work bolsters efforts to protect digital systems against evolving cyber threats, ensuring the safety and integrity of both individual and collective digital operations.

关键词： Productivity Performance evaluation Protocols Operating systems Medical services Universal Serial Bus Telecommunication computing Rubber Protection Penetration testing

来源：评论

学校读者我要写书评

暂无评论

A New Secure Encryption Algorithm Based on RC4 Cipher and 4D Hyperchaotic Sprott-S System 5

A New Secure Encryption Algorithm Based on RC4 Cipher and 4D...

引用

5th College of science International Conference on Recent Trends in Information Technology, CSCTIT 2022

作者： Mohammed, Nadia M. Al-Kateeb, Zeena N. College of Computer Science and Mathematics University of Mosul Department of Software Engineering Mosul Iraq College of Computer Science and Mathematics University of Mosul Department of Computer Science Mosul Iraq

ISBN: (纸本)9798350334920

The widespread exchange of data in various formulas such as text and images via multimedia has created a great need for encryption techniques development, that can protect sharing of important secure data from untrusted or unauthorized access. In this paper, a two-level encryption method is proposed, the first level involves the use of an RC4 algorithm with several different length keys. The number of used keys depends on the length of the input original text. The keys are extracted from a 4D hyperchaotic Sprott_S system. The first encryption process is followed by the second encryption using the XOR gate for the first encryption output, with another key chain extracted from the same hyperchaotic system, that is pre-processed differently. Several measurements were used to measure the efficiency of the algorithm, including the time of application of the algorithm, histogram, bit error rate, and correlation. The experiments that were conducted on texts of different sizes showed the efficiency of the algorithm's performance, its high level of security, and the lack of time it needs, which confirms its quality. © 2022 IEEE.

关键词： Cryptography

来源：评论

学校读者我要写书评

暂无评论

Testing Refactoring Engine via Historical Bug Report driven LLM

arXiv

引用

arXiv 2025年

作者： Wang, Haibo Xu, Zhuolin Tan, Shin Hwei Department of Computer Science & Software Engineering Concordia University Montreal Canada

Refactoring is the process of restructuring existing code without changing its external behavior while improving its internal structure. Refactoring engines are integral components of modern Integrated Development Environments (IDEs) and can automate or semi-automate this process to enhance code readability, reduce complexity, and improve the maintainability of software products. Similar to traditional software systems such as compilers, refactoring engines may also contain bugs that can lead to unexpected behaviors. In this paper, we propose a novel approach called RETESTER, a LLM-based framework for automated refactoring engine testing. Specifically, by using input program structure templates extracted from historical bug reports and input program characteristics that are error-prone, we design chain-of-thought (CoT) prompts to perform refactoring-preserving transformations. The generated variants are then tested on the latest version of refactoring engines using differential testing. We evaluate RETESTER on two most popular modern refactoring engines (i.e., ECLIPSE, and INTELLIJ IDEA). It successfully revealed 18 new bugs in the latest version of those refactoring engines. By the time we submit our paper, seven of them were confirmed by their developers, and three were fixed. © 2025, CC BY-NC-SA.

关键词： software testing

来源：评论

学校读者我要写书评

暂无评论

Maximizing IoT Security: An Examination of Cryptographic Algorithms

Maximizing IoT Security: An Examination of Cryptographic Alg...

引用

2023 International Conference on Power Energy, Environment and Intelligent Control, PEEIC 2023

作者： Arya, Leena Sharma, Yogesh Kumar Kumar, Ramakrishna Padmanaban, Harish Devi, Suman Tyagi, Lalit Kumar Koneru Lakshmaiah Education Foundation Department of Computer Science and Engineering AP Guntur India College of Engineering National University of Science and Technology Department of Ece Muscat Oman Site Reliability and Software Engineering Professional Investment Banking HoustonTX United States Chaudhary Devi Lal University Department of Computer Science and Engineering Haryana Sirsa India G L Bajaj Institute of Technology Department of Computer Science and Engineering Greater Noida India

ISBN: (纸本)9798350357769

The proliferation of Internet of Things (IoT) devices has created a ubiquitous network of interconnected sensors and devices that generate and exchange vast amounts of data. With this increased connectivity comes a pressing need for robust security measures to safeguard IoT communications' integrity, confidentiality, and authenticity. This paper categorizes cryptographic algorithms commonly employed in IoT security, including symmetric and asymmetric encryption methods, digital signatures, and key exchange protocols. By examining the attributes of these algorithms, their strengths, and potential vulnerabilities, this paper assesses their effectiveness within the unique context of IoT. Furthermore, the paper highlights the significance of cryptographic algorithm optimization in IoT security. Strategies for enhancing algorithm efficiency, such as algorithm selection, key management, and hardware acceleration are thoroughly explored. Through these case studies, this paper underscores the practical implications of cryptographic algorithm selection and optimization, illustrating how they can prevent security breaches and enhance IoT security. © 2023 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Curse to Blessing: Leveraging Model Inversion Attacks to Detect Backdoor Attacks in Federated Learning

Curse to Blessing: Leveraging Model Inversion Attacks to Det...

引用

IEEE International Conference on Performance, Computing and Communications (IPCCC)

作者： Zhaowen Chen Mingze Zhang Caleb Mostyn Honglu Jiang Xianglong Feng Department of Computer Science and Software Engineering Miami University Oxford

ISBN: (数字)9798350367942

ISBN: (纸本)9798350367959

Federated Learning (FL) offers significant advancements in user/data privacy, learning quality, model efficiency, scalability, and network communication latency. However, it faces notable security challenges, particularly with the emergence of backdoor attacks. The distributed nature of FL complicates the development of backdoor-resistant systems compared to traditional machine learning environments. In this paper, we propose a novel approach to turn the perceived curse of model inversion (MI) attacks into a blessing, using them as a tool for detecting backdoor attacks in FL environments. Leveraging MI outputs, we propose a K-means-based feature extraction and Isolation-Forest-based anomaly detection algorithm to analyze behavior and detect abnormal learning performance, thereby identifying backdoor attacks. Experimental results demonstrate the effectiveness and superior performance of our method in detecting backdoor attacks within FL systems.

关键词： Privacy Machine learning algorithms Federated learning Databases Scalability Forestry Feature extraction Security Faces Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Evaluating the Inclusiveness of Artificial Intelligence software in Enhancing Project Management Efficiency - A review and examples of quantitative measurement methods

Evaluating the Inclusiveness of Artificial Intelligence Soft...

引用

2024 International Conference on Artificial Intelligence, computer, Data sciences, and Applications, ACDSA 2024

作者： Alevizos, Vasileios Georgousis, Ilias Simasiku, Akebu Messinis, Antonis Karypidou, Sotiria Malliarou, Dimitra Karolinska Institute Department of Learning Informatics Managament and Ethics Stockholm Sweden International Hellenic University Mlv Research Group Department of Computer Science Kavala Greece Zambia University Department of Computer Software Engineering Ndola Zambia Greece International Hellenic University Mlv Research Group Department of Computer Science Greece IntelliSolutions Athens Greece

ISBN: (纸本)9798350394528

The escalating integration of Artificial Intelligence (AI) in various domains, especially Project Management (PM), has brought to light the imperative need for inclusivity in AI systems. This paper investigates the role of AI software in augmenting both the inclusiveness and efficiency within the realm of PM. The research pivots around specific criteria that define and measure the inclusiveness of AI in PM, highlighting how AI, when developed with inclusiveness in mind, can significantly enhance project outcomes. However, there are inherent challenges in achieving this inclusiveness, primarily due to biases embedded in AI learning databases and the design and development processes of AI systems. The study offers a comprehensive examination of AI's potential to revolutionize PM by enabling managers to concentrate more on people-centric aspects of their work. This is achieved through AI's ability to perform tasks such as data collection, reporting, and predictive analysis more consistently and efficiently than human counterparts. However, the incorporation of AI in PM extends beyond mere efficiency;it represents a paradigm shift in the epistemology of PM, calling for a deeper understanding of AI's role and impact on society. Despite these advantages, the adoption of AI comes with significant challenges, particularly in terms of bias and inclusiveness. Biased AI learning databases, which use shared and reusable datasets, often perpetuate initially discriminatory algorithms. Moreover, unconscious biases and stereotypes of AI designers, developers, and trainers can inadvertently influence the behavior of the AI systems they create. This necessitates a paradigmatic shift in how AI systems are developed and governed to ensure they do not replicate or exacerbate existing social inequalities. The research proposes a methodological approach involving the development of criteria for inclusion and exclusion, alongside data extraction, to evaluate the inclusiveness and efficienc

关键词： Project management

来源：评论

学校读者我要写书评

暂无评论

Optimization of Building Construction Control System Based on Nonlinear Image Enhancement

引用

computer-Aided Design and Applications 2023年 20卷 213-224页

作者： Liu, Congru Lin, Mingsen Ghafoor, Kayhan Zrar Al-Dabagh, Mustafa Zuhaer Nayef Karras, Dimitrios A. School of Urban Construction Wuhan University of Science and Technology Wuhan China Changjiang Polytechnic Wuhan China Department of Computer Science Knowledge University Erbil44001 Iraq Department of Software & Informatics Engineering Salahaddin University-Erbil Erbil44001 Iraq School of Science Dept. General Athens Greece

To reflect the nonlinear characteristics of the building structural adjustment system, an active vibration control strategy based on the nonlinear is proposed. In this method, the size of the structural control force is determined by comparing the allowable energy with the actual energy, and its direction is determined by taking the derivative of the energy. Because there is no need to solve the linear matrix inequality, the calculation is simple and the operation is convenient. Moreover, when multiple actuators with the same capacity limit are used, the control output force is consistent, thus avoiding the design of multiple control systems and simplifying the controller design. The simulation results show that the maximum controlled displacements of floor 6 to floor 8 are 1.16cm, 1.12cm, and 0.97cm, respectively. The proposed nonlinear energy control method has the advantages of simple control process and avoiding actuator saturation. © 2023 CAD Solutions, LLC.

关键词： Floors

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：