检索结果-内蒙古大学图书馆

7th IET Smart Cities Symposium, SCS 2023

作者： Aljanabi, Mohammad Omran, Alaa Hamza Mijwil, Maad M. Abotaleb, Mostafa El-Kenawy, El-Sayed M. Mohammed, Sahar Yousif Ibrahim, Abdelhameed Department of computer College of Education Aliarqai university Baghdad Iraq University of information technology and communications Baghdad Iraq Computer Techniques Engineering Department Baghdad College of Economic Sciences University Baghdad Iraq Department of System Programming South Ural State University Chelyabinsk Russia Department of Communications and Electronics Delta Higher Institute of Engineering and Technology Egypt Computer Science Department Computer Science &Information Technology College Anbar University Anbar Iraq Computer Engineering and Control Systems Department Faculty of Engineering Mansoura University Mansoura Egypt

ISBN: (纸本)9781839539831

Data poisoning attacks, where adversaries manipulate training data to degrade model performance, are an emerging threat as machine learning becomes widely deployed in sensitive applications. This paper provides a comprehensive overview of data poisoning including attack techniques, adversary incentives, impacts on security and reliability, detection methods, defenses, and key research gaps. We examine label flipping, instance injection, backdoors, and other attack categories that enable malicious outcomes ranging from IP theft to accidents in autonomous systems. Promising detection approaches include statistical tests, robust learning, and forensics. However, significant challenges remain in translating academic defenses like adversarial training and sanitization into practical tools ready for operational use. With safety and trustworthiness at stake, more research on benchmarking evaluations, adaptive attacks, fundamental tradeoffs, and real-world deployment of defenses is urgently needed. Understanding vulnerabilities and developing resilient machine learning pipelines will only grow in importance as data integrity is fundamental to developing safe artificial intelligence. © The Institution of Engineering & technology 2023.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Concept of an Optical Distance and Speed Sensor Using Novel Offsetless Spatial Frequency Filters in the Area of Functional Safety

Concept of an Optical Distance and Speed Sensor Using Novel ...

引用

IEEE International Symposium on Industrial Electronics (ISIE)

作者： Frank Wasinski Werner Bonath Ubbo Ricklefs Josef Börcsök Michael Schwarz Eike Hahn Dept. of Electrical Engineering and Information Technology THM University of Applied Sciences Giessen Germany ICAS Institute for Computer Architecture and System Programming University of Kassel Kassel Germany

Optical speed sensors based on the spatial frequency filter method are a proven technology that offer high measurement accuracy over a wide speed range. Newly developed variants also enable measurements at very low speeds and increase the robustness of the method [1]. This makes the sensor very suitable for use in the area of functional safety. A measurement chain up to safety integrity level 3 (SIL3) should be feasible via a combination with a safety system on a chip (SoC) for evaluating the measurement data and an extension of the sensor module to include safety-related elements [2], [3]. By integrating the sensor at IC level, a compact overall solution is to be made possible. After the first successful tests with the safety SoC, further examinations of the measuring method with regard to functional safety are now necessary.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Convergence analysis of stochastic gradient descent with adaptive preconditioning for non-convex and convex functions

arXiv

引用

arXiv 2023年

作者： Pasechnyuk, Dmitrii A. Gasnikov, Alexander Takáč, Martin Mohamed bin Zayed University of Artificial Intelligence United Arab Emirates Moscow Institute of Physics and Technology Russia Kharkevich Institute for Information Transmission Problems RAS Russia Ivannikov Institute for System Programming RAS Russia

Preconditioning is a crucial operation in gradient-based numerical optimisation. It helps decrease the local condition number of a function by appropriately transforming its gradient. For a convex function, where the gradient can be computed exactly, the optimal linear transformation corresponds to the inverse of the Hessian operator, while the optimal convex transformation is the convex conjugate of the function. Different conditions result in variations of these dependencies. Practical algorithms often employ low-rank or stochastic approximations of the inverse Hessian matrix for preconditioning. However, theoretical guarantees for these algorithms typically lack a justification for the defining property of preconditioning. This paper presents a simple theoretical framework that demonstrates, given a smooth function and an available unbiased stochastic approximation of its gradient, that it is possible to refine the dependency of the convergence rate on the Lipschitz constant of the *** Codes 65K10 © 2023, CC BY.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

Upper bounds on the maximum admissible level of noise in zeroth-order optimisation

arXiv

引用

arXiv 2023年

作者： Pasechniuk, Dmitrii A. Lobanov, Aleksandr Gasnikov, Alexander Mohamed bin Zayed University of Artificial Intelligence United Arab Emirates Moscow Institute of Physics and Technology Dolgoprudny Russia Kharkevich Institute for Information Transmission Problems RAS Russia Ivannikov Institute for System Programming RAS Russia Skoltech Russia

MSC Codes 65K10In this paper, we leverage an information-theoretic upper bound on the maximum admissible level of noise (MALN) in convex Lipschitz-continuous zeroth-order optimisation to establish corresponding upper bounds for classes of strongly convex and smooth problems. We derive these bounds through non-constructive proofs via optimal reductions. Furthermore, we demonstrate that by employing a one-dimensional grid-search algorithm, one can devise an algorithm for simplex-constrained optimisation that offers a superior upper bound on the MALN compared to the case of ball-constrained optimisation and estimates asymptotic in dimensionality. © 2023, CC BY.

关键词： Constrained optimization

来源：评论

学校读者我要写书评

暂无评论

Creating a Dynamic Online Learning Environment with AI Integration

Creating a Dynamic Online Learning Environment with AI Integ...

引用

International Computer Sciences and information Technologies (CSIT)

作者： Oleksandra Bulgakova Zarina Viniarska Viacheslav Zosimov P.M Platonov Educational and Scientific Institute of Computer Engineering Automation Robotics and Computer Programming Odesa National University of Technology Odesa Ukraine Department of Applied information systems Taras Shevchenko National University of Kyiv Kyiv Ukraine

ISBN: (数字)9798331542634

ISBN: (纸本)9798331542641

Educational, online learning has become a common practice due to rapid digitalization and recent global events. This study focuses on developing a comprehensive online learning platform that addresses users' needs by integrating advanced AI capabilities for personalized support and adaptive learning. The platform supports user registration and authentication, course and lesson management, and offers interactive features like AI-driven chat support. In this study, we show the importance of creating user-friendly online learning platforms with the implementation of modern AI trends. The development and testing of this platform is ongoing to determine the adaptation of the system to different learning styles.

关键词： Adaptive learning Electronic learning Authentication Passwords Market research Real-time systems Artificial intelligence information technology Standards Testing

来源：评论

学校读者我要写书评

暂无评论

A Horizontal Federated Learning Approach to IoT Malware Traffic Detection: An Empirical Evaluation with N-BaIoT Dataset 26

A Horizontal Federated Learning Approach to IoT Malware Traf...

引用

26th International Conference on Advanced Communications technology, ICACT 2024

作者： Do, Phuc Hao Le, Tran Duc Vishnevsky, Vladimir Berezkin, Aleksandr Kirichek, Ruslan The Bonch-Bruevich Saint-Petersburg State University of Telecommunications Saint-Petersburg Russia Danang Architecture University Da Nang Viet Nam University of Telecommunications Department of Communication Networks and Data Transmission at Bonch-Bruevich Saint-Petersburg State Russia University of Science and Technology The University of Danang Da Nang Viet Nam The University of Danang University of Science and Technology Information Technology Faculty Danang Viet Nam V. A. Trapeznikov Institute of Control Sciences of Russian Academy of Sciences Moscow Russia Institute of Control Sciences of Russian Academy of Sciences Russia Bonch Bruevich Saint Petersburg State University of Telecommunications Department of Programming Engineering and Computer Science Russia

ISBN: (纸本)9791188428120

The increasing prevalence of botnet attacks in IoT networks has led to the development of deep learning techniques for their detection. However, conventional centralized deep learning models pose challenges in simultaneously ensuring user data privacy and detecting botnet attacks. To address this issue, this study evaluates the efficacy of Federated Learning (FL) in detecting IoT malware traffic while preserving user privacy. The study employs N-BaIoT, a dataset of real-world IoT network traffic infected by malware, and compares the effectiveness of FL models using Convolutional Neural Network, Long Short-Term Memory, and Gated Recurrent Unit models with a centralized approach. The results indicate that FL can achieve high performance in detecting abnormal traffic in IoT networks, with the CNN model yielding the best results among the three models evaluated. The study recommends the use of FL for IoT malware traffic detection due to its ability to preserve data privacy. © 2024 Global IT Research institute - GIRI.

关键词： Malware

来源：评论

学校读者我要写书评

暂无评论

Min-max optimization over slowly time-varying graphs

arXiv

引用

arXiv 2023年

作者： Nguyen, Nhat Trung Rogozin, Alexander Metelev, Dmitriy Gasnikov, Alexander Moscow Institute of Physics and Technology Moscow Russia Institute for Information Transportation Problems Moscow Russia Caucasus Mathematic Center Adygh State University Moscow Russia Ivannikov Institute for System Programming The Russian Academy of Sciences Research Center for Trusted Artificial Intelligence Moscow Russia

Distributed optimization is an important direction of research in modern optimization theory. Its applications include large scale machine learning, distributed signal processing and many others. The paper studies decentralized min-max optimization for saddle point problems. Saddle point problems arise in training adversarial networks and in robust machine learning. The focus of the work is optimization over (slowly) time-varying networks. The topology of the network changes from time to time, and the velocity of changes is limited. We show that, analogically to decentralized optimization, it is sufficient to change only two edges per iteration in order to slow down convergence to the arbitrary time-varying case. At the same time, we investigate several classes of time-varying graphs for which the communication complexity can be reduced. Copyright © 2023, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Development of a visual programming tool called SmrAI for function testing to mitigate the shortage of programming personnel in the manufacturing

Computer Software

引用

Computer Software 2022年第4期39卷 61-74页

作者： Sugiyama, Ko-Ichiro Okuda, Satsuki Tanabe, Tsubasa Takao, Kouji Higashi, Hirohito Tanaka, Kazuaki Dept. of Information Engineering National Institute of Technology Matsue College Japan NIPPO Co. Ltd. Japan Ruby Programming Shounendan Japan Shimane IT Open-innovation Center Japan Faculty of Computer Science and Systems Engineering Kyushu Institute of Technology Japan

We have developed a visual programming tool called SmrAI for function testing, and investigated whether wrapping existing source code with Scratch Blocks is an effective means of mitigating the shortage of programming personnel in the manufacturing. SmrAI is based on Smalruby, which can convert Scratch Blocks into Ruby code. In addition, SmrAI introduces two new sets of Blocks that wrap existing Ruby libraries for function testing. Since existing tools and libraries were utilized, the cost of developing SmrAI was low, and there were no changes in the function testing procedure. We conducted a verification test using staff members who were familiar with the function testing process but had little or no programming experience, and confirmed that they were able to program using SmrAI and that they had confidence in its business applications. These results are expected to contribute to the diversification and increase of programming personnel responsible for function test programming. © 2022 Japan Society for Software Science and technology. All rights reserved.

关键词： Application programs

来源：评论

学校读者我要写书评

暂无评论

Deviations in Efficiencies of Logarithmically Growing Sorting Algorithms at Infinitely Large Datasets

Deviations in Efficiencies of Logarithmically Growing Sortin...

引用

Innovations in Power and Advanced Computing Technologies (i-PACT)

作者： Steve Mathew D A School of Information Technology and Engineering Vellore Institute of Technology Vellore India Programming and Data Science Indian Institute of Technology Madras Chennai India

ISBN: (纸本)9781665426923

Asymptotic Notations have been very effective in representing the efficiencies of algorithms by analyzing the number of steps and the nature of traversals and operations that the algorithm is bound to perform. Though they represent the nature of growth of the time or space consumed by the algorithms, they only consider the fastest-growing term and not the other terms. The result from this kind of analysis often seems to be fruitful in grading the algorithms based on their efficiency, but theoretically, there seem to be evident deviations when these complexities are extrapolated to larger datasets, hypothetically ‘infinitely large’ datasets. This deviation is tracked down when the constant and slow-growing terms involved are considered. The practical difficulty of empirically verifying this fact due to the ambiguity in defining a very large number of inputs is overcome by theoretically calculating the ratio between the time complexities of algorithms of interest and applying their limit to be infinity. In this study, the algorithms heapsort and merge sort are analyzed and the drastic deviation between them is shown mathematically though they both have the complexity of $n(log(n))$ , concluding that the merge sort is actually twice as fast as heap sort when approaching infinitely large data elements.

关键词： Computers Technological innovation Complexity theory Time complexity Sorting

来源：评论

学校读者我要写书评

暂无评论

Word-Based Turkish Lip Reading System with Two Stream 3dcnn and Bilstm

SSRN

引用

SSRN 2023年

作者： Erbey, Ali Barışçı, Necaattin Department of Computer Programming Distance Education Vocational School Usak University Usak64200 Turkey Department of Information Systems Informatics Institute Gazi University Ankara Turkey Department of Computer Engineering Faculty of Technology Gazi University Ankara06500 Turkey

Lip reading is a technique that aims to understand spoken words by analyzing people's lip movements. Deep learning algorithms are used as a powerful tool for detecting and recognizing lip movements more accurately. In this study, we present a lip-reading architecture for the Turkish language. The architecture is trained to recognize Turkish words using 3DCNN (3D Convolutional Neural Network) architecture and two-stream deep learning methods. The model was trained on video data representing lip movements and learned to classify words accurately. The Turkish lip reading system has been trained and tested on a large Turkish lip reading dataset. In the experiments, an accuracy of 87.12% was achieved with the proposed model, indicating successful results in the Turkish language. The proposed model demonstrates high accuracy rates in recognizing Turkish words, showcasing its effectiveness. This paper introduces a novel architecture, a lip-reading system that employs deep learning techniques, providing a robust tool for successful Turkish lipreading applications. © 2023, 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

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：