检索结果-内蒙古大学图书馆

Deep Learning Based Side-Channel Attack Detection for Mobile Devices Security in 5G Networks

清华大学学报自然科学版（英文版） 2025年第3期30卷 1012-1026页

作者： Amjed A.Ahmed Mohammad Kamrul Hasan Ali Alqahtani Shayla Islam Bishwajeet Pandey Leila Rzayeva Huda Saleh Abbas Azana Hafizah Mohd Aman Nayef Alqahtani Center for Cyber Security Faculty of Information Science and TechnologyUniversiti Kebangsaan MalaysiaBangi 43600Malaysia Imam Alkadhim University College Department of Computer Techniques EngineeringBaghdad 10066Iraq Center for Cyber Security Faculty of Information Science and TechnologyUniversiti Kebangsaan MalaysiaBangi 43600Malaysia Department of Networks and Communications Engineering College of Computer Science and Information SystemsNajran UniversityNajran 61441Saudi Arabia Institute of Computer Science and Digital Innovation UCSI UniversityKuala Lumpur 56000Malaysia Department of Intelligent Systems and Cyber Security Astana IT UniversityAstana 20000Kazakstan Department of Computer Science College of Computer Science and EngineeringTaibah UniversityMadinah 42353Saudi Arabia Department of Electrical Engineering College of EngineeringKing Faisal UniversityAl-Hofuf 31982Saudi Arabia

Mobile devices within Fifth Generation(5G)networks,typically equipped with Android systems,serve as a bridge to connect digital gadgets such as global positioning system,mobile devices,and wireless routers,which are vital in facilitating end-user communication ***,the security of Android systems has been challenged by the sensitive data involved,leading to vulnerabilities in mobile devices used in 5G *** vulnerabilities expose mobile devices to cyber-attacks,primarily resulting from security ***-permission apps in Android can exploit these channels to access sensitive information,including user identities,login credentials,and geolocation *** such attack leverages"zero-permission"sensors like accelerometers and gyroscopes,enabling attackers to gather information about the smartphone's *** underscores the importance of fortifying mobile devices against potential future *** research focuses on a new recurrent neural network prediction model,which has proved highly effective for detecting side-channel attacks in mobile devices in 5G *** conducted state-of-the-art comparative studies to validate our experimental *** results demonstrate that even a small amount of training data can accurately recognize 37.5％of previously unseen user-typed ***,our tap detection mechanism achieves a 92％accuracy rate,a crucial factor for text *** findings have significant practical implications,as they reinforce mobile device security in 5G networks,enhancing user privacy,and data protection.

关键词： Fifth Generation(5G)networks smartphone information leakage Side-Channel Attack(SCA) deep learning

来源：评论

学校读者我要写书评

暂无评论

Dual-Channel Multiplex Graph Neural Networks for Recommendation

引用

IEEE Transactions on Knowledge and Data engineering 2025年第6期37卷 3327-3341页

作者： Li, Xiang Fu, Chaofan Zhao, Zhongying Zheng, Guangjie Huang, Chao Yu, Yanwei Dong, Junyu Ocean University of China Faculty of Information Science and Engineering Qingdao266005 China Shandong University of Science and Technology College of Computer Science and Engineering Qingdao266590 China Shanghai Jiao Tong University Department of Computer Science and Engineering Shanghai200240 China The University of Hong Kong Department of Computer Science Hong Kong

Effective recommender systems play a crucial role in accurately capturing user and item attributes that mirror individual preferences. Some existing recommendation techniques have started to shift their focus towards modeling various types of interactive relations between users and items in real-world recommendation scenarios, such as clicks, marking favorites, and purchases on online shopping platforms. Nevertheless, these approaches still grapple with two significant challenges: (1) Insufficient modeling and exploitation of the impact of various behavior patterns formed by multiplex relations between users and items on representation learning, and (2) ignoring the effect of different relations within behavior patterns on the target relation in recommender system scenarios. In this work, we introduce a novel recommendation framework, Dual-Channel Multiplex Graph Neural Network (DCMGNN), which addresses the aforementioned challenges. It incorporates an explicit behavior pattern representation learner to capture the behavior patterns composed of multiplex user-item interactive relations, and includes a relation chain representation learner and a relation chain-aware encoder to discover the impact of various auxiliary relations on the target relation, the dependencies between different relations, and mine the appropriate order of relations in a behavior pattern. Extensive experiments on three real-world datasets demonstrate that our DCMGNN surpasses various state-of-the-art recommendation methods. It outperforms the best baselines by 10.06% and 12.15% on average across all datasets in terms of Recall@10 and NDCG@10 respectively. The source code of our paper is available at https://***/lx970414/TKDE-DCMGNN. © 1989-2012 IEEE.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

A Novel Framework for Gauging Information Extracted from Smartphones Using Neutrosophic Logic

引用

Neutrosophic Sets and Systems 2025年 76卷 154-171页

作者： Abou Alzahab, R.M. Ismail, Amr Abd Elkhalik, S.H. Shams, M.Y. El-Bakry, H.M. Salama, A.A. Department of Mathematics and Computer Science Faculty of Science Port Said University Egypt Department of Cybersecurity College of Engineering and Information Technology Buraydah Private Colleges Buraydah51418 Saudi Arabia Department. of Communication and Computer Engineering Air Defense University Egypt Faculty of Artificial Intelligence Kafrelsheikh University Kafrelsheikh33516 Egypt Department of Information Systems. Faculty of Computer and Information Science Mansoura University Egypt

Smartphones contain a vast amount of information about their users, which can be used as evidence in criminal cases. However, the sheer volume of data can make it challenging for forensic investigators to identify and use the most relevant information. Neutrosophic logic is a generalization of fuzzy logic that allows for uncertainty and vagueness, making it a more potent tool for dealing with the ambiguity of real-world data. The proposed framework aims to identify and utilize the most relevant information for forensic investigators, making it easier to solve criminal cases using Neutrosophic logic. This novel approach provides a more powerful tool for dealing with the ambiguity of smartphone data, ultimately improving the accuracy and effectiveness of forensic investigations. Our research has utilized Neutrosophic logic to evaluate the degree of truth, falsity, or Indeterminacy of this information. Additionally, this study analyzes conversations between individuals using Excel’s fuzzy lookup add-in to determine the percentage of truth and false in each conversation. The results were compiled into a dataset and utilized a Neutrosophic Python code to evaluate the information. The results indicate the percentage of truth, false, and Indeterminacy in each conversation and which can be used to determine its admissibility as evidence and which not. © 2025, University of New Mexico. All rights reserved.

关键词： Smartphones

来源：评论

学校读者我要写书评

暂无评论

Fault-Tolerant Controller Design for PMSM Drives with Single-Phase Fault Inverters 4

Fault-Tolerant Controller Design for PMSM Drives with Single...

引用

4th International Symposium on Instrumentation, Control, Artificial Intelligence, and Robotics, ICA-SYMP 2025

作者： Buakaew, Sornchai Pongyart, Witthawas King Mongkut's University of Technology North Bangkok Faculty of Engineering Department of Electrical and Computer Engineering Bangkok Thailand

ISBN: (纸本)9798331505400

Permanent magnet synchronous motors (PMSMs) are commonly used in various electrical drive applications due to their high efficiency and performance. However, these systems are susceptible to several types of faults. To ensure uninterrupted operation in the event of a fault, researchers have focused on developing fault-tolerant control systems. This paper presents a fault-tolerant controller design for PMSM drives with single-phase fault inverters. A fault-tolerant inverter is introduced, and an energy-based controller is implemented in the current loop, with a PI-controller governing speed control. The proposed control system is tested under both normal and fault conditions, demonstrating its ability to maintain motor torque and speed while ensuring system stability in both scenarios. © 2025 IEEE.

关键词： Permanent magnets

来源：评论

学校读者我要写书评

暂无评论

Blockchain-enhanced artificial intelligence for advanced collision avoidance in the Internet of Vehicles (IoV)

引用

Neural Computing and Applications 2025年第6期37卷 4915-4936页

作者： Talaat, Fatma M. Hamza, Alyaa A. Faculty of Artificial Intelligence Kafrelsheikh University Kafrelsheikh33516 Egypt Faculty of Engineering Technology Elsewedy University of Technology–Polytechnic of Egypt 10th of Ramadan City44629 Egypt Faculty of Computer Science & Engineering New Mansoura University Gamasa35712 Egypt Bahrain Polytechnic Isa Town Bahrain Badr City11829 Egypt

The convergence of blockchain technology and artificial intelligence (AI) presents a promising solution for enhancing safety within the Internet of Vehicles (IoV) ecosystem. This paper introduces the "Blockchain-Based Collision Avoidance with AI for Vehicles" (BCA-CAR) algorithm, which aims to provide advanced and intelligent collision avoidance capabilities in IoV. BCA-CAR combines the security and data integrity features of blockchain with the real-time decision-making capabilities of AI to prevent collisions and improve road safety. The algorithm consists of five key phases: Data Collection and Processing, AI Collision Risk Assessment, Decision and Smart Contract Execution, Data Validation and Trust (Blockchain Integration), and Learning and Improvement. In the Data Collection and Processing phase, data from vehicle sensors, cameras, V2V and V2I communication, and external infrastructure is collected and preprocessed. The AI Collision Risk Assessment phase utilizes machine learning models to analyze real-time data and predict collision risks. In the Decision and Smart Contract Execution phase, smart contracts on the blockchain automate collision avoidance actions. The Data Validation and Trust phase ensures the authenticity and integrity of data through blockchain technology. Finally, the Learning and Improvement phase leverages historical collision data to enhance predictive models and overall system performance. BCA-CAR's primary objective is to enhance safety by preventing collisions, ensuring data trustworthiness, and providing intelligent collision avoidance capabilities. This innovative algorithm has the potential to revolutionize road safety in the era of IoV by reducing accidents, improving traffic management, and enhancing the security and privacy of vehicular communication. The findings highlight that Support Vector Regression (SVR) demonstrates strong predictive accuracy and adaptability within the Internet of Vehicles (IoV), offering a reliable modeli

关键词： Risk assessment

来源：评论

学校读者我要写书评

暂无评论

YOLOv8n-CGW: A novel approach to multi-oriented vehicle detection in intelligent transportation systems

引用

Multimedia Tools and Applications 2025年第7期84卷 3809-3840页

作者： Berwo, Michael Abebe Fang, Yong Sarwar, Nadeem Mahmood, Jabar Aljohani, Mansourah Elhosseini, Mostafa School of Information and Engineering Chang’an University Shaanxi Xi’an710064 China Department of Computer Science Bahria University Lahore Campus Punjab Lahore54600 Pakistan Department of Information Technology Faculty of Computing and Information Technology University of Sialkot Punjab Sialkot51040 Pakistan College of Computer Science and Engineering Taibah University Yanbu46421 Saudi Arabia Computers and Control Systems Engineering Department Faculty of Engineering Mansoura University Mansoura35516 Egypt

In the context of Intelligent Transportation Systems (ITS), the role of vehicle detection and classification is indispensable for streamlining transportation management, refining traffic control, and conducting in-depth accident analyses. However, the intricate task of accurately detecting multi-oriented vehicles in diverse scenarios remains a challenge, even with the advancements in ITS. Factors such as vehicle morphology, design, road conditions, structural details, and climatic variables provide a significant part in the detection. To address this, our study introduces an advanced YOLOv8n model, specifically the YOLOv8n-CGW, which is built upon pre-trained deep learning frameworks. This model is meticulously tailored to enhance the detection capabilities for multi-oriented vehicles. Comprehensive evaluations on esteemed datasets like MtV, MERGED, Custom dataset, DAWN, WEDGE, and UA-DETRAC underscore the superiority of our approach over existing models. Notably, our YOLOv8n-CGW model achieves a remarkable mAP of 83.3% and boasts a swift inference time of 0.0019s, setting a new benchmark in the domain. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

A new metaheuristic optimization algorithm based on the participation of smart students to increase the class performance

引用

Soft Computing 2025年第6期29卷 2829-2844页

作者： Pira, Einollah Rouhi, Alireza Faculty of Information Technology and Computer Engineering Azarbaijan Shahid Madani University Tabriz-Maragheh East-Azarbaijan Tabriz *** Iran

The learning and teaching power of the students in different courses can be different according to their intelligence and talent. One student can be smart in a single course while he/she is lazy in other courses. After teaching all courses by the class teacher, the lazy students in each course are taught again by the smart student in the course. Inspired by this fact, we present a new metaheuristic optimization algorithm called Participation of Smart Students (PSS) in increasing the class efficiency. The effectiveness of the PSS algorithm has been analyzed by 10 general test functions, 9 test functions from CEC 2019, and 12 test functions from CEC 2022. The results of PSS algorithm are compared with the effectiveness of eight recently developed well-known algorithms, i.e., Teaching and Learning-based Optimization (TLBO) Algorithm, Black Widow Optimization (BWO), Political Optimization (PO), Barnacle Mating Optimizer (BMO),Chimpanzee Optimization Algorithm (CHOA), Aquila Optimizer (AO), Reptile Search Algorithm (RSA), Prairie Dog Optimization (PDO), and Fick’s Law Optimization (FLA). Comparison of the results obtained by the Friedman rank and Wilcoxon signed-rank tests, for all 31 test functions, shows that PSS outperforms TLBO, BMO, BWO, CHOA, AO, RSA, PDO, and FLA algorithms by 38%, 38%, 64%, 74%, 45%, 64%, 58%, and 35%, respectively. Moreover, the PSS algorithm has a higher convergence speed and hit rate (= 35%) than all other compared algorithms. Finally, the reported results of solving two practical optimization problems by the PSS algorithm confirm its higher effectiveness compared to some good algorithms in the literature. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2025.

关键词： Evolutionary computation Hit rate Metaheuristic algorithm Smart student Test function

来源：评论

学校读者我要写书评

暂无评论

Scoring System for Quantifying the Privacy in Re-Identification of Tabular Datasets

引用

IEEE Access 2025年 13卷 75727-75743页

作者： Folz, Jakob Vidanalage, Manjitha D. Aufschlager, Robert Almaini, Amar Heigl, Michael Fiala, Dalibor Schramm, Martin University of West Bohemia Faculty of Applied Sciences Department of Computer Science and Engineering Technická 8 Plzeň301 00 Czech Republic Institute ProtectIT Deggendorf Institute of Technology Dieter-Görlitz-Platz 1 Faculty of Computer Science Deggendorf94469 Germany

This study introduces the System for Calculating Open Data Re-identification Risk (SCORR), a framework for quantifying privacy risks in tabular datasets. SCORR extends conventional metrics such as k-anonymity, l-diversity, and t-closeness with novel extended metrics, including uniqueness-only risk, uniformity-only risk, correlation-only risk, and Markov Model risk, to identify a broader range of re-identification threats. It efficiently analyses event-level and person-level datasets with categorical and numerical attributes. Experimental evaluations were conducted on three publicly available datasets: OULAD, HID, and Adult, across multiple anonymisation levels. The results indicate that higher anonymisation levels do not always proportionally enhance privacy. While stronger generalisation improves k-anonymity, l-diversity and t-closeness vary significantly across datasets. Uniqueness-only and uniformity-only risk decreased with anonymisation, whereas correlation-only risk remained high. Meanwhile, Markov Model risk consistently remained high, indicating little to no improvement regardless of the anonymisation level. Scalability analysis revealed that conventional metrics and Uniqueness-only risk incurred minimal computational overhead, remaining independent of dataset size. However, correlation-only and uniformity-only risk required significantly more processing time, while Markov Model risk incurred the highest computational cost. Despite this, all metrics remained unaffected by the number of quasi-identifiers, except t-closeness, which scaled linearly beyond a certain threshold. A usability evaluation comparing SCORR with the freely available ARX Tool showed that SCORR reduced the number of user interactions required for risk analysis by 59.38%, offering a more streamlined and efficient process. These results confirm SCORR’s effectiveness in helping data custodians balance privacy protection and data utility, advancing privacy risk assessment beyond existing tools

关键词： Risk assessment

来源：评论

学校读者我要写书评

暂无评论

F2multisense: a novel approach to fuzzy fusion in multisensor data to improve saving energy in WBSN

引用

Journal of Supercomputing 2025年第6期81卷 1-19页

作者： Shankani, Rana Khalifavi, Maedeh Shirmohammadi, Zahra Nikoofard, Amirhossein Faculty of Electrical Engineering K.N.Toosi University of Technology Tehran16317-14191 Iran Department of Computer Engineering Shahid Rajaee Teacher Training University Tehran16785-163 Iran

Wireless body sensor networks (WBSNs) are vital for healthcare applications but face challenges due to limited energy resources and continuous data transmission. This study proposes F2multisense, a novel fuzzy data fusion method to optimize energy consumption at two levels: adaptive emergency detection at the node level and dynamic sampling rate adjustment at the coordinator level. At the first level, data transmission is optimized using adaptive local emergency detection and the NEWS system. At the second level, coordinator level, optimization is achieved through a fuzzy system that adaptively determines the sampling rate. Furthermore, the number of sensors aligns with the number of vital signs in the NEWS system, and the samples examined are numerous, demonstrating the completeness of the method. In addition, the dual-layer design of the system supports real-time adaptation and scalability, ensuring robust performance in dynamically changing environments and large-scale deployments. This approach integrates fuzzy logic with the NEWS system, ensuring reliable health assessments without compromising timeliness or accuracy. To evaluate the method, simulations were performed based on real sensor data from the MIMIC-II database. The results demonstrate a 40% reduction in data transmission and a 64% decrease in energy consumption compared to state-of-the-art methods, allowing efficient and precise patient monitoring. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2025.

关键词： Energy saving Fuzzy fusion Sampling rate Wireless body sensor network

来源：评论

学校读者我要写书评

暂无评论

Hybrid lightweight encryption for IoT: integrating chaotic key generators with Feistel and substitution-permutation networks for secure 3DV transmission

引用

Multimedia Tools and Applications 2025年 1-47页

作者： El-Shafai, Walid Mesrega, Ahmed K. Ahmed, Hossam Eldin H. Elbahnasawy, Nirmeen A. El-Samie, Fathi E. Abd Computer Science Department Prince Sultan University Riyadh11586 Saudi Arabia Deptartment of Electronics and Electrical Communications Engineering Faculty of Electronic Engineering Menoufia University Menouf32952 Egypt Department of Computer Science and Engineering Faculty of Electronic Engineering Menoufia University Menouf Egypt Department of Information Technology College of Computer and Information Sciences Princess Nourah Bint Abdulrahman University P.O. Box 84428 Riyadh11671 Saudi Arabia

The Internet of Things (IoT) stands as a revolutionary leap in digital connectivity, envisioning a future network connecting billions of devices, seamlessly. Amidst the myriad benefits, there arises an intricate web of challenges, prominently centered around potential threats and data security implications. Recent cryptography techniques, such as DNA-based cryptography, 3D chaos-based cryptography, and optical cryptography, face challenges including large encryption times, high energy consumption, and suboptimal rather than optimal performance. Particularly, the burden of long encryption cycles strains the energy resources of typical low-power and compact IoT devices. These challenges render the devices vulnerable to unauthorized breaches, despite large storage capacities. The hallmark of the IoT ecosystem, characterized by its low-power compact devices, is the burgeoning volume of data they generate. This escalating data influx, while necessitating expansive storage, remains vulnerable to unauthorized access and breaches. Historically, encryption algorithms, with their multifaceted architectures, have been the bulwark against such intrusions. However, their inherently-complex nature, entailing multiple encryption cycles, strains the limited energy reserves of typical IoT devices. In response to this intricate dilemma, we present a hybrid lightweight encryption strategy. Our algorithm innovatively leverages both one-dimensional (1D) and two-dimensional (2D) chaotic key generators. Furthermore, it amalgamates a classical encryption philosophy, harmonizing the strengths of Feistel and substitution-permutation networks. The centerpiece of our strategy is achieving effective encryption in merely three rounds, tailored expressly for compressed Three-Dimensional Video (3DV) frames, ensuring their unwavering integrity. Our workflow commences with the H.264/MVC compression algorithm, setting the stage for the subsequent encryption phase. Through rigorous MATLAB simulations,

关键词： Image coding

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：