检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Zhang, Zongyuan Duan, Tianyang Lin, Zheng Huang, Dong Fang, Zihan Sun, Zekai Xiong, Ling Liang, Hongbin Cui, Heming Cui, Yong Gao, Yue Department of Computer Science The University of Hong Kong Hong Kong School of Computer Science Fudan University Shanghai China School of Computer and Software Engineering Xihua University Chengdu China School of Transportation and Logistics Southwest Jiaotong University Chengdu China Department of Computer Science and Technology Tsinghua University Beijing China

Deep reinforcement learning (DRL) has emerged as a promising approach for robotic control, but its real-world deployment remains challenging due to its vulnerability to environmental perturbations. Existing white-box adversarial attack methods, adapted from supervised learning, fail to effectively target DRL agents as they overlook temporal dynamics and indiscriminately perturb all state dimensions, limiting their impact on long-term rewards. To address these challenges, we propose the Adaptive Gradient-Masked Reinforcement (AGMR) Attack, a white-box attack method that combines DRL with a gradient-based soft masking mechanism to dynamically identify critical state dimensions and optimize adversarial policies. AGMR selectively allocates perturbations to the most impactful state features and incorporates a dynamic adjustment mechanism to balance exploration and exploitation during training. Extensive experiments demonstrate that AGMR outperforms state-of-the-art adversarial attack methods in degrading the performance of the victim agent and enhances the victim agent’s robustness through adversarial defense mechanisms. Copyright © 2025, The Authors. All rights reserved.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

A Comparative Analysis of Goal-Oriented Requirements engineering and Model-Based Systems engineering Frameworks for Managing Requirements of Systems of Systems

A Comparative Analysis of Goal-Oriented Requirements Enginee...

引用

Information technology (ACIT)

作者： Suhair AlHajHassan Samer Murrar Ahmad Samhan Mohammed Odeh Ali Elrashidi Software Engineering Department Applied Science Private University Amman Jordan Computer Science Department Applied Science Private University Amman Jordan Software Engineering Department Zarqa University Zarqa Jordan Global Academy for Digital Health Bristol United Kingdom Department of Electrical Engineering University of Business and Technology Jeddah Saudi Arabia

ISBN: (数字)9798331540012

ISBN: (纸本)9798331540029

Goal-oriented requirements engineering (GORE) for Systems of Systems (SoS) includes combining individual operational systems local goals to achieve higher-level goals. GORE offers a structured approach to managing complex requirements, ensuring that strategic goals are translated into operational tasks. This paper provides a review of GORE frameworks, including those incorporating Model-Based Systems engineering (MBSE), that could be used in the management of complex Systems of Systems. The paper analyzes recent GORE frameworks such as CGS4Adaptation which combines Goals and SysML for managing adaptive Socio-Cyber-Physical Systems (SCPSs); GORE-based approach to Energy Management Systems (EnMS); Model-Based and Goal-Oriented Approach for the conceptual design of smart grid services; GORE and reference architecture approach for microgrid systems; and Adaptation-Oriented Requirement Modeling approach (ADORE). A comparative analysis is conducted to assess the extent of effectiveness these frameworks provide for improving SoS traceability, adaptability, and system design integrity. The paper concludes with key findings on the strengths and limitations of the considered frameworks, on the basis of which, major conclusions on how GORE combined with MBSE can be used for managing SoS requirements in Smart Grid (SG) and socio-cyber-physical systems could be drawn. This review paper also contributes to the requirements engineering domain by outlining effective strategies for designing and managing complex, adaptive Systems of Systems.

关键词： Adaptation models Analytical models Adaptive systems Reviews Microgrids Smart grids Requirements engineering Information technology System analysis and design System of systems

来源：评论

学校读者我要写书评

暂无评论

Lossless and Privacy-Preserving Graph Convolution Network for Federated Item Recommendation

arXiv

引用

arXiv 2024年

作者： Wu, Guowei Pan, Weike Yang, Qiang Ming, Zhong College of Computer Science and Software Engineering Shenzhen University Shenzhen China WeBank AI Lab WeBank China Hong Kong University of Science and Technology Hong Kong Shenzhen China

Graph neural network (GNN) has emerged as a state-of-the-art solution for item recommendation. However, existing GNN-based recommendation methods rely on a centralized storage of fragmented user-item interaction sub-graphs and training on an aggregated global graph, which will lead to privacy concerns. As a response, some recent works develop GNN-based federated recommendation methods by exploiting decentralized and fragmented user-item sub-graphs in order to preserve user privacy. However, due to privacy constraints, the graph convolution process in existing federated recommendation methods is incomplete compared with the centralized counterpart, causing a degradation of the recommendation performance. In this paper, we propose a novel lossless and privacypreserving graph convolution network (LP-GCN), which fully completes the graph convolution process with decentralized user-item interaction sub-graphs while ensuring privacy. It is worth mentioning that its performance is equivalent to that of the non-federated (i.e., centralized) counterpart. Moreover, we validate its effectiveness through both theoretical analysis and empirical studies. Extensive experiments on three real-world datasets show that our LP-GCN outperforms the existing federated recommendation methods. The code will be publicly available once the paper is accepted. Copyright © 2024, The Authors. All rights reserved.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Multi-Hierarchy Metamorphic Testing for Hyphenated Words in Machine Translation

Multi-Hierarchy Metamorphic Testing for Hyphenated Words in ...

引用

Asia-Pacific Conference on software engineering

作者： Rui Zhu Chuanqi Tao Jerry Gao College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics Nanjing China Ministry Key Laboratory for Safety-Critical Software Development and Verification Nanjing University of Aeronautics and Astronautics Nanjing China State Key Laboratory for Novel Software Technology Nanjing University Nanjing China Computer Engineering Department San Jose State University San Jose USA

ISBN: (数字)9798331534011

ISBN: (纸本)9798331534028

With the advancement of deep neural networks, machine translation has seen rapid progress in recent years. Individuals often rely on machine translation software to facil-itate various tasks. However, the intricacies of neural networks can lead to translation errors, resulting in misunderstandings or conflicts. The most common method for testing machine translation is metamorphic testing. However, metamorphic testing at the phrase or sentence hierarchy may result in some test cases being incorrectly identified as failures. To mitigate this issue, we added the word hierarchy. We proposed a multi-hierarchy metamorphic testing method, MHT, to test machine translation. Hyphenated words as a specific format prone to translation errors, which are chosen as our research object. Based on the common notion that translations of words within the same sentence should be similar, we extract contents from different hierarchies within sentences containing hyphenated words and compare the similarity of their corresponding translations for these specific words. We conducted the experiments on 881 sentences leveraging Google Translate, Microsoft Bing Translator, and Baidu Translate, which detected 111, 91, and 111 suspicious errors with high precision (78.4 %, 82.4 %, and 81.1 %). Translation errors mainly include mis-translation, under-translation, over-translation, and non-translation.

关键词： Translation Web and internet services Artificial neural networks software Internet Machine translation Usability Testing software engineering

来源：评论

学校读者我要写书评

暂无评论

Identifying Dna-Binding Proteins Using Local Features Dpc-Pssm and Ab-Pssm with Primary Sequences Based on 2dcnn

SSRN

引用

SSRN 2024年

作者： Sikander, Rahu Rahu, Ali Ghulam Rahu, Mujeeb -Ur-Rehman Center for Computing Research Department of Computer Science and Software Engineering Jinnah University for Women Karachi Pakistan Information Technology Centre Sindh Agriculture University Sindh Tandojam Pakistan School of Information and Communication Engineering Guilin University of Electronic Technology Guilin China

DBPs, also known as DNA-binding proteins, play a crucial role in the evolutionary and genetic mechanisms of humans. Understanding the features of DNA-binding peptides might develop our comprehension of protein roles inside cellular genetic processes. Investigation on predicting the function of DNA-binding proteins can advance the study of drug proteins and facilitate the development of computer-assisted medications. Deep learning methods have become the major approach for protein prediction in recent years. While current approaches can yield impressive expect performance, further research is necessary to enhance this performance. This work proposed the prediction of DNA-binding proteins using two-dimensional Convolutional Neural Network (CNN) named 2DCNN-DBP. The prominent characteristics are obtained through innovative techniques, specifically position specific scoring matrix-dipeptide composition dipeptide composition (PSSM-DPC), Second, we employed Average Block novel approach to representing proteins using position-specific scoring matrices (AB-PSSM) in images. The DPC-PSSM feature extraction approach achieved a prediction accuracy of 0.9309% for the validation set, which is notably superior to the AB-PSSM. Based on the analysis, DPC-PSSM shown superior performance compared to the other two feature selection approaches in classification using 2DCNN. Specifically, AB-PSSM attained a higher accuracy level of 73.50% using independent test datasets and a training dataset accuracy score of 87.52%. The results demonstrate the superior performance of our innovative predictor compared to previous studies. Utilizing PSSM-DPC could lead to the development of more effective therapeutic approaches for the treatment of life-threatening diseases. © 2024, The Authors. All rights reserved.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

A Framework for Systematic Classification of Assets for Security Testing

引用

computers, Materials & Continua 2021年第1期66卷 631-645页

作者： Sadeeq Jan Omer Bin Tauqeer Fazal Qudus Khan George Tsaramirsis Awais Ahmad Iftikhar Ahmad Imran Maqsood Niamat Ullah National Center for Cyber Security Department of CS&ITUniversity of Engineering&TechnologyPeshawarPakistan Department of Information Technology FCITKing Abdulaziz UniversityJeddahSaudi Arabia Dipartimento di Informatica(DI) UniversitàDegli Studi di Milano StataleVia Celoria 18MilanoItaly Department of Computer Science&IT University of Engineering&TechnologyPeshawarPakistan Department of Software Engineering University of Engineering&TechnologyMardanPakistan University of Buner BunerPakistan

Over the last decade,a significant increase has been observed in the use of web-based Information systems that process sensitive information,e.g.,personal,financial,*** this increased use,the security of such systems became a crucial aspect to ensure safety,integrity and authenticity of the *** achieve the objectives of data safety,security testing is ***,with growth and diversity of information systems,it is challenging to apply security testing for each and every ***,it is important to classify the assets based on their required level of security using an appropriate *** this paper,we propose an asset security classification technique to classify the System Under Test(SUT)based on various factors such as system exposure,data criticality and security *** perform an extensive evaluation of our technique on a sample of 451 information ***,we use security testing on a sample extracted from the resulting prioritized systems to investigate the presence of *** technique achieved promising results of successfully assigning security levels to various assets in the tested environments and also found several vulnerabilities in them.

关键词： Security security testing privacy asset classification

来源：评论

学校读者我要写书评

暂无评论

Publisher Correction: Twinenet: coupling features for synthesizing volume rendered images via convolutional encoder–decoders and multilayer perceptrons

引用

The Visual computer 2024年第2期41卷 1409-1411页

作者： Luo, Shengzhou Xu, Jingxing Dingliana, John Wei, Mingqiang Han, Lu He, Lewei Pan, Jiahui School of Computer Science Guangdong University of Education Guangzhou China School of Software South China Normal University Foshan China School of Computer Science and Statistics Trinity College Dublin Dublin Ireland School of Computer Science and Technology Nanjing University of Aeronautics and Astronautics Nanjing China School of Engineering Guangzhou College of Technology and Business Guangzhou China Pazhou Lab Guangzhou China

来源：评论

学校读者我要写书评

暂无评论

Boosting the Prediction of Brain Tumor Using Two Stage BiGait Architecture

Boosting the Prediction of Brain Tumor Using Two Stage BiGai...

引用

Proceedings of the Digital Image Computing: Technqiues and Applications (DICTA)

作者： Saif-ur-Rehman Khan Zia Khan Md Zakir Hossain Nicanor Mayumu Farhana Yasmin Younas Aziz School of Computer Science and Engineering Central South University Changsha China School of Elec Eng Comp and Math Sci (EECMS) Curtin University Perth Australia Department of Computer and Software Nanjing University of information Science and Technology Nanjing

ISBN: (数字)9798350379037

ISBN: (纸本)9798350379044

Deep learning (DL) techniques hold immense promise for revolutionizing medical diagnostics, including brain tumor detection. Detecting malignancies in the brain is fraught with challenges that carry critical implications for accurate and timely diagnosis. Early detection is paramount, and our paper presents a novel approach to address this issue. We introduce the BiGait ensemble transfer learning (TL) architecture tailored for brain tumor classification tasks. Our proposed methodology is a two-stage process that harnesses the power of TL. In the initial phase, we employ two established models, ResNet50 and EfficientNetB1, and fine-tune them using the Kaggle multiclass dataset. This includes the incorporation of supplementary feature layers. We also leverage a stack ensemble solution to combine these feature layers, enhancing the model's overall predictive capabilities. Our approach is designed to shift the input distribution positively, effectively mitigating overfitting and reducing hardware overhead. To validate the effectiveness of our method, we conducted extensive experiments and evaluation. The dataset utilized in this work, publicly available on Kaggle contains 3,264 brain MRIs categorized into four groups: normal (500 images), meningioma (937 images), glioma (926 images), and pituitary tumor (901 images). The experimental results demonstrate that our model surpasses traditional single-model approaches, achieving an impressive accuracy rate of 96% and exhibiting superior generalization capabilities. This advancement in brain tumor classification holds great promise for early diagnosis and improved patient outcomes.

关键词： Accuracy Transfer learning Brain tumors computer architecture Predictive models Brain modeling Reliability Medical diagnosis Residual neural networks Overfitting

来源：评论

学校读者我要写书评

暂无评论

Digital forensics for the socio-cyber world (DF-SCW): A novel framework for deepfake multimedia investigation on social media platforms

引用

Egyptian Informatics Journal 2024年 27卷

作者： Ayub Khan, Abdullah Chen, Yen-Lin Hajjej, Fahima Ahmed Shaikh, Aftab Yang, Jing Soon Ku, Chin Yee Por, Lip Department of Computer Science and Information Technology Benazir Bhutto Shaheed University Lyari Sindh Karachi75660 Pakistan Department of Computer Science Sindh Madressatul Islam University Sindh Karachi74000 Pakistan Department of Computer Science and Information Engineering National Taipei University of Technology Taipei106344 Taiwan Department of Software Engineering College of Computer and Inf. Sci. Princess Nourah bint Abdulrahman University P.O. Box 84428 Riyadh11671 Saudi Arabia Department of Computer System and Technology Faculty of Computer Science and Information Technology Universiti Malaya Kuala Lumpur50603 Malaysia Department of Computer Science Universiti Tunku Abdul Rahman Kampar31900 Malaysia

Owing to the major development of social media platforms, the usage of technological adaptation increases by means of editing software tools. Posting media in social communication environments has become one of our common daily routines. Before posting, various editing generators are used to manipulate pixel values, such as for enhancing brightness and contrast. Undoubtedly, this software helps bring posting media from ordinary to outstanding. But such a type of editing crosses the line in terms of creating fakes—anything that comes from anywhere and does not retain its originality anyway. It poses a series of issues in the process of multimedia forensics investigation and chain of custody. In order to restrict the attempts at deep faking and make the investigation hierarchy more effective, efficient, and reliable in the socio-cyber space (SCS), this paper presents a novel framework called DF-SCW. A digital forensics-enabled socio-cyber world with artificial intelligence (AI), especially deep neural networks (DNNs), for detecting and analyzing deep fake media investigations on social media platforms. It compares pixels with their neighboring values in the same media (such as images and videos) to identify information about the original one. There is a media flag designed to filter out malicious and dangerous attempts, like a powerful leader declaring war. Putting flags on such fakes helps digital investigators resist sharing the posts. In addition, the other prospect of this research is to make the digital forensics ecosystem more appropriate to take qualitative judgments in real-time while media is uploaded on social media platforms. The simulation of the proposed DF-SCW is tested on three different platforms, such as Instagram, Facebook, and Twitter. Through the experiment, the DF-SCW outperformed in terms of detection, identification, and analysis of deepfake media by an increased rate of 3.77%. © 2024

关键词： Social networking (online)

来源：评论

学校读者我要写书评

暂无评论

Integrating Post-Quantum Cryptography Plugins for IPsec Offloads to Data Processing Units in the Cloud-Edge Continuum

Integrating Post-Quantum Cryptography Plugins for IPsec Offl...

引用

International Conference on Network Protocols

作者： Abraham Cano Carlos Rubio Garcia Raphaël Frantz Idelfonso Tafur Monroy José Luis Imaña Juan José Vegas Department of Electrical Engineering Eindhoven University of Technology Eindhoven The Netherlands Department of Computer Architecture and Automation Complutense University of Madrid Madrid Spain Software Architecture NVIDIA corporation Yokneam Israel

ISBN: (数字)9798350351712

ISBN: (纸本)9798350351729

The imminent advent of Quantum computers poses a significant threat to the cryptographic algorithms supporting the public key infrastructure (PKI) of widely used communication protocols. High Performance Computing (HPC) data centers among other interested parties are well aware of the catastrophic consequences quantum attacks could have on their PKI and are consequently transitioning to Post-Quantum Cryptographic (PQC) methods, despite the substantial overhead this introduces for handling incoming network packets. This work addresses the transition to PQC within the context of the Cloud-Edge Continuum by integrating the Open Quantum Safe (OQS) library into the accelerated strongSwan developed by Mellanox for Data Processing Units (DPUs). This integration offloads cryptographic operations from central servers to data DPUs distributed across the cloud-edge continuum. Our solution ensures quantum security by providing PQ authentication through CRYSTALS-Dilithium or CRYSTALS-FALCON, PQ key exchanges via CRYSTALS-Kyber, and confidential data transmission using AES-256. Additionally, the deployment of this implementation on DPUs helps reduce the computational load on both HPC data centers and edge devices, promoting more efficient and secure operations across the entire cloud-edge continuum.

关键词： Resistance Data centers Quantum computing Protocols Public key Throughput Data processing Libraries Cryptography Servers

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：