检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Kumar, Jahnavi Janapati, Venkata Lakshmana Sasaank Tanguturi, Mokshith Reddy Chimalakonda, Sridhar Research in Intelligent Software & Human Analytics Lab Department of Computer Science and Engineering Indian Institute of Technology Tirupati India

Owing to the rapid evolution of technologies and project requirements, organizations need to upgrade the code base in their software projects to a new version of the programming language or even translating to an entirely new one. However, code translation is resource-intensive and requires expertise in both the source and target languages. While researchers have made progress in automating translations between legacy and modern languages, recent work has increasingly turned to pre-trained Large Language Models (LLMs) to translate efficiently. Given the proprietary nature of code, organizations prefer finetuning LLMs locally rather than relying on external APIs. This is one of the first empirical studies that proposes a Federated LLM-based approach for code translation. The proposed approach enables clients to jointly train a code translator without sharing sensitive data. This study demonstrates that participants can collaboratively develop a FedLLM for efficient code translation (particularly C# to Java and vice-versa) with superior results (more than 40% improvement in CodeLLaMA’s CodeBLEU score) compared to individual client models. Our findings indicate that FedLLM offers a collaborative approach to code translation and could serve as a promising direction for future research in this field. © 2025, CC BY.

关键词： Program translators

来源：评论

学校读者我要写书评

暂无评论

Special issue on advances in techniques for assessment performance portability of HPC applications

引用

Future Generation computer Systems 2025年 171卷

作者： Marowka, Ami Stpiczyński, Przemyslaw Wyrzykowski, Roman Parallel Research Lab Petach Tikva49729 Israel Institute of Computer Science Maria Curie-Sklodowska University Lublin20-033 Poland Department of Computer Science Czestochowa University of Technology Czestochowa42-201 Poland

This special issue aims to present new developments and advances in techniques for assessment performance portability of high performance computing applications. It contains revised and extended versions of selected papers presented at the 10th Workshop on Language-Based Parallel programming Models, WLPP 2024, which was a part of 15th International Conference on Parallel Processing and Applied Mathematics, PPAM 2024, held on September 8–11, 2024, in Ostrava, Czech Republic. © 2025

关键词： HPC applications Parallel programming languages Performance portability

来源：评论

学校读者我要写书评

暂无评论

Analyzing Digital Image Anti-Forensics Techniques and Countermeasures 27

Analyzing Digital Image Anti-Forensics Techniques and Counte...

引用

27th International Conference on Advanced Communications technology, ICACT 2025

作者： Agarwal, Saurabh Kumar, Rajeev Devi, Abha Jung, Ki-Hyun Department of Information and Communication Engineering Yeungnam University Gyeongsan38541 Korea Republic of Blockchain Technology Research Lab Department of Computer Science and Engineering Delhi Technological University New Delhi110042 India Department of Software Convergence Andong National University Gyeongbuk36729 Korea Republic of College Uttar Pradesh Sikandrabad India

ISBN: (纸本)9791188428137

With the increasing use of digital media, digital forensics has become a crucial method for ascertaining authenticity and detecting manipulations in images. However, intentional anti-forensic manipulations to hide forensic clues have made verification more difficult. The efforts to develop countermeasures against anti-forensics have contributed to the evolution toward robust techniques in the field of anti-forensics;hence, the development of anti-forensic methods and their respective countermeasures will remain continuous. This work provides a scientometric analysis, a powerful tool for the study of the growth of research output in accordance with time and citation, author, organizational, and keyword co-occurrence analysis. It enhances state-of-the-art analysis by underlining highly influential authors, organizations, and works and stipulates knowledge gaps. This would consequently provide a platform for building a community where insights and inclusiveness among researchers, industry practitioners, and policymakers would all come together to guide their strategies and decisions for innovation in this dynamic field. Copyright 2025 Global IT Research Institute (GIRI). All rights reserved.

关键词： Fake detection

来源：评论

学校读者我要写书评

暂无评论

Non-Uniform Illumination Attack for Fooling Convolutional Neural Networks

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2025年

作者： Jain, Akshay Dubey, Shiv Ram Singh, Satish Kumar Santosh, K.C. Chaudhuri, Bidyut Baran Indian Institute of Information Technology Allahabad Computer Vision and Biometrics Lab Department of Information Technology Uttar Pradesh Prayagraj211015 India University of South Dakota AI Research Lab Department of Computer Science VermillionSD57069 United States Indian Statistical Institute Computer Vision and Pattern Recognition Unit Kolkata700108 India

Convolutional Neural Networks (CNNs) have made remarkable strides;however, they remain susceptible to vulnerabilities, particularly to image perturbations that humans can easily recognize. This weakness, often termed as 'attacks,' underscores the limited robustness of CNNs and the need for research into fortifying their resistance against such manipulations. This study introduces a novel Non-Uniform Illumination (NUI) attack technique, where images are subtly altered using varying NUI masks. Extensive experiments are conducted on widely-accepted datasets including CIFAR10, TinyImageNet, CalTech256 and NWPU-RESISC45 focusing on image classification with 12 different NUI masks. The resilience of VGG, ResNet, MobilenetV3-small, InceptionV3 and efficientNet b0 models against NUI attacks are evaluated. Our results show a substantial decline in the CNN models' classification accuracy when subjected to NUI attacks, due to changes in the image pixel value distribution, indicating their vulnerability under non-uniform illumination. To mitigate this, a defense strategy is proposed, including NUI-attacked images, generated through the new NUI transformation, into the training set. The results demonstrate a significant enhancement in CNN model performance when confronted with perturbed images affected by NUI attacks. This strategy seeks to bolster CNN models' resilience against NUI attacks. A comparative study with other attack techniques shows the effectiveness of the NUI attack and defense technique. © 2020 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Enhancing LLM Reliability via Explicit Knowledge Boundary Modeling

arXiv

引用

arXiv 2025年

作者： Zheng, Hang Xu, Hongshen Liu, Yuncong Chen, Lu Fung, Pascale Yu, Kai X-LANCE Lab Department of Computer Science and Engineering Shanghai Jiao Tong University China Hong Kong University of Science and Technology Hong Kong

Large language models (LLMs) frequently hallucinate due to misaligned self-awareness, generating erroneous outputs when addressing queries beyond their knowledge boundaries. While existing approaches mitigate hallucinations via uncertainty estimation or query rejection, they suffer from computational inefficiency or sacrificed helpfulness. To address these issues, we propose the Explicit Knowledge Boundary Modeling (EKBM) framework, integrating fast and slow reasoning systems to harmonize reliability and usability. The framework first employs a fast-thinking model to generate confidence-labeled responses, enabling immediate use of high-confidence outputs. For uncertain predictions, a slow refinement model conducts targeted reasoning to improve accuracy. To align model behavior with our proposed object, we propose a hybrid training pipeline, enhancing self-awareness without degrading task performance. Evaluations on dialogue state tracking tasks demonstrate that EKBM achieves superior model reliability over uncertainty-based baselines. Further analysis reveals that refinement substantially boosts accuracy while maintaining low computational overhead. Our work establishes a scalable paradigm for advancing LLM reliability and balancing accuracy and practical utility in error-sensitive applications. Copyright © 2025, The Authors. All rights reserved.

关键词： Reliability analysis

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-Driven Throughput Maximization in Covert Communication for UAV-RIS Cognitive Systems

IEEE Open Journal of the Communications Society

引用

IEEE Open Journal of the Communications Society 2025年 6卷 4140-4155页

作者： Vo, Van Nhan Long, Nguyen Quoc Dang, Viet-Hung Ho, Tu Dac Tran, Hung Chatzinotas, Symeon Tran, Dinh-Hieu Sanguanpong, Surasak So-In, Chakchai Faculty of Information Technology Duy Tan University Da Nang550000 Viet Nam Institute of Research and Development Duy Tan University Da Nang550000 Viet Nam Department of Information Security and Communication Technology Faculty of Information Technology and Electrical Engineering Norwegian University of Science and Technology - NTNU Norway DATCOM Lab Faculty of Data Science and Artificial Intelligence College of Technology National Economics University Hanoi12116 Viet Nam University of Luxembourg Luxembourg Department of Computer Engineering Faculty of Engineering Kasetsart University Bangkok10900 Thailand College of Computing Khon Kaen University Khon Kaen40002 Thailand

This paper examines a cognitive radio (CR) nonorthogonal multiple access (NOMA) system in which an unmanned aerial vehicle equipped with a reconfigurable intelligent surface (UAV-RIS) plays two roles: relaying and friendly jamming. The communication protocol has two phases. The first is an energy harvesting phase in which the UAV harvests radio frequency energy from a power beacon. A secondary transmitter (ST) simultaneously sends superimposed signals to secondary receivers (SRs) (a public SR and a covert SR) via NOMA with the assistance of the UAV-RIS. Then, a UAV warden and a UAV jammer launch a cooperative attack, in which the first adversary wiretaps the signals from the ST and UAV-RIS, whereas the second interferes with the SRs to force the ST to increase its transmit power. For improved secrecy, the UAV-RIS uses its harvested energy to combat the UAV warden. For this system, the secrecy performance is evaluated on the basis of the concept of covert communication. In particular, optimization algorithms are employed to maximize the covert SR throughput under outage probability and security constraints. A deep neural network model is subsequently trained to discover the relationships between the environmental parameters and optimized parameters to enable rapid adaptation to environmental conditions. © 2020 IEEE.

关键词： Drones

来源：评论

学校读者我要写书评

暂无评论

Beyond Vision: How Large Language Models Interpret Facial Expressions from Valence-Arousal Values

arXiv

引用

arXiv 2025年

作者： Mehra, Vaibhav laban, Guy Gunes, Hatice HEI-Lab Universidade Lusófona Lisbon Portugal Department of Computer Science and Technology University of Cambridge Cambridge United Kingdom

Large Language Models primarily operate through text-based inputs and outputs, yet human emotion is communicated through both verbal and non-verbal cues, including facial expressions. While Vision-Language Models analyze facial expressions from images, they are resource-intensive and may depend more on linguistic priors than visual understanding. To address this, this study investigates whether LLMs can infer affective meaning from dimensions of facial expressions—Valence-Arousal values, structured numerical representations, rather than using raw visual input. VA values were extracted using Facechannel from images of facial expressions and provided to LLMs in two tasks: (1) categorizing facial expressions into basic (on the IIMI dataset) and complex emotions (on the Emotic dataset) and (2) generating semantic descriptions of facial expressions (on the Emotic dataset). Results from the categorization task indicate that LLMs struggle to classify VA values into discrete emotion categories, particularly for emotions beyond basic polarities (e.g., happiness, sadness). However, in the semantic description task, LLMs produced textual descriptions that align closely with human-generated interpretations, demonstrating a stronger capacity for free-text affective inference of facial expressions. © 2025, CC BY.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

GBSVR: Granular Ball Support Vector Regression

arXiv

引用

arXiv 2025年

作者： Rastogi, Reshma Bisht, Ankush Kumar, Sanjay Chandra, Suresh MLSI Lab Department of Computer Science South Asian University New Delhi India Department of Computer Science Deshbandhu College University of Delhi New Delhi India Department of Mathematics Indian Institute of Technology Delhi New Delhi India

Support Vector Regression (SVR) and its variants are widely used to handle regression tasks, however, since their solution involves solving an expensive quadratic programming problem, it limits its application, especially when dealing with large datasets. Additionally, SVR uses an ϵ-insensitive loss function which is sensitive to outliers and therefore can adversely affect its performance. We propose Granular Ball Support Vector Regression (GBSVR) to tackle problem of regression by using granular ball concept. These balls are useful in simplifying complex data spaces for machine learning tasks, however, to the best of our knowledge, they have not been sufficiently explored for regression problems. Granular balls group the data points into balls based on their proximity and reduce the computational cost in SVR by replacing the large number of data points with far fewer granular balls. This work also suggests a discretization method for continuous-valued attributes to facilitate the construction of granular balls. The effectiveness of the proposed approach is evaluated on several benchmark datasets and it outperforms existing state-of-the-art approaches. © 2025, CC BY.

关键词： Wind forecasting

来源：评论

学校读者我要写书评

暂无评论

EEG VMAC Toolbox: A User-Friendly Open-Source Toolbox for EEG Signals Visualization Manipulation Analysis and Classification

引用

Procedia computer science 2025年 258卷 1062-1080页

作者： Gopal Chandra Jana Abhishek Karmakar Anupam Agrawal Interactive Technologies & Multimedia Research (ITMR) Lab Department of Information Technology Indian Institute of Information Technology Allahabad Prayagraj – 211015 Uttar Pradesh India Indian Institute of Information Technology Kalyani Department of Computer Science and Engineering Kalyani – 741235 West Bengal India

Electroencephalography (EEG) is a well-known, non-invasive method for monitoring and recording electrical activities of the human brain. Problem: EEG signal visualization, manipulation, analysis, and classification are essential for clinical experts, doctors, and researchers to make certain decisions. So, there is a need for a toolbox that can provide such functionalities with a user-friendly graphical user interface (GUI); availability may be commercial or open-source. Aim: This paper describes the proposed and developed open-source EEG VMAC Toolbox, which provides an interface with features including a series of state-of-the-art methods for EEG signal analysis. Method: The main menu options of EEG VMAC Toolbox are - 1) File, 2) Signal Visualization, 3) Filtering, 4) Signal Decomposition, 5) Feature Reduction, 6) Feature Extraction, 7) label, 8) Classification Models, and 9) Help. Each menu of the toolbox contains several functionalities. In addition to these nine menus, a file conversion option is available at the bottom of the toolbox. EEG VMAC Toolbox integrates all major state-of-the-art functionalities for EEG signal visualization, manipulation, analysis, and classification, which would be a valuable addition to the current literature. Results and Findings: The EEG VMAC Toolbox has been developed using Python programming language and tested over the CHB-MIT EEG Scalp EEG dataset, a benchmark dataset for seizure detection. So, this toolbox has a provision to bring psychologists, neuroscientists, clinical experts, and EEG researchers on the same platform to pursue extensive investigation and research for better reach.

关键词： Electroencephalogram (EEG) EEG toolbox EEG signal visualization toolbox EEG signal analysis tool Open-source toolbox Python EEG toolbox

来源：评论

学校读者我要写书评

暂无评论

Generative Adversarial Networks for Dynamic Malware Behavior: A Comprehensive Review, Categorization, and Analysis

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2025年

作者： Gebrehans, Ghebrebrhan Ilyas, Naveed Eledlebi, Khouloud Lunardi, Willian T. Andreoni, Martin Yeun, Chan Yeob Damiani, Ernesto Lab Khalifa University of Science and Technology Abu Dhabi United Arab Emirates University of California Riverside United States Khalifa University of Science and Technology Department of Electrical Engineering and Computer Science Abu Dhabi United Arab Emirates Abu Dhabi United Arab Emirates Khalifa University Department of Electrical Engineering and Computer Science Abu Dhabi United Arab Emirates Khalifa University of Science and Technology Center for Secure Cyber-physical Systems Abu Dhabi United Arab Emirates University of Milan Dept. of Computer Science Italy

This paper highlights the critical role of Machine Learning (ML) in combating the dynamic nature of cybersecurity threats. Unlike previous studies focusing mainly on static analysis, this work surveys the literature on dynamic analysis-based malware generation and detection. The study addresses the complexities of applying GANs to tabular data with heavy-tailed and multimodal distributions. It also examines the challenges of generating sequential malware behavior data and categorizes GAN-based models and their primary use cases. Furthermore, the paper evaluates adversarial losses and their limitations in generating dynamic malware behavior. Finally, it identifies existing metrics to assess GAN generalization in malware research and suggests future research directions based on identified limitations. © 2020 IEEE.

关键词： Generative adversarial 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：