检索结果-内蒙古大学图书馆

17th International Conference on COMmunication Systems and NETworkS, COMSNETS 2025

作者： Chaudhuri, Arunava Shukla, Shubhi Bhattacharya, Sarani Mukhopadhyay, Debdeep Indian Institute of Technology Kharagpur Department of Computer Science and Engineering Kharagpur India Indian Institute of Technology Kharagpur Centre for Computational and Data Sciences Kharagpur India

ISBN: (纸本)9798331531195

With the rapid advancement of machine learning (ML) models and their widespread application across various sectors such as intrusion detection, medical diagnosis, natural language processing, and autonomous driving, these technologies have achieved remarkable success. However, this progress has also raised significant concerns about ensuring the security of ML models and protecting both private training data and model outputs from getting exposed in a shared cloud environment. To address these challenges, researchers have proposed various methodologies to create privacy-preserving, secure, and trustworthy model execution environments to prevent adversarial attacks. This study provides a comprehensive review of Trusted Execution Environment (TEE) implementations across different hardware accelerators. It also offers an overview of modern techniques for preserving privacy and security in execution environments, while identifying critical research gaps that require attention. In essence, this survey is an important resource for researchers, providing insights into recent methodologies and guiding them to focus on pressing research challenges. © 2025 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Spatio-Temporal NDVI Prediction for Rice Crop

引用

SN Computer science 2025年第3期6卷 1-13页

作者： Dey, Anamika Sarkar, Somrita Mondal, Arijit Mitra, Pabitra Centre for Computational and Data Sciences Indian Institute of Technology Kharagpur West Bengal Kharagpur 721302 India Department of Computer Science and Engineering Indian Institute of Technology Patna Bihar Bihta 801106 India Department of Computer Science and Engineering Indian Institute of Technology Kharagpur West Bengal Kharagpur 721302 India

Accurately predicting the Normalized Difference Vegetation Index (NDVI) is crucial for effective agricultural planning and decision-making. Despite much literature on NDVI prediction, most of these methods do not consider spatial-temporal variations. Generating a dataset for predicting NDVI is another major bottleneck, as such data needs to be collected over an extensive period. In this work, we develop a semi-automated framework to generate a comprehensive time-series dataset after necessary preprocessing using the information from Sentinel-2, POWER data Access Viewer, and the Google Earth Engine (GEE). We propose a deep learning-based model to predict NDVI based on its historical time series and meteorological and spatial information for the rice crop in India. Here, we use a Long Short-Term Memory (LSTM)-based model augmented with spatial information to predict the NDVI of the near-about region for which the data is unavailable. We compared the proposed approach with a method that uses a weighted average of nearest neighbors prediction. Also, we compare the proposed method with existing statistical techniques such as the Autoregressive (AR), AutoRegressive Integrated Moving Average (ARIMA), and Seasonal AutoRegressive Integrated Moving Average (SARIMA). Experimental results show that our methodology outperforms other techniques by a margin of 4% to 8%. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2025.

关键词： Autoregressive integrated moving average Long short-term memory Normalized difference vegetation index Seasonal autoregressive integrated moving average Sentinel-2 Weighted average of nearest neighbors prediction

来源：评论

学校读者我要写书评

暂无评论

Guardian of the Ensembles: Introducing Pairwise Adversarially Robust Loss for Resisting Adversarial Attacks in DNN Ensembles

Guardian of the Ensembles: Introducing Pairwise Adversariall...

引用

2025 IEEE/CVF Winter Conference on Applications of Computer Vision, WACV 2025

作者： Shukla, Shubhi Dalui, Subhadeep Alam, Manaar Datta, Shubhajit Mondal, Arijit Mukhopadhyay, Debdeep Chakrabarti, Partha Pratim Centre for Computational and Data Sciences Iit Kharagpur India Iit Kharagpur Computer Science and Engineering Department India Center for Cyber Security New York University Abu Dhabi United Arab Emirates Iit Kharagpur Department of Artificial Intelligence India Iit Patna Computer Science and Engineering Department India

ISBN: (纸本)9798331510831

Adversarial attacks rely on transferability, where an adversarial example (AE) crafted on a surrogate classifier tends to mislead a target classifier. Recent ensemble methods demonstrate that AEs are less likely to mislead multiple classifiers in an ensemble. This paper proposes a new ensemble training using a Pairwise Adversarially Robust Loss (PARL) that by construction produces an ensemble of classifiers with diverse decision boundaries. PARL utilizes outputs and gradients of each layer with respect to network parameters in every classifier within the ensemble simultaneously. PARL is demonstrated to achieve higher robustness against black-box transfer attacks than previous ensemble methods as well as adversarial training without adversely affecting clean example accuracy. Extensive experiments using standard Resnet20, WideResnet28-10 classifiers demonstrate the robustness of PARL against state-of-the-art adversarial attacks. While maintaining similar clean accuracy and lesser training time, the proposed architecture has a 24.8% increase in robust accuracy (= 0.07) from the state-of-the art method. Code is available at: https://***/shubhishukla10/PARL © 2025 IEEE.

关键词： adversarial attack decision-boundary diversity defense ensemble models

来源：评论

学校读者我要写书评

暂无评论

Fuzzychain: An equitable consensus mechanism for blockchain networks

引用

Journal of Network and Computer Applications 2025年 241卷

作者： Ramos-Cruz, Bruno Andreu-Perez, Javier Quesada-Real, Francisco J. Martínez, Luis Computer Science Department University of Jaen Jaen Jaen23071 Spain Centre for Computational Intelligencer School of Computer Science and Electronic Engineering University of Essex Colchester United Kingdom Andalusian Research Institute in Data Science and Computational Intelligence Jaen Jaen23071 Spain

Blockchain technology has become a trusted method for establishing secure and transparent transactions through a distributed, encrypted network. The operation of blockchain is governed by consensus algorithms, among which Proof of Stake (PoS) is popular yet has its drawbacks, notably the potential for centralising power in nodes with larger stakes or higher rewards. Our proposed novel solution, Fuzzychain, leverages fuzzy sets to define stake semantics, introducing a degree of softness in validator selection. This approach mitigates rigid threshold-based decision-making by allowing gradual transitions between stake levels, reducing sharp disparities among validators. By incorporating this enhanced stake evaluation, Fuzzychain promotes a more adaptive and distributed selection process, ensuring a fairer and more inclusive blockchain network. A thorough assessment of a real-time multi-agent blockchain system to examine validator selection and reduce inequality, promoting a more equitable distribution of stakes among validators compared to other consensus mechanisms. This fosters a more inclusive selection process and a more equitably distributed network. © 2025 The Authors

关键词： Consensus algorithm

来源：评论

学校读者我要写书评

暂无评论

Minimal Counters, Maximum Insight: Simplifying System Performance With HPC Clusters for Optimized Monitoring

IEEE Computer Architecture Letters

引用

IEEE Computer Architecture Letters 2025年第01期24卷 177-180页

作者： Shukla, Shubhi Singh, Abhijeet Chakraborty, Rajdeep Chakraborty, Anirban Rathod, Tejas Mumbaikar, Harshal Munigala, Manoj Kumar Madhusudhan, K.N. Mitra, Pabitra Mukhopadhyay, Debdeep Indian Institute of Technology Kharagpur Centre for Computational Data Sciences India Indian Institute of Technology Kharagpur Computer Science and Engineering Department India Intel Corporation Bangalore India

As computer systems become more complex, evaluating performance requires tracking various hardware performance counters that capture the system's internal activities. While these counters provide valuable insights, their growing number makes it challenging to identify the most relevant ones for performance analysis. In this paper, we investigate the correlation between performance counter values and overall system performance, while also exploring the inter-correlation between different counters. Our findings demonstrate that specific counters are strongly correlated with key performance metrics and that significant redundancy exists among counters. By leveraging these relationships, we propose a method for selecting a small, representative set of performance counters. This streamlined set can further be used to accurately predict performance score across various workloads and system configurations. © 2002-2011 IEEE.

关键词： Complex networks

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of Parametric and Non-Parametric Machine Learning Models for CO2 Solubility Estimation

Comparative Analysis of Parametric and Non-Parametric Machin...

引用

2025 International Petroleum Technology Conference, IPTC 2025

作者： Darkwah-Owusu, Victor Turkson, Joshua Nsiah Yusof, Muhammad Aslam Md Tackie-Otoo, Bennet Nii Sokama-Neuyam, Yen Adams Fjelde, Ingebret Gbillah, Louis Kwesi Otchere, Daniel Asante Petroleum Engineering Department Universiti Teknologi PETRONAS Malaysia Centre of Reservoir Dynamics Institute of Sustainable Energy & Resources Universiti Teknologi PETRONAS Malaysia Department of Petroleum Engineering King Fahd University of Petroleum & Minerals Saudi Arabia Department of Petroleum Engineering Kwame Nkrumah University of Science and Technology Ghana Department of Energy & Technology NORCE Norwegian Research Centre AS Stavanger Norway Institute for Computational & Data Sciences The Pennsylvania State University University ParkPA16802 United States

ISBN: (纸本)9781959025436

This study investigates the application of parametric and non-parametric supervised machine learning techniques for CO2 solubility estimation in brine. CO2 solubility in brine is crucial in estimating the CO2 storage capacity of geological formations, assessing CO2 surface mixing, and evaluating the performance of CO2-enhanced oil recovery projects. Hence this research aims to provide an alternative approach for accurate CO2 solubility prediction, critical for various applications in CO2 geo-storage and EOR projects. Independent variables including pressure (0.1-40 MPa), temperature (273-474 K), salinity (0-6 mol/kg), and salt type (NaCl, CaCl2, and MgCl2) were sourced from the credible scientific literature. To ensure data quality, a comprehensive data exploration process was conducted. Subsequently, the dataset was then split into training (70%) and testing (30%) sets for model development and evaluation. Hyperparameter tuning was employed to optimize model performance. Statistical metrics and visualizations were also used to evaluate model performance. The model reliability and the statistical validity of the dataset were assessed using William's plot. Sensitivity analysis and feature importance were also explored using correlation and model-intrinsic methods. The findings of this study showed that non-parametric models (random forest (RF) and decision tree (DT)) significantly outperformed the parametric model (multiple linear regression (MLR)). Specifically, RF and DT exhibited exceptional general behaviour and robustness, achieving an overall coefficient of determination>0.97, mean absolute error2/kg2 while MLR yielded 0.76, 0.272 mol/kg, and 0.155 mol2/kg2, respectively. This disparity is attributed to the inherent limitations of parametric models in capturing complex relationships between CO2 solubility and its influencing factors. The RF model was adjudged the best-performing model and demonstrated considerable prediction accuracy compared to the Søreide-Whi

关键词： Enhanced recovery

来源：评论

学校读者我要写书评

暂无评论

Secured and Privacy-Preserving GPU-Based Machine Learning Inference in Trusted Execution Environment: A Comprehensive Survey

Secured and Privacy-Preserving GPU-Based Machine Learning In...

引用

International Communication Systems and Networks and Workshops, COMSNETS

作者： Arunava Chaudhuri Shubhi Shukla Sarani Bhattacharya Debdeep Mukhopadhyay Department of Computer Science and Engineering Indian Institute of Technology Kharagpur Kharagpur India Centre for Computational and Data Sciences Indian Institute of Technology Kharagpur Kharagpur India

ISBN: (数字)9798331531195

ISBN: (纸本)9798331531201

关键词： Surveys Deep learning Training Privacy data privacy Training data data models Stability analysis Security Hardware acceleration

来源：评论

学校读者我要写书评

暂无评论

Synergetic effects of multiple junction and surface hydroxyl in Cu/CuO/Cu2O/TiO2 heterostructures towards highly efficient photocatalysts for hydrogen generation

引用

Materials science for Energy Technologies 2025年 8卷 131-142页

作者： Subagyo, Riki Anindika, Garcelina Rizky Aufkani, Afif Akmal Zhang, Lei Ardhyananta, Hosta Burhan, R.Y. Perry Nugraheni, Zjahra Vianita Akhlus, Syafsir Bahruji, Hasliza Prasetyoko, Didik Wellia, Diana Vanda Ivansyah, Atthar Luqman Arramel Kusumawati, Yuly Department of Chemistry Faculty of Science and Analytic Data Institut Teknologi Sepuluh Nopember Surabaya60111 Indonesia Center of Excellence Applied Physics and Chemistry Nano Center Indonesia Jl PUSPIPTEK South Tangerang Banten15314 Indonesia Department of Physics National University of Singapore Singapore117551 Singapore Department of Materials and Metallurgical Engineering Faculty of Industrial Technology and Systems Engineering Institut Teknologi Sepuluh Nopember Surabaya60111 Indonesia Centre of Advanced Material and Energy Science Universiti Brunei Darussalam Jalan Tungku Link BE 1410 Brunei Department of Chemistry Faculty of Mathematics and Natural Sciences Universitas Andalas Padang25163 Indonesia Master Program in Computational Science Faculty of Mathematics and Natural Science Institut Teknologi Bandung Jalan Ganesha No. 10 Bandung40132 Indonesia Instrumentation and Computational Physics Research Group Department of Physics Faculty of Mathematics and Natural Sciences Institut Teknologi Bandung Jalan Ganesha No.10 West Java Bandung40132 Indonesia

The implementation of titanium dioxide (TiO2) as a photocatalyst material in hydrogen (H2) evolution reaction (HER) has embarked renewed interest in the past decade. Rapid electron-hole pairs recombination and wide band gap of a photo-sensitive material of TiO2 are detrimental toward the targeted catalytical reaction. In this study, we present the rational design, fabrication, photocatalytic performance of TiO2-Cu/CuO/Cu2O heterostructures (CuTi) using viable chemical reduction method. The Z-scheme and S-scheme are succesfully generated across the TiO2/CuO/Cu2O interfaces, while the Schottky junction arises on the Cu perimeters. This is evidenced from the blue shifted about 0.3 eV of Cu 2p core level determined by using X-ray photoemission spectroscopy (XPS), in combination with the formation of inverse V-shape of the Mott-Schottky plots. In addition, we find that Cu/CuO/Cu2O facilitates photon absorption range up to the visible region. The multiple heterojunction and the large number of OHsurface enhanced charge carrier transfer are associated to the suppression of photoluminescence (PL) intensity, high surface hydroxyl (OHsurface) density in CuTi probed by XPS, and fast electron transfer based on the electrochemical measurements. The presence of OHsurface inhibits the recombination of electron. A significant H2 photogeneration rate enhancement is achieved when an optimized 5 wt% Cu/CuO/Cu2O concentration is used on TiO2 to achieve 7,157.19 μmol·g−1 (1,789.30 μmol·g−1·h−1). Based on this finding, zero emission energy innitiative could be materialized under multiple heterojunctions in photocatalytic process is beneficial for enhancing the H2 production. © 2025 The Authors

关键词： Titanium dioxide

来源：评论

学校读者我要写书评

暂无评论

Hyperparameter Tuning of SVM Using Metaheuristics: An Empirical Analysis

Hyperparameter Tuning of SVM Using Metaheuristics: An Empiri...

引用

Wireless Africa Conference (WAC)

作者： Sunday O. Oladejo Lateef A. Akinyemi Stephen O. Ekwe Taiwo G. Omomule Oluwaseyi P. Babalola School for Data Science and Computational Thinking Stellenbosch University South Africa Centre for Augmented Intelligence and Data Science University of South Africa South Africa Dept. of Electrical Electronic and Comp. Engineering Cape Peninsula University of Technology South Africa Dept of Mathematics and Statistics University of Guelph Ontario Canada

ISBN: (数字)9798331517588

ISBN: (纸本)9798331517595

The Support Vector Machine (SVM) performance is highly dependent on the selection of optimal hyperparameterse Conventional optimisation methods, including grid search, gradient descent, randomized search, and various experimental approaches, have been extensively utilized in the literature to identify optimal hyperparameters. This paper provides an empirical analysis of SVM's hyperparameter tuning by use of metaheuristics. We compare 11 widely known metaheuristics, such as the Genetic Algorithm (GA), Ant Colony Optimisation (ACO), Particle Swarm Optimisation (PSO), and Differential Evolution (DE), and employ three common datasets, namely Iris, Breast Cancer Wisconsin, and MNIST, due to their unique characteristics. Empirical analysis takes into account factors including cross-validation, number of agents, noise, and mis-labelled data insertion, with emphasis on performance metrics such as accuracy, number of support vectors, and computational time. Our findings reveal that the PSO outperforms other metaheuristics, followed by the DE and ACO. In addition, we conclude that the ACO has the least computational time.

关键词： Support vector machines Wireless communication Accuracy Reviews Metaheuristics Optimization methods Vectors Particle swarm optimization Tuning Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Guardian of the Ensembles: Introducing Pairwise Adversarially Robust Loss for Resisting Adversarial Attacks in DNN Ensembles

Guardian of the Ensembles: Introducing Pairwise Adversariall...

引用

IEEE Workshop on Applications of Computer Vision (WACV)

作者： Shubhi Shukla Subhadeep Dalui Manaar Alam Shubhajit Datta Arijit Mondal Debdeep Mukhopadhyay Partha Pratim Chakrabarti Centre for Computational and Data Sciences IIT Kharagpur India Computer Science and Engineering Department IIT Kharagpur India Center for Cyber Security New York University Abu Dhabi UAE Department of Artificial Intelligence IIT Kharagpur India Computer Science and Engineering Department IIT Patna India

ISBN: (数字)9798331510831

ISBN: (纸本)9798331510848

Adversarial attacks rely on transferability, where an adversarial example (AE) crafted on a surrogate classifier tends to mislead a target classifier. Recent ensemble methods demonstrate that AEs are less likely to mislead multiple classifiers in an ensemble. This paper proposes a new ensemble training using a Pairwise Adversarially Robust Loss (PARL) that by construction produces an ensemble of classifiers with diverse decision boundaries. PARL utilizes outputs and gradients of each layer with respect to network parameters in every classifier within the ensemble simultaneously. PARL is demonstrated to achieve higher robustness against black-box transfer attacks than previous ensemble methods as well as adversarial training without adversely affecting clean example accuracy. Extensive experiments using standard Resnet20, WideResnet28-10 classifiers demonstrate the robustness of PARL against state-of-the-art adversarial attacks. While maintaining similar clean accuracy and lesser training time, the proposed architecture has a 24.8% increase in robust accuracy (∊= 0.07) from the state-of-the art method. Code is available at: https://***/shubhishukla10/PARL

关键词： Training Computer vision Accuracy Perturbation methods Neural networks Closed box Computer architecture Robustness Ensemble learning Standards

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：