检索结果-内蒙古大学图书馆

Unlocking the black box: an in-depth review on interpretability, explainability, and reliability in deep learning

Neural Computing and Applications 2025年第2期37卷 859-965页

作者： ŞAHiN, Emrullah Arslan, Naciye Nur Özdemir, Durmuş Department of Software Engineering Kütahya Dumlupınar University Kütahya43100 Turkey Department of Computer Engineering Kütahya Dumlupınar University Kütahya43100 Turkey

Deep learning models have revolutionized numerous fields, yet their decision-making processes often remain opaque, earning them the characterization of "black-box" models due to their lack of transparency and comprehensibility. This opacity presents significant challenges to understanding the rationale behind their decisions, thereby impeding their interpretability, explainability, and reliability. This review examines 718 studies published between 2015 and 2024 in high-impact journals indexed in SCI, SCI-E, SSCI, and ESCI, providing a crucial reference for researchers investigating methodologies and techniques in related domains. In this exploration, we evaluate a wide array of interpretability and explainability (XAI) strategies, including visual and feature-based explanations, local approach-based techniques, and Bayesian methods. These strategies are assessed for their effectiveness and applicability using a comprehensive set of evaluation metrics. Moving beyond traditional analyses, we propose a novel taxonomy of XAI methods, addressing gaps in the literature and offering a structured classification that elucidates the roles and interactions of these methods. Moreover, we explore the intricate relationship between interpretability and explainability, examining potential conflicts and highlighting the necessity for interpretability in practical applications. Through detailed comparative analysis, we underscore the strengths and limitations of various XAI methods across different data types, ensuring a thorough understanding of their practical performance and real-world utility. The review also examines model robustness against adversarial attacks, emphasizing the critical importance of transparency, reliability, and ethical considerations in model development. A significant emphasis is placed on identifying and mitigating biases in deep learning systems, providing insights into future research directions that aim to enhance fairness and reduce bias. By thoroughl

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

PDIFT++: System-Wide Memory Tracking Using a Single-Process Memory Tracker

引用

SN computer Science 2024年第2期5卷 226页

作者： Kiperberg, Michael Zaidenberg, Nezer Department of Software Engineering Shamoon College of Engineering Beer-Sheva Israel Department of Computer Sciences Ariel University Ariel Israel

Information-flow tracking is useful for preventing malicious code execution and sensitive information leakage. Unfortunately, the performance penalty of the currently available solutions is too high for real-world applications. This paper presents PDIFT++, a hybrid system-wide dynamic information-flow tracker. PDIFT++ uses a hypervisor for coarse memory tracking and an emulator for fine memory tracking. The switching between the two modes allows PDIFT++ to achieve high performance without compromising the memory tracking precision. In addition, PDIFT++ provides system-wide tracking by monitoring system calls that can transmit information between two processes and between a process and a file system. The results show that PDIFT++ induces a performance penalty of 26% on average. © 2024, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.

关键词： DIFT Emulator Hypervisor Virtualization

来源：评论

学校读者我要写书评

暂无评论

Committed-programming reductions: formalizations,implications and relations

引用

Science China(Information Sciences) 2024年第10期67卷 151-171页

作者： Jiang ZHANG Yu YU Dengguo FENG Shuqin FAN Zhenfeng ZHANG State Key Laboratory of Cryptology Department of Computer Science and Engineering Shanghai Jiao Tong University Trusted Computing and Information Assurance Laboratory Institute of SoftwareChinese Academy of Sciences

In this work, we introduce a class of black-box(BB) reductions called committed-programming reduction(CPRed) in the random oracle model(ROM) and obtain the following interesting results:(1) we demonstrate that some well-known schemes, including the full-domain hash(FDH) signature(Eurocrypt1996) and the Boneh-Franklin identity-based encryption(IBE) scheme(Crypto 2001), are provably secure under CPReds;(2) we prove that a CPRed associated with an instance-extraction algorithm implies a reduction in the quantum ROM(QROM). This unifies several recent results, including the security of the Gentry-Peikert-Vaikuntanathan IBE scheme by Zhandry(Crypto 2012) and the key encapsulation mechanism(KEM) variants using the Fujisaki-Okamoto transform by Jiang et al.(Crypto 2018) in the ***, we show that CPReds are incomparable to non-programming reductions(NPReds) and randomly-programming reductions(RPReds) formalized by Fischlin et al.(Asiacrypt 2010).

关键词： provable security random oracle model quantum random oracle model black-box reduction/separation programmability

来源：评论

学校读者我要写书评

暂无评论

Critical Thermal Characterization of Next-Generation Solid-State Batteries for Automotive Battery Management Systems 14

Critical Thermal Characterization of Next-Generation Solid-S...

引用

14th Annual IEEE Applied Power Electronics Conference and Exposition, APEC 2025

作者： Chetri, Chandan Williamson, Sheldon Group Department of Electrical Computer and Software Engineering Oshawa Canada

ISBN: (纸本)9798331516116

Solid-state batteries (SSBs) are at the forefront of next-generation energy storage technologies, promising enhanced safety, energy density, and longevity compared to traditional lithium-ion batteries. However, managing the thermal behavior of SSBs during charging is critical to ensuring their safe and reliable operation. This paper presents an in-depth analysis of the thermal characteristics of SSBs under various charging conditions, based on laboratory experiments conducted in controlled environments. The study specifically evaluates the thermal performance of SSBs in comparison to traditional lithium nickel cobalt aluminum oxide (NCA) batteries, with an emphasis on their potential application in e-mobility. The insights gained from this research are expected to inform the development of advanced thermal management strategies, contributing to the design of safer and more efficient solid-state battery technologies for e-mobility applications. © 2025 IEEE.

关键词： Solid-State Batteries

来源：评论

学校读者我要写书评

暂无评论

Modified Bat Algorithm: a newly proposed approach for solving complex and real-world problems

引用

Soft Computing 2024年第13-14期28卷 7983-7998页

作者： Umar, Shahla U. Rashid, Tarik A. Ahmed, Aram M. Hassan, Bryar A. Baker, Mohammed Rashad Department of Software College of Computer Science and Information Technology University of Kirkuk Kirkuk Iraq Computer Science and Engineering Department School of Science and Engineering University of Kurdistan Hewler KRI Erbil Iraq Department of Computer Science College of Science Charmo University Sulaimani Chamchamal46023 Iraq

Bat Algorithm (BA) is a nature-inspired metaheuristic search algorithm designed to efficiently explore complex problem spaces and find near-optimal solutions. The algorithm is inspired by the echolocation behavior of bats, which acts as a signal system to estimate the distance and hunt prey. Although the BA has proven effective for various optimization problems, it exhibits limited exploration ability and susceptibility to local optima. The algorithm updates velocities and positions based on the current global best solution, causing all agents to converge toward a specific location, potentially leading to local optima issues in optimization problems. On this premise, this paper proposes the Modified Bat Algorithm (MBA) as an enhancement to address the local optima limitation observed in the original BA. MBA incorporates the frequency and velocity of the current best solution, enhancing convergence speed to the optimal solution and preventing local optima entrapment. While the original BA faces diversity issues, both the original BA and MBA are introduced. To assess MBA’s performance, three sets of test functions (classical benchmark functions, CEC2005, and CEC2019) are employed, with results compared to those of the original BA, Particle Swarm Optimization (PSO), Genetic Algorithm (GA), and Dragonfly Algorithm (DA). The outcomes demonstrate the MBA’s significant superiority over other algorithms. In addition, MBA successfully addresses a real-world assignment problem (call center problem), traditionally solved using linear programming methods, with satisfactory results. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2024.

关键词： Swarm intelligence

来源：评论

学校读者我要写书评

暂无评论

DocTTT: Test-Time Training for Handwritten Document Recognition Using Meta-Auxiliary Learning

DocTTT: Test-Time Training for Handwritten Document Recognit...

引用

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

作者： Gu, Wenhao Gu, Li Wang, Ziqiang Suen, Ching Yee Wang, Yang Concordia University Department of Computer Science and Software Engineering Canada

ISBN: (纸本)9798331510831

Despite recent significant advancements in Handwritten Document Recognition (HDR), the efficient and accurate recognition of text against complex backgrounds, diverse handwriting styles, and varying document layouts remains a practical challenge. Moreover, this issue is seldom addressed in academic research, particularly in scenarios with minimal annotated data available. In this paper, we introduce the DocTTT framework to address these challenges. The key innovation of our approach is that it uses test-time training to adapt the model to each specific input during testing. We propose a novel Meta-Auxiliary learning approach that combines Meta-learning and self-supervised Masked Autoencoder (MAE). During testing, we adapt the visual representation parameters using a self-supervised MAE loss. During training, we learn the model parameters using a meta-learning framework, so that the model parameters are learned to adapt to a new input effectively. Experimental results show that our proposed method significantly outperforms existing state-of-the-art approaches on benchmark datasets. © 2025 IEEE.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

How far are we to GPT-4V?Closing the gap to commercial multimodal models with open-source suites

引用

Science China(Information Sciences) 2024年第12期67卷 5-22页

作者： Zhe CHEN Weiyun WANG Hao TIAN Shenglong YE Zhangwei GAO Erfei CUI Wenwen TONG Kongzhi HU Jiapeng LUO Zheng MA Ji MA Jiaqi WANG Xiaoyi DONG Hang YAN Hewei GUO Conghui HE Botian SHI Zhenjiang JIN Chao XU Bin WANG Xingjian WEI Wei LI Wenjian ZHANG Bo ZHANG Pinlong CAI Licheng WEN Xiangchao YAN Min DOU Lewei LU Xizhou ZHU Tong LU Dahua LIN Yu QIAO Jifeng DAI Wenhai WANG State Key Laboratory for Novel Software Technology Nanjing University Shanghai AI Laboratory School of Computer Science Fudan University SenseTime Research Department of Information Engineering The Chinese University of Hong Kong Department of Electronic Engineering Tsinghua University

In this paper, we introduce InternVL 1.5, an open-source multimodal large language model(MLLM) to bridge the capability gap between open-source and proprietary commercial models in multimodal understanding. We introduce three simple improvements.(1) Strong vision encoder: we explored a continuous learning strategy for the large-scale vision foundation model — InternViT-6B, boosting its visual understanding capabilities, and making it can be transferred and reused in different LLMs.(2) Dynamic high-resolution: we divide images into tiles ranging from 1 to 40 of 448×448 pixels according to the aspect ratio and resolution of the input images, which supports up to 4K resolution input.(3) High-quality bilingual dataset: we carefully collected a high-quality bilingual dataset that covers common scenes, document images,and annotated them with English and Chinese question-answer pairs, significantly enhancing performance in optical character recognition(OCR) and Chinese-related tasks. We evaluate InternVL 1.5 through a series of benchmarks and comparative studies. Compared to both open-source and proprietary commercial models, InternVL 1.5 shows competitive performance, achieving state-of-the-art results in 8 of 18 multimodal benchmarks. Code and models are available at https://***/OpenGVLab/InternVL.

关键词： multimodal model open-source vision encoder dynamic resolution bilingual dataset

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Based Phishing Attacks Detection Using Multiple Datasets

International Journal of Interactive Mobile Technologies

引用

International Journal of Interactive Mobile Technologies 2023年第5期17卷 71-83页

作者： Aljammal, Ashraf H. taamneh, Salah Qawasmeh, Ahmad Salameh, Hani Bani Department of Computer Science and Applications The Hashemite University Zarqa Jordan Department of Software Engineering The Hashemite University Zarqa Jordan

Nowadays, individuals and organizations are increasingly targeted by phishing attacks, so an accurate phishing detection system is required. Therefore, many phishing detection techniques have been proposed as well as phishing datasets have been collected. In this paper, three datasets have been used to train and test machine learning classifiers. The datasets have been archived by Phish-Tank and UCI Machine Learning Repository. Furthermore, Information Gain algorithm have been used for features reduction and selection purpose. In addition, six machine learning classifiers have been evaluated, namely NaiveBayes, ANN, DecisionStump, KNN, J48 and RandomForest. However, the classifiers have been trained and tested over the three datasets in two stages. The first stage is using all features included in each dataset while the second stage using selected features by IG algorithm. At the first stage RandomForest classifier has shown the best performance over Dataset-1 and Dataset-2, while J48 has shown the best performance over Dataset-3. On the other hand, after features selection, the RandomForest classifier was the superior among the other five classifiers over Dataset-1 and Dataset-2 with accuracy of 98% and 93.66% respectively. While ANN classifier has shown the best performance with accuracy of 88.92% over Dataset-3. Because of the few number of instances as well as features in Dataset-3 comparing to the other two dataset;the performance of the classifiers has been affected © 2023, International Journal of Interactive Mobile *** Rights Reserved.

关键词： Network security

来源：评论

学校读者我要写书评

暂无评论

Application of Physical Unclonable Function for Lightweight Authentication in Internet of Things

引用

computers, Materials & Continua 2023年第4期75卷 1901-1918页

作者： Ahmad O.Aseeri Sajjad Hussain Chauhdary Mohammed Saeed Alkatheiri Mohammed A.Alqarni Yu Zhuang Department of Computer Science College of Computer Engineering and SciencesPrince Sattam Bin Abdulaziz UniversityAl-Kharj11942Saudi Arabia Department of Computer Science and Artificial Intelligence College of Computer Science and EngineeringUniversity of JeddahJeddahSaudi Arabia Department of Cybersecurity College of Computer Science and EngineeringUniversity of JeddahJeddahSaudi Arabia Department of Software Engineering College of Computer Science and EngineeringUniversity of JeddahJeddahSaudi Arabia Department of Computer Science Texas Tech UniversityLubbockUSA

IoT devices rely on authentication mechanisms to render secure message *** data transmission,scalability,data integrity,and processing time have been considered challenging aspects for a system constituted by IoT *** application of physical unclonable functions(PUFs)ensures secure data transmission among the internet of things(IoT)devices in a simplified network with an efficient time-stamped *** paper proposes a secure,lightweight,cost-efficient reinforcement machine learning framework(SLCR-MLF)to achieve decentralization and security,thus enabling scalability,data integrity,and optimized processing time in IoT *** has been integrated into SLCR-MLF to improve the security of the cluster head node in the IoT platform during transmission by providing the authentication service for device-to-device *** IoT network gathers information of interest from multiple cluster members selected by the proposed *** addition,the software-defined secured(SDS)technique is integrated with SLCR-MLF to improve data integrity and optimize processing time in the IoT *** analysis shows that the proposed framework outperforms conventional methods regarding the network’s lifetime,energy,secured data retrieval rate,and performance *** enabling the proposed framework,number of residual nodes is reduced to 16%,energy consumption is reduced by up to 50%,almost 30%improvement in data retrieval rate,and network lifetime is improved by up to 1000 msec.

关键词： Cyber-physical systems security data aggregation Internet of Things physical unclonable function swarm intelligences

来源：评论

学校读者我要写书评

暂无评论

Prediction of software quality with Machine Learning-Based ensemble methods

引用

Materials Today: Proceedings 2023年 81卷 18-25页

作者： Ceran, A. Ayberk Ar, Yilmaz Tanrıöver, Ö. Özgür Seyrek Ceran, Sinem Department of Computer Engineering Ankara University Ankara 06830 Turkey Department of Software Engineering Turkish Aeronautical Association University Ankara 06790 Turkey

software quality prediction is used at various stages of projects. There are several metrics that provide the quality measure with respect to different types of software. In this study, defect density is used as the feature that represents the quality. The aim of this study is to predict software quality with higher accuracy than previous studies. The study shows that data pre-processing, feature extraction and machine learning algorithms provide more accurate results in predicting the quality of the software. Algorithms were applied on three datasets that include software metrics. The obtained accuracy values were compared with the existing ones in the literature. Ensemble methods, which enable the use of different machine learning algorithms together, contributed to obtaining results with higher accuracy rates in software quality prediction. In EBSPM dataset, logistic regression produced the best accuracy value as 96.67%. On the other hand, in ISBSG dataset and in PROMISE dataset, the ensemble methods Soft Voting & Stacking and Gradient Boosting & Bagging generated the best results respectively with the values 96.31% and 94.59%. © 2022

关键词： Machine learning

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：