检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Farhan Shahriyar, Md. Tanbhir, Gazi Chy, Abdullah Md Raihan Tanzin, Mohammed Abdul Al Arafat Jisan Mashrafi, Md. Dept. of Computer Science and Engineering World University of Bangladesh Dhaka Bangladesh Dept. of Computer Science and Engineering Southern University Bangladesh Chittagong Bangladesh Dept. of Computer Science and Engineering Brac University Dhaka Bangladesh

—Phishing URL detection is crucial in cybersecurity as malicious websites disguise themselves to steal sensitive information. Traditional machine learning techniques struggle to perform well in complex real-world scenarios due to large datasets and intricate patterns. Motivated by quantum computing, this paper proposes using Variational Quantum Classifiers (VQC) to enhance phishing URL detection. We present PhishVQC, a quantum model that combines quantum feature maps and variational ansatzes such as RealAmplitude and EfficientSU2. The model is evaluated across two experimental setups with varying dataset sizes and feature map repetitions. PhishVQC achieves a maximum macro average F1-score of 0.89, showing a 22% improvement over prior studies. This highlights the potential of quantum machine learning to improve phishing detection accuracy. The study also notes computational challenges, with execution wall times increasing as dataset size grows. Copyright © 2025, The Authors. All rights reserved.

关键词： Phishing

来源：评论

学校读者我要写书评

暂无评论

Event Identification and Chronology Model of Ramayana

Event Identification and Chronology Model of Ramayana

引用

International Conference on Electronics, Materials engineering and Nano-Technology (IEMENTech)

作者： Apurba Paul Rishabh Mishra Nayan Padia Dipankar Das Dept. of Computer Science & Engineering IEM Kolkata UEM Kolkata Kolkata India Dept. of Computer Science & Engineering IEM Kolkata Kolkata India Dept. of Computer Science & Engineering Jadavpur University Kolkata India

ISBN: (数字)9798331520762

ISBN: (纸本)9798331520779

The paper introduces an event chronology model for Hindu mythological texts, with a focus on the Ramayana's Bala-kanda. It captures and structures sentence-level events based on their chronological order to better understand narrative progression and character interactions. A manually crafted dataset of 1217 events, involving 214 characters across 75 chapters, is used to generate a knowledge graph. The graph organizes events by sequence, linking characters, actions, and chapters within the storyline. The event chronology is mapped by establishing relationships between events, ensuring they are connected in the proper sequence to reflect the narrative flow. This approach enables a deeper understanding of how each event contributes to the overarching story, providing insights into both the individual actions of characters and their significance within the broader mythological narrative. Transformer-based models (BERT, DistilBERT, and RoBERTa) were utilized for predicting subsequent events, with RoBERTa showing the highest accuracy in preserving the correct event chronology. This structure is key to analyzing the sequential development of the Ramayana's storyline.

关键词： Accuracy Annotations Refining Knowledge graphs Manuals Predictive models Transformers Guidelines

来源：评论

学校读者我要写书评

暂无评论

Artificial Intelligence Techniques for the Ransomware Detection: Current Methods and Challenges 1

Artificial Intelligence Techniques for the Ransomware Detect...

引用

1st International Conference on AIML-Applications for engineering and Technology, ICAET 2025

作者： Rakibe, Priya Jawale, Madhuri Computer Engineering Research Centre Sanjivani College of Engineering Kopargaon Savitribai Phule Pune University Pune India Sanjivani College of Engineering Kopargaon Savitribai Phule Pune University Dept. of Information Technology Pune India

ISBN: (纸本)9798350355611

Recently, Artificial Intelligence (AI) Techniques have received significant interest across the different fields for data analysis and decision-making. Ransomware detection using AI has been a challenging research problem for the last decade in hybrid communication systems like blockchainintegrated Internet of Things (IoT) architectures. Ransomware is a form of malicious software that restricts access to a victim's resources by altering system login credentials or encrypting digital data. Consequently, typical approaches used to identify other types of threats are inadequate for recognizing ransomware. Different AI techniques recently have been used for the detection of such threats, but an appropriate level of accuracy and minimum false rate with automation are vital challenges. This study presents a systematic review of the current methods for ransomware detection using different AI techniques. The ransomware detection methods under categories such as rule-based, machine learning-based, and deep learning-based are reviewed in this study. The comparative analysis of these methods is provided quantitatively and qualitatively. As per the recent progress in the domain of ransomware detection, the current research problems are identified and discussed as the outcome of the study. The roadmap for future work is described as the research gap analysis output. © 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

Federated Learning in Healthcare: A Privacy-Preserving Approach to Predictive Analytics

Federated Learning in Healthcare: A Privacy-Preserving Appro...

引用

2025 IEEE International Conference on Computational, Communication and information Technology, ICCCIT 2025

作者： Reddy, M. Jithender Kotiyal, Arnav Lakhanpal, Sorabh Badhoutiya, Arti Mounika, T. Jayanthi, Muthuswamy Vasavi College of Engineering Dept. of Computer Science and Engineering Telangana Hyderabad India Graphic Era Deemed to Be University Department of Computer Science & Engineering Dehradun India Lovely Professional University Punjab Phagwara India GLA University Department of Electrical Engineering Mathura India MLR Institute of Technology Department of Computer Science and Engineering Telangana Hyderabad India New Horizon College of Engineering Department of Electronics and Communication Engineering Bangalore India

ISBN: (纸本)9798331512965

Technology such as machine learning in healthcare has pushed privacy concerns to the point that the handling of sensitive patient data has become paramount. In the context of FL, predictive analytics without data sharing between institutions can be performed through the process. Next, we explore the application of FL in healthcare in order to maintain data privacy while obtaining robust predictive models. FL utilizes aggregated decentralized data from multiple healthcare providers to reduce the chance of data breaches and continue to be compliant with rigorous regulatory frameworks, like HIPAA and GDPR, while doing so. In this work, we evaluate the model performance of FL models in predicting different types of health outcomes in comparison with traditional centralized models. We show that FL can achieve similar predictive accuracy while maintaining data privacy, which makes the choice of FL as a viable alternative to privacy sensitive healthcare environments. Second, applying FL is very challenging: there are communication overhead, data heterogeneity, and security risks. This study also considers ways to minimize these challenges. The results demonstrate the promise of Federated Learning as an innovative paradigm for applying predictive analytics in healthcare, indicative of a robust shift toward more secure, efficient and privacy preserving healthcare systems. © 2025 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

PhishVQC: Optimizing Phishing URL Detection with Correlation Based Feature Selection and Variational Quantum Classifier

PhishVQC: Optimizing Phishing URL Detection with Correlation...

引用

International Symposium on Advanced Computing and Communication (ISACC)

作者： Md. Farhan Shahriyar Gazi Tanbhir Abdullah Md Raihan Chy Mohammed Abdul Al Arafat Tanzin Md. Jisan Mashrafi Dept. of Computer Science and Engineering World University of Bangladesh Dhaka Bangladesh Dept. of Computer Science and Engineering Southern University Bangladesh Chittagong Bangladesh Dept. of Computer Science and Engineering Brac University Dhaka Bangladesh

ISBN: (数字)9798331523893

ISBN: (纸本)9798331523909

Phishing URL detection is crucial in cybersecurity as malicious websites disguise themselves to steal sensitive information. Traditional machine learning techniques struggle to perform well in complex real-world scenarios due to large datasets and intricate patterns. Motivated by quantum computing, this paper proposes using Variational Quantum Classifiers (VQC) to enhance phishing URL detection. We present PhishVQC, a quantum model that combines quantum feature maps and variational ansatzes such as RealAmplitude and EfficientSU2. The model is evaluated across two experimental setups with varying dataset sizes and feature map repetitions. PhishVQC achieves a maximum macro average F1-score of 0.89, showing a 22% improvement over prior studies. This highlights the potential of quantum machine learning to improve phishing detection accuracy. The study also notes computational challenges, with execution wall times increasing as dataset size grows.

关键词： Uniform resource locators Quantum computing Correlation Accuracy Phishing Computational modeling Machine learning Feature extraction Intelligent systems

来源：评论

学校读者我要写书评

暂无评论

Retrieval Augmented Generation for Relational Mapping of Resume Data for Improved Analysis

Retrieval Augmented Generation for Relational Mapping of Res...

引用

Machine Learning and Autonomous Systems (ICMLAS), International Conference on

作者： Vazzula Manish Yugandhar Manchala Sudeep Banerjee Chopra Muddam Siddartha Kothi Yashwanth Reddy Dept. of Information Technology Vardhaman College of Engineering Hyderabad India Dept. of Computer Science (AI & ML) Vardhaman College of Engineering Hyderabad India

ISBN: (数字)9798331505745

ISBN: (纸本)9798331505752

Analysis of resume data is often a critical and time-intensive process that requires extensive metadata. However, a lack of consistency and scalability often leads to inefficiencies and errors in the recruitment process. Tools like Applicant Tracking Systems (ATS) often struggle with the contextual understanding of resume data, as they evaluate each resume in isolation without considering its relations to other similar resumes. We proposes the implementation of a Retrieval-Augmented Generation (RAG) architecture to create a vector relational mapping of resume data based on several curated parameters, such as skills, experiences, and education. This approach enables the system to understand the contextual relations between different resumes, helping the system evaluate them more effectively within a broader context, and improve recruitment outcomes by reducing biases and increasing efficiency.

关键词： Social networking (online) Soft sensors Resumes Retrieval augmented generation Software as a service Transforms Natural language processing Vectors Recruitment Software development management

来源：评论

学校读者我要写书评

暂无评论

Integrated Framework for Equitable Healthcare AI: Bias Mitigation, Community Participation, and Regulatory Governance

Integrated Framework for Equitable Healthcare AI: Bias Mitig...

引用

International Conference on Communication Systems and Network Technologies (CSNT)

作者： Joydeep Chandra Ramanjot Kaur Rashi Sahay Dept. of Computer Science and Engineering Chandigarh University Mohali Punjab India Dept. of Computer Science and Engineering MRIIRS Faridabad India

ISBN: (数字)9798331531935

ISBN: (纸本)9798331531942

Artificial intelligence (AI) has revolutionized healthcare by enhancing diagnostic precision, personalizing treatments, and optimizing clinical workflows. However, algorithmic biases arising from imbalanced training data dis-proportionately affect marginalized populations, perpetuating health disparities. For instance, a widely-used predictive model underprioritized Black patients by equating healthcare costs with illness severity, restricting access to essential care. To address these challenges, this paper introduces an integrated framework combining adversarial debiasing, reinforcement learning (RL)-driven threshold optimization, synthetic data augmentation, and community engagement strategies. Empirical evaluations using the MIMIC-III dataset demonstrate near-perfect Area Under the ROC Curve (AUC = 0.994) alongside significant reductions in demographic parity (DP = 0.000) and error rate differences across subgroups. While the RL-optimized threshold ensures no missed diagnoses, it increases false positives, highlighting the trade-offs between fairness and precision. This work underscores the importance of synthesizing technical, regulatory, and community-driven approaches to promote equitable AI deployments. By embedding participatory design principles and aligning with emerging governance frameworks like the European Union’s AI Act, the proposed methodology offers a scalable pathway toward transparent, accountable, and high-impact healthcare AI solutions.

关键词： Ethics Prevention and mitigation Training data Medical services Reinforcement learning Prediction algorithms Optimization Standards Synthetic data Guidelines

来源：评论

学校读者我要写书评

暂无评论

Integrated Framework for Equitable Healthcare AI: Bias Mitigation, Community Participation, and Regulatory Governance 14

Integrated Framework for Equitable Healthcare AI: Bias Mitig...

引用

14th IEEE International Conference on Communication Systems and Network Technologies, CSNT 2025

作者： Chandra, Joydeep Kaur, Ramanjot Sahay, Rashi Dept. of Computer Science and Engineering Chandigarh University Punjab Mohali India Dept. of Computer Science and Engineering MRIIRS Faridabad India

ISBN: (纸本)9798331531935

Artificial intelligence (AI) has revolutionized healthcare by enhancing diagnostic precision, personalizing treatments, and optimizing clinical workflows. However, algorithmic biases arising from imbalanced training data disproportionately affect marginalized populations, perpetuating health disparities. For instance, a widely-used predictive model underprioritized Black patients by equating healthcare costs with illness severity, restricting access to essential care. To address these challenges, this paper introduces an integrated framework combining adversarial debiasing, reinforcement learning (RL)-driven threshold optimization, synthetic data augmentation, and community engagement strategies. Empirical evaluations using the MIMIC-III dataset demonstrate near-perfect Area Under the ROC Curve (AUC = 0.994) alongside significant reductions in demographic parity (DP = 0.000) and error rate differences across subgroups. While the RL-optimized threshold ensures no missed diagnoses, it increases false positives, highlighting the trade-offs between fairness and precision. This work underscores the importance of synthesizing technical, regulatory, and community-driven approaches to promote equitable AI deployments. By embedding participatory design principles and aligning with emerging governance frameworks like the European Union’s AI Act, the proposed methodology offers a scalable pathway toward transparent, accountable, and high-impact healthcare AI solutions. © 2025 IEEE.

关键词： Patient treatment

来源：评论

学校读者我要写书评

暂无评论

A Comparative Analysis of Deep Learning Based Approaches for DeepFake Identification

引用

Procedia computer science 2025年 259卷 482-493页

作者： Krity Duhan Abhishek Kajal Dept. of Computer Science and Engineering GJUS&T Hisar 125001 India

One of the major concerns in the present global environment is the creation and utilization of deepfakes. In this work, we have examined the issues and challenges that are created by the deepfake in the security and surveillance mechanisms. Deepfakes are used for by passing the facial identification or biometrics system that are normally used as surveillance mechanisms. Previously the only issue was to find the authentic person through the photographs that they have put on their identity proofs but nowadays it is extended to find the forged pics that are manipulated with the usage of AI based methods like deepfakes. Deepfakes are used in the current environments for bypassing the security by impersonation and providing false information and thus become a source of danger especially in the politics arena and entertainment landscape. Deep learning has the tendency to mitigate the impact of deepfakes to considerable extent by incorporating the same in the techniques develop for the identification of deepfakes. This paper provides the comprehensive review of the deepfake related work that has been done by researchers with the usage of deep learning approaches which could identify the fake images, videos to significant extent in various contexts along with the mechanism used for deepfake creation and identification in general. Moreover, the comparative analysis of the existing techniques has been done considering a range of factors like dataset used, technique used, accuracy, AUC, data type used for deepfake identification etc. It has been inferred that majority of the researchers have used the FaceForensics++, Celeb-DF, DFDC dataset and have utilized CNN technique for the deepfake identification primarily on images.

关键词： Deepfake CNN GAN Accuracy Deep learning Dataset AUC

来源：评论

学校读者我要写书评

暂无评论

Moth flame optimization algorithm for efficient feature selection and hybrid classification technique for intrusion detection system

引用

Multimedia Tools and Applications 2025年 1-21页

作者： Keerthanarani, U. Selvakumar, V. Singaravelan, S. Raja, S. Edwin Thenmozhi, K. Shunmugam, D. Arun Dept. of Computer Science and Engineering P.S.R Engineering College Sivakasi India Dept.Of Computer Science and Engineering Vel Tech Rangarajan Dr Sagunthala R & d Institute of Science and Technology Chennai Avadi India Dept. Of Computer Science and Engineering Coimbatore Institute of Engineering and Technology Coimbatore India Dept. Of Electronics and Communication Engineering P.S.R Engineering College Sivakasi India

The rapid expansion of the Internet of Things (IoT) brings numerous benefits but further presents fresh difficulties, especially in terms of security. The distributed and interconnected nature of IoT devices makes them susceptible to various security threats. An Intrusion Detection System (IDS) plays a crucial role in safeguarding IoT networks by monitoring, detecting, and responding to potential security incidents. The Internet of Things (IoT) connects billions of devices, sensors, and systems, transforming industries and everyday life. However, this extensive interconnectivity also introduces significant security risks, making Intrusion Detection Systems (IDS) a critical component for safeguarding IoT environments. Feature selection is a crucial aspect of building effective Intrusion Detection Systems (IDS). Selecting relevant features not only helps in achieving better classification accuracy but also contributes to reducing false alarm rates. In the proposed system a moth flame optimizer is utilized to select the efficient features from the dataset, overall accuracy of over 97%. Further it is classified employing Random Forest and J48 classifier which attains high classification accuracy and low false alarm rate. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2025.

关键词： Feature Selection

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：