检索结果-内蒙古大学图书馆

Fast Detection and Traceback-Based Mitigation of Interest Flooding Attack

SN computer science 2025年第2期6卷 1-15页

作者： Kumar, Naveen Singh, Ashutosh Kumar Srivastava, Shashank Department of Computer Science and Engineering Sardar Vallabhbhai National Institute of Technology Gujarat Surat 395007 India Department of Computer Science Allahabad Degree College University of Allahabad Uttar Pradesh Prayagraj 211003 India Computer Science and Engineering Motilal Nehru National Institute of Technology Allahabad Uttar Pradesh Prayagraj 211004 India

The Pending Interest Table (PIT) in Named Data Networking (NDN) plays a crucial role by storing state information of requests within the router, enabling efficient data packet routing back to the requester. However, this mechanism is vulnerable to Interest Flooding Attacks (IFA), where an attacker sends a large number of malicious requests to overwhelm the PIT, disrupting network performance. Previous research primarily focused on offline detection of IFA using selected features and machine learning techniques. In this work, we build on these findings by deploying a trained Artificial Neural Network (ANN) classifier on each NDN router for real-time, online detection of IFA. Additionally, we introduce a novel traceback-based mitigation strategy activated upon detection, significantly improving the network’s resilience against such attacks. Our proposed method demonstrates superior performance in terms of satisfaction ratio and throughput for legitimate consumers compared to existing approach. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2025.

关键词： ANN Feature selection Interest Flooding Attack Named Data Networking NDN Traceback

来源：评论

学校读者我要写书评

暂无评论

UAV and UGV Assisted Path Planning for Sensor Data Collection in Precision Agriculture 11

UAV and UGV Assisted Path Planning for Sensor Data Collectio...

引用

11th International Symposium on Electronic Systems Devices and Computing, ESDC 2023

作者： Singh, Himanshu Biken Singh, Moirangthem Pratik, Harsh Pratap, Ajay Department of Computer Science and Engineering Varanasi India

ISBN: (纸本)9781665455725

In recent years, automated (Intelligent) decision support systems have become prevalent in various smart city applications such as healthcare, transportation, energy management, and environmental monitoring. Internet of Things (IoT) and Unmanned Aerial Vehicle (UAV)-based smart sensing and actuation devices in agricultural events can change the sector from static and manual to dynamic and intelligent, resulting in increased production with minimal human efforts. In addition, soil measurements that are time-consuming can be collected using Unmanned Ground Vehicles (UGVs). However, to collect data efficiently from wireless sensors in agricultural fields, UAV and UGV need to follow an optimal path. Thus, in this paper, we formulate utility maximization problem using UAV and UGV by simultaneously minimizing energy consumption and maximizing data collection. To solve the formulated problem, we propose a modified Greedy Randomised Adaptive Search Procedure (GRASP) algorithm to predict an efficient path for UAV and UGV to collect data from the agricultural field. Moreover, the efficacy of the proposed algorithm is showcased theoretically and experimentally on real-world data and compared with other state-of-the-art methods. © 2023 IEEE.

关键词： Energy utilization

来源：评论

学校读者我要写书评

暂无评论

Decentralized File Sharing: Leveraging Blockchain and IPFS for Secure Data Storage

Decentralized File Sharing: Leveraging Blockchain and IPFS f...

引用

2024 International Conference on Integration of Emerging Technologies for the Digital World, ICIETDW 2024

作者： Gowda, Manasa G Raj, Neha Prajna, P. Vishrutha, R. Aruna, S. Dayananda Sagar College of Engineering Department of Computer Science Bengaluru India

ISBN: (纸本)9798331541170

The rapid growth in data creation and the demand for secure storage solutions have driven the development of decentralized file-sharing platforms. Traditional centralized systems face issues like single points of failure, data breaches, and censorship, which threaten data integrity. Blockchain, known for its security and transparency, combined with the Inter Planetary File System (IPFS), offers a robust alternative for decentralized file sharing. This research explores how blockchain and IPFS enhance data security, reliability, and efficiency. The system uses blockchain for secure transaction logging, ensuring data immutability and traceability. IPFS provides decentralized file storage by splitting files into chunks, hashing them, and distributing them across nodes. Access is managed through blockchain-based smart contracts, handling authentication and authorization. Performance is evaluated through experiments measuring data retrieval speed, system throughput, and *** results show that integrating blockchain with IPFS significantly improves security and resilience over traditional systems. IPFS ensures high availability and redundancy, while blockchain offers a tamper-proof record of transactions. The system matches centralized systems in data retrieval speed and throughput, with added security and *** and IPFS offer a promising solution for decentralized file sharing, addressing the shortcomings of centralized systems. This approach enhances data security and integrity and supports data *** key contribution is the implementation of a multi-formatting technique that increases the flexibility and efficiency of data storage and retrieval. © 2024 IEEE.

关键词： BLOCKCHAIN DATA PRIVACY DECENTRALIZED STORAGE IPFS NETWORK SECURITY

来源：评论

学校读者我要写书评

暂无评论

Advanced Reinforcement Learning Based Penetration Testing 1

Advanced Reinforcement Learning Based Penetration Testing

引用

1st IEEE International Conference on Electronics, Computing, Communication and Control Technology, ICECCC 2024

作者： Anish Udupa, H. Anavi, B.S. Goyal, Barkha Kasturi, Sanjana Pai Agarwal, Pooja PES University Computer Science and Engineering Department Bengaluru560100 India

ISBN: (纸本)9798350371802

Penetration testing is a technique that involves the identification and exploitation of security flaws by simulating real world attacks to find security loopholes. Manual pentesting is a tedious and time consuming process. With applications being developed within weeks and the rapid growth of cybercrime, automated pentesting is the need of the hour. This research focuses on training the pentesting agent using three different reinforcement learning algorithms - Proximal Policy Optimization(PPO), Deep Q-Network (DQN) and Ad-vantageous Actor-Critic (A2C) to discover the suitable technique to perform penetration testing. The goal is to create an agent which is capable of exploiting the vulnerabilities in a host system in an effective manner. The training occurs against various vulnerable machines to identify the optimal exploit path with each algorithm and their convergence is compared. The study finds that Advantageous Actor-Critic has the best convergence rate compared to the performance of Deep Q-Network and Proximal Policy Optimization. The time duration and resource consumption is minimal proving that manual penetration testing is old and outdated and automating the process is tedious but worthy and effective. © 2024 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Advanced remote sensing techniques for underwater Fin whale detection in the Indian Ocean 6

Advanced remote sensing techniques for underwater Fin whale ...

引用

6th IEEE International Conference on Image Processing, Applications and Systems, IPAS 2025

作者： Sanikommu, Vasavi Sura, Akshaya Chimirala, Pranavi Velagapudi Ramakrishna Siddhartha Engineering College Department of Computer Science and Engineering Andhra Pradesh India

ISBN: (纸本)9798331506520

The accurate detection and monitoring of whales in the Indian Ocean are vital for marine conservation but face significant challenges due to the complexities of underwater environments. Advanced remote sensing technologies offer potential solutions to overcome these limitations. This study integrates hyperspectral imaging, satellite imagery, and thermal imaging to develop a comprehensive whale detection system. Hyperspectral imaging captures the spectral reflectance of whale skin, enabling detection under varying water conditions. Satellite imagery aids in identifying subsurface features, while thermal imaging detects whales' thermal signatures. Machine learning algorithms process the combined data to enhance detection accuracy and reliability. The integrated system demonstrated effective detection of whales at various depths and environmental conditions in the Indian Ocean. Hyperspectral imaging proved sensitive to water turbidity and target reflectance, while the coastal blue band successfully identified subsurface whale features. Thermal imaging further enhanced detection capabilities in low-light conditions. The combined use of these technologies outperformed traditional methods, offering an accuracy of 0.96 and reliability for real-time whale monitoring. © 2025 IEEE.

关键词： Hyperspectral imaging

来源：评论

学校读者我要写书评

暂无评论

Multi-class Generative Adversarial Network for Hyperspectral Image Classification for Addressing Class Imbalance Problem 4th

Multi-class Generative Adversarial Network for Hyperspectral...

引用

4th International Conference on Smart IoT Systems: Innovations and Computing, SSIC 2023

作者： Kumar, Deepak Kumar, Dharmender Department of Computer Science and Engineering Guru Jambheshwar University of Science and Technology Haryana Hisar India

ISBN: (纸本)9789819751990

Class-imbalanced datasets are commonly observed in hyperspectral image classification and deep learning models often tend to demonstrate a bias toward the dominant class, resulting in very low efficiency for minority classes. Data augmentation has been the most widely used strategy to mitigate class-imbalanced challenge. Therefore, in this paper, the authors have introduced a data augmentation approach utilizing a multi-class generative adversarial network (MCGAN) to deal with this issue. In the proposed approach a generative adversarial network is utilized to specifically generate fake minority class samples and integrating these samples with the existing class samples. Further, a convolutional neural network (CNN) has been employed for classification of hyperspectral image samples. A series of experiments, utilizing the proposed approach, has been conducted with two most popular and publicly available datasets. The experiment results obtained are then compared with four state-of-the-art data augmentation techniques. The comparison results prove the supremacy of the proposed approach in terms of the quality of the generated samples and the classification accuracy over the state-of-the-art techniques. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Few-Shot Lung Cancer Classification Using Prototypical Networks 4

Few-Shot Lung Cancer Classification Using Prototypical Netwo...

引用

4th International Conference on Advanced Research in Computing, ICARC 2024

作者： Amarasinghe, Nimesha Hansani Ambegoda, Thanuja D. University of Moratuwa Department of Computer Science and Engineering Moratuwa Sri Lanka

ISBN: (纸本)9798350384864

Lung cancer, a leading cause of mortality globally, demands early and accurate detection to improve patient out-comes. Current diagnostic methods, primarily relying on CT scans, face challenges in lung cancer subtype identification, particularly due to the scarcity of extensive medical image datasets for each subtype. This study addresses this limitation by leveraging prototypical networks, an innovative few-shot learning approach, which excels in scenarios with limited data. The proposed method capitalizes on a small number of samples per category, integrating a pre-trained model for feature extraction from lung CT scans. We rigorously evaluated the model's performance, focusing on its accuracy relative to the sample size per category. Remarkably, the method achieved a 98% accuracy rate after 15 epochs, showcasing its efficacy. This research not only confirms the feasibility of using prototypical networks for lung cancer subtype classification but also opens new avenues for applying few-shot learning techniques in medical imaging. Our findings hold significant potential for enhancing lung cancer diagnostics, thereby contributing to improved patient care and survival rates. © 2024 IEEE.

关键词： computerized tomography

来源：评论

学校读者我要写书评

暂无评论

Comprehensive Analysis of Attention Deficit/Hyperactivity Disorder using Machine Learning and Deep Learning Algorithms 1

Comprehensive Analysis of Attention Deficit/Hyperactivity Di...

引用

1st International Conference on Intelligent Systems and Computational Networks, ICISCN 2025

作者： Sindhu, T.N. Sujatha, S.R. Sri Siddhartha Institute of Technology Department of Computer Science and Engineering Tumakuru India

ISBN: (纸本)9798331529246

Attention deficit/hyperactivity disorder (ADHD) is a neurodevelopmental disorder that affects children from childhood to adulthood. The symptoms of ADHD include attention deficit, impulsive behaviour, hyperactivity, and early diagnosis and treatment are imperative, especially for children as it continues into adulthood. ADHD detection is generally carried out using the existing methods such as Machine Learning (ML) and Deep Learning (DL) methods. The ML methods such as Linear Support Vector Machine (SVM), K-Nearest Neighbors (KNN), Linear Discriminative Analysis (LDA), Linear Regression (LR), Random Forest (RF), and Least Square SVM (LS-SVM) are used for the detection and analysis of ADHD. The existing DL methods such as Deep Convolutional Neural Network (DCNN), Graph Recurrent Unit (GRU), Convolutional Long Short-Term Memory (ConvLSTM), and Bidirectional LSTM are also employed for the detection of ADHD. The ML and DL algorithms enhance ADHD detection and diagnosis by automatically determining large patterns in data, thereby offering higher accuracy. The performance of the existing techniques is evaluated in terms of evaluation metrics: accuracy, precision, sensitivity, and F1-score to assess their effectiveness. © 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

Automatic Number Plate Recognition System using Machine Learning Techniques

Automatic Number Plate Recognition System using Machine Lear...

引用

2024 International Conference on Electrical, Electronics and Computing Technologies, ICEECT 2024

作者： Dayal, Avnish Porwal, Aryan Gupta, Avinash Srivastava, Aditya Kumar Mahendru, Mansi ABES Engineering College Department of Computer Science UP Ghaziabad India

ISBN: (纸本)9798350378092

The system employs video processing technology to detect the image of a vehicle's number plate from a video stream. Subsequently, various algorithms are applied to extract the number from the detected plate. This system can be used at college entrances, cantonment area and other places with strict access restrictions. The system detects the number plate whenever a vehicle passes by, converting it into both images and text. Subsequently, this information is stored in the database for future reference or analysis. This research paper introduces ANPR system which is designed to optimize accuracy, efficiency, and ease of implementation which includes combination of Python programming language, YOLOv8 (You Only Look One-level), and EasyOCR, the proposed system addresses the complexities associated with detection of license plate and recognition in diverse real-world situations. Core of the system lies in the adoption of YOLOv8, an object detection model renowned for its real-time capabilities and high accuracy. EasyOCR, a user-friendly Optical Character Recognition (OCR) library, is seamlessly integrated into the ANPR system. This addition enhances the system's ability to accurately extract alphanumeric information from detected license plates, bridging the gap between detection and recognition phases. Due to this the system ensures efficient noise reduction, image segmentation, and overall improvement in the quality of input images, contributing to the system's reliability. The paper presents an in-depth evaluation of the ANPR system's performance through datasets. Additionally, the research explores potential applications of the ANPR system in real-world scenarios, emphasizing its applicability in traffic management, law enforcement, and security systems. © 2024 IEEE.

关键词： Noise abatement

来源：评论

学校读者我要写书评

暂无评论

An Intelligent Innovation of Electrochemical Energy Based Smart Industrial Automation 2

An Intelligent Innovation of Electrochemical Energy Based Sm...

引用

2nd IEEE International Conference on Distributed Computing and Electrical Circuits and Electronics, ICDCECE 2023

作者： Kumar, N. Shantha Karthikeyan, S. Department of Computer Science and Engineering Bangalore India

ISBN: (纸本)9798350347456

Electrochemical energy based smart industrial automation uses electrochemical energy generated from chemical reactions to power and control industrial processes. This energy is generated through the use of electrolyte and electrodes, which convert chemical energy into electrical energy. This energy can then be used to power and control industrial machines, such as industrial robots and automated assembly lines. Additionally, this energy can be used to monitor, regulate, and control processes, such as temperature and pressure, within an industrial environment. This technology offers numerous advantages over traditional methods of powering and controlling industrial operations. Firstly, it is more efficient and cost effective than traditional methods. Secondly, it has the potential to reduce energy consumption, improve efficiency, and increase productivity. Finally, it is environmentally friendly, as it does not produce harmful emissions or waste materials. The use of electrochemical energy based smart industrial automation is the way of the future for industrial operations. The potential of this technology is immense, and the advantages it can bring to industrial operations are numerous. With the right implementation and application, this technology has the potential to revolutionize how industrial processes are operated and managed. © 2023 IEEE.

关键词： Electrolytes

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：