检索结果-内蒙古大学图书馆

Leveraging blockchain and machine learning to counter DDoS attacks over IoT network

Multimedia Tools and Applications 2025年第1期84卷 317-341页

作者： Kumari, Pooja Jain, Ankit Kumar Seth, Arpit Raghav Department of Computer Engineering National Institute of Technology Haryana Kurukshetra136119 India

The paper presents an approach for detecting Distributed Denial of Service (DDoS) attacks using machine learning and blockchain technology. With the increasing complexity and frequency of DDoS attacks, network security faces significant challenges. The proposed approach aims to detect DDoS attacks in a real-time environment by applying machine learning algorithms and storing false IP addresses in a blockchain ledger. The decentralized nature of the blockchain network makes it extremely difficult for attackers to tamper with the stored information. By utilizing blockchain to store blacklisted IP addresses and their timestamps, the approach ensures the integrity and correctness of the data. The performance of the proposed approach is evaluated on a combination of CSE-CIC-IDS2018-AWS, CICIDS2017, and CICDoS2016 datasets, demonstrating its effectiveness. The Random Forest model outperforms other models by achieving 99.34% accuracy, indicating that the proposed method accurately identifies DDoS attacks in real-time and securely stores the false IP addresses in a transparent blockchain ledger. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Multi-modal feature fusion for object detection using neighbourhood component analysis and bounding box regression

引用

International Journal of Business Intelligence and Data Mining 2023年第1期23卷 73-99页

作者： Dhillon, Anamika Verma, Gyanendra K. Department of Computer Engineering NIT Kurukshetra India

Object detection has gained remarkable interest in the research area of computer vision applications. This paper presents an efficient method to detect multiple objects and it contains two parts: 1) training phase;2) testing phase. During the training phase, firstly we have exploited two convolutional neural network models namely Inception-ResNet-V2 and MobileNet-V2 for feature extraction and then we fuse the features extracted from these two models by using concatenation operation. To acquire a more compact presentation of features, we have utilised neighbourhood component analysis (NCA). After that, we classify the multiple objects by using SVM classifier. During the testing phase, to detect various objects in an image, a bounding box regression module is proposed by applying LSTM. We have performed our experiments on two datasets: wild animal camera trap and gun. In particular, our method achieves an accuracy rate of 97.80% and 97.0% on wild animal camera trap and gun datasets respectively. Copyright © 2023 Inderscience Enterprises Ltd.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Limits of Depth: Over-Smoothing and Over-Squashing in GNNs

引用

Big Data Mining and Analytics 2024年第1期7卷 205-216页

作者： Aafaq Mohi ud din Shaima Qureshi Department of Computer Science and Engineering National Institute of Technology SrinagarSrinagar 190006India

Graph Neural Networks(GNNs)have become a widely used tool for learning and analyzing data on graph structures,largely due to their ability to preserve graph structure and properties via graph representation ***,the effect of depth on the performance of GNNs,particularly isotropic and anisotropic models,remains an active area of *** study presents a comprehensive exploration of the impact of depth on GNNs,with a focus on the phenomena of over-smoothing and the bottleneck effect in deep graph neural *** research investigates the tradeoff between depth and performance,revealing that increasing depth can lead to over-smoothing and a decrease in performance due to the bottleneck *** also examine the impact of node degrees on classification accuracy,finding that nodes with low degrees can pose challenges for accurate *** experiments use several benchmark datasets and a range of evaluation metrics to compare isotropic and anisotropic GNNs of varying depths,also explore the scalability of these *** findings provide valuable insights into the design of deep GNNs and offer potential avenues for future research to improve their performance.

关键词： Graph Neural Networks(GNNs) learning on graphs over-smoothing over-squashing isotropic-GNNs anisotropic-GNNs

来源：评论

学校读者我要写书评

暂无评论

A lightweight and efficient model for botnet detection in IoT using stacked ensemble learning

引用

Soft Computing 2025年第1期29卷 89-101页

作者： Esmaeilyfard, Rasool Shoaei, Zohre Javidan, Reza Department of Computer and Information Technology Engineering Shiraz University of Technology Shiraz Iran

Efficient botnet detection is of great security importance and has been the focus of researchers in recent years. Botnet detection is also a difficult task due to the difficulty in distinguishing it from normal traffic. At the same time, detecting these botnets require a lot of computation resources using traditional methods and this limitation makes it even more difficult to detect them on Internet of Things (IoT) devices. Considering the massive IoT data, an efficient and lightweight approach for detecting and predicting IoT botnet attacks is required. In this paper, multiple lightweight machine learning methods including a deep Multilayer Perceptron (MLP) method and a Random Forest (RF) method are integrated into a stacked ensemble learning model to detect botnet attacks in IoT devices. This integration is based on applying lasso regression on features and utilizing a logistic regression in ensemble learning, which leads to increasing the accuracy of botnet detection and reducing its computational complexity. The performance evaluation of the proposed model is examined from two perspectives: accuracy and lightweight characteristics;and for this purpose, a real-world UNSW (BoT-IoT) dataset is used. A comparative study with competitive neural network methods demonstrates that our approach delivers a better outcome. Experimental results reveal that this method has a higher efficiency in all metrics than competing methods including accuracy, precision, recall, and F1 score with values of 99.3%, 99.2%, 99%, and 99.1%, respectively. Besides, the results showed that the proposed method requires at least 36% less CPU and 38% less memory compared to the competing methods, which makes the proposed method to be suitable for IoT devises with limited resources. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2025.

关键词： Bot (Internet)

来源：评论

学校读者我要写书评

暂无评论

TPUXtract: An Exhaustive Hyperparameter Extraction Framework

IACR Transactions on Cryptographic Hardware and Embedded Sys...

引用

IACR Transactions on Cryptographic Hardware and Embedded Systems 2025年第1期2025卷 78-103页

作者： Kurian, Ashley Dubey, Anuj Yaman, Ferhat Aysu, Aydin Department of Electrical and Computer Engineering North Carolina State University United States

Model stealing attacks on AI/ML devices undermine intellectual property rights, compromise the competitive advantage of the original model developers, and potentially expose sensitive data embedded in the model’s behavior to unauthorized parties. While previous research works have demonstrated successful side-channelbased model recovery in embedded microcontrollers and FPGA-based accelerators, the exploration of attacks on commercial ML accelerators remains largely unexplored. Moreover, prior side-channel attacks fail when they encounter previously unknown models. This paper demonstrates the first successful model extraction attack on the Google Edge Tensor Processing Unit (TPU), an off-the-shelf ML accelerator. Specifically, we show a hyperparameter stealing attack that can extract al l layer configurations including the layer type, number of nodes, kernel/filter sizes, number of filters, strides, padding, and activation function. Most notably, our attack is the first comprehensive attack that can extract previously unseen models. This is achieved through an online template-building approach instead of a pre-trained ML-based approach used in prior works. Our results on a black-box Google Edge TPU evaluation show that, through obtained electromagnetic traces, our proposed framework can achieve 99.91% accuracy, making it the most accurate one to date. Our findings indicate that attackers can successfully extract various types of models on a black-box commercial TPU with utmost detail and call for countermeasures. © 2025, Ruhr-University of Bochum. All rights reserved.

关键词： Network security

来源：评论

学校读者我要写书评

暂无评论

Improved IVUS and VH-IVUS image segmentation using a hybrid approach based on active counter model and clustering algorithms

引用

Multimedia Tools and Applications 2025年第16期84卷 17051-17082页

作者： Rezaei, Zahra Department of Computer Engineering Marvdasht Branch Islamic Azad University Marvdasht Iran

Heart attack due to the vulnerable atherosclerotic plaque is one of the most common causes of death in the world. One of the imaging modalities in the coronary artery is Virtual Histology Intravascular Ultrasound (VH-IVUS);however, segmentation of overlapped plaque components can be challenging. Therefore, this research study proposes a new approach based on the level set method to detect the plaque border in VH-IVUS images accurately. Three classifiers, including support vector machine (SVM), k-nearest neighbor, and proposed Selecting Nearest Pixel (SNP), were hybridized with FCM to enhance the VH-IVUS segmentation. Moreover, for segmentation and plaque extraction in IVUS images, a hybrid of the snake approach and fuzzy clustering method is proposed. Geometric features were extracted from VH-IVUS and IVUS images. The proposed hybrid model used 599 images obtained from 10 patients. The validation for the proposed segmentation model showed an average of 0.96 for the silhouette validity index. The SVM classifier is used to classify the TCFA and Non-TCFA plaques using VH-IVUS and IVUS features. The accuracy of the hybrid feature set was obtained over 0.99 for TCFA plaque. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Impulse Noise Suppression in Color Images Using Median Filter and Deep Learning

引用

Recent Advances in computer Science and Communications 2023年第6期16卷 56-68页

作者： Ashpreet Biswas, Mantosh Department of Computer Engineering NIT Kurukshetra India

Refining the quality of a noisy image is essential for many image applications. Various median filter variants have been introduced to suppress various noises, but they have their own limitations when detecting noise and restoring noise-free images. Denoising convolutional neural networks (DnCNNs), primarily developed for Gaussian noise removal, are influential nonlinear mapping models in image processing. After alterations in training data, they can be used to suppress other noise with outstanding results. This article suggests a frequency median filter method combined with deep learning for color images polluted by Salt and Pepper (SnP) noise. The analysis presented in this paper has primarily used a frequency median filter to suppress impulse noise wherein the restored value for the center pixel is evaluated by the frequency median rather than the traditional median. After which, the pretrained denoising convolutional neural network is hired to suppress the remaining noise and attain the output image finally. With a visual comparative study, simulation results on the taken test images show that the proposed method surpasses de-noising methods in terms of PSNR, SSIM, NMSE, Entropy, IEF, NCC, PCC and Running Time. © 2023 Bentham Science Publishers.

关键词： Median filters

来源：评论

学校读者我要写书评

暂无评论

Advanced brain tumor analysis: a novel strategy for segmentation and classification using modern computational methods

引用

Neural Computing and Applications 2025年第6期37卷 4697-4731页

作者： Reis, Hatice Catal Turk, Veysel Department of Geomatics Engineering Gumushane University Gumushane29000 Turkey Department of Computer Engineering University of Harran Sanliurfa63000 Turkey

Despite their low incidence, brain tumors are one of the most invasive cancer types, constituting a significant burden of death and disease in all age groups. Early and accurate diagnosis of brain tumors plays a vital role in reducing mortality rates. The heterogeneous nature of brain tumors and the diversity of tumor lesions may make it difficult for radiologists to make the right decision in the manual diagnosis process. This study proposes the use of machine learning methods for the classification of brain tumors (pituitary, meningioma, and glioma) and the use of metaheuristic algorithms graph theory, and random walker algorithms in the segmentation of brain tumors. The classification performed with the proposed method obtained an overall accuracy rate of 98.33%. In addition, the classification accuracy of 99.50%, 99.50%, 98.67%, and 99.00% was achieved for no tumor, pituitary, meningioma, and glioma, respectively. Experiments in the segmentation process show that metaheuristic algorithms and max-flow graph cut approach produce successful results. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Heuristic algorithms

来源：评论

学校读者我要写书评

暂无评论

DenseRSE-ASPPNet: An Enhanced DenseNet169 with Residual Dense Blocks and CE-HSOA-Based Optimization for IoT Botnet Detection

引用

International Journal of Advanced computer Science and Applications 2025年第4期16卷 688-699页

作者： Khan, Mohd Abdul Rahim Department of Electrical Engineering and Computer Science A’sharqiyah University IBRA-400 Oman

The growing prevalence of Internet of Things (IoT) devices has heightened vulnerabilities to botnet-based cyberattacks, necessitating robust detection mechanisms. This paper proposes DenseRSE-ASPPNet, an advanced deep learning framework for botnet detection, incorporating comprehensive preprocessing, feature extraction, and optimization. The preprocessing pipeline includes data cleaning and Min-Max normalization to ensure high-quality input data. The DenseNet169 backbone is enhanced with Residual Squeeze-and-Excitation (RSE) blocks for channel-wise attention recalibration and Atrous Spatial Pyramid Pooling (ASPP) for capturing multi-scale spatial patterns, enabling effective feature extraction. Hyperparameter optimization is performed using the Cyclone-Enhanced Humboldt Squid Optimization Algorithm (CE-HSOA), which balances global exploration and local exploitation, ensuring faster convergence and enhanced robustness. Experimental results demonstrate the superior performance of the proposed framework, achieving 99.00 per cent accuracy, 96.40 per cent sensitivity, and 99.95 per cent specificity, significantly minimizing false positives and false negatives. The proposed DenseRSE-ASPPNet provides an efficient, scalable, and effective solution for mitigating botnet threats in IoT environments. © (2025), (Science and Information Organization). All rights reserved.

关键词： Feature Selection

来源：评论

学校读者我要写书评

暂无评论

A novel cluster based reliable security enhancement in FANET directed by game theory

引用

Soft Computing 2025年第2期29卷 1091-1106页

作者： Gupta, Shikha Sharma, Neetu Department of Computer Science Engineering College Ajmer Rajasthan Ajmer305001 India

The emergence of interconnected UAVs has given rise to the creation of flying ad hoc networks (FANETs) aimed at efficiently facilitating network-dependent services. However, FANET encountered considerable challenges in achieving reliability due to security issues influenced by the existence of malicious nodes. These nodes continuously engage in communication and present a significant threat. These issues are precisely addressed in this article by introducing a novel methodology enhancing network security through a game theory-driven decision tree approach. The proposed strategy involves the implementation of a cluster mechanism based on path similarity techniques. Additionally, an optimized strategy put forth to minimize cluster overhead. Comparing with state-of-the-art protocols in identifying malicious nodes within the network, the results indicate a notable enhancement averaging at 52.84%. Moreover, in aspects such as delay reduction, precision rate increase, and message drop minimization, the experimental outcomes exhibit average improvements of 42.17%, 65.24%, and 46.63%, respectively. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2025.

关键词： Decision trees

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：