Enhanced Hybrid Approach for Multi-Class DDoS Attack Detection and Classification in Software-Defined Networks Using Remote Sensing and Data Analytics

Remote Sensing in Earth Systems Sciences, Год журнала: 2025, Номер unknown

Опубликована: Фев. 28, 2025

Язык: Английский

---

Classification and severity assessment of disaster losses based on multi-modal information in social media

Information Processing & Management, Год журнала: 2025, Номер 62(5), С. 104179 - 104179

Опубликована: Апрель 9, 2025

Язык: Английский

---

A machine learning-based intrusion detection framework with labeled dataset generation for IEEE 802.1 time-sensitive networking

Journal of Systems Architecture, Год журнала: 2025, Номер unknown, С. 103408 - 103408

Опубликована: Апрель 1, 2025

Язык: Английский

---

Metaparameter optimized hybrid deep learning model for next generation cybersecurity in software defined networking environment

Scientific Reports, Год журнала: 2025, Номер 15(1)

Опубликована: Апрель 23, 2025

Язык: Английский

---

A DDoS Attack Detection Method Based on IQR and DFFCNN in SDN

Journal of Network and Computer Applications, Год журнала: 2025, Номер unknown, С. 104203 - 104203

Опубликована: Апрель 1, 2025

Язык: Английский

---

Traffic Feature Selection and Distributed Denial of Service Attack Detection in Software-Defined Networks Based on Machine Learning

Sensors, Год журнала: 2024, Номер 24(13), С. 4344 - 4344

Опубликована: Июль 4, 2024

As 5G technology becomes more widespread, the significant improvement in network speed and connection density has introduced challenges to security. In particular, distributed denial of service (DDoS) attacks have become frequent complex software-defined (SDN) environments. The complexity diversity networks result a great deal unnecessary features, which may introduce noise into detection process an intrusion system (IDS) reduce generalization ability model. This paper aims improve performance IDS networks, especially terms accuracy. It proposes innovative feature selection (FS) method filter out most representative distinguishing features from traffic data robustness efficiency IDS. To confirm suggested method's efficacy, this uses four common machine learning (ML) models evaluate InSDN, CICIDS2017, CICIDS2018 datasets conducts real-time DDoS attack on simulation platform. According experimental results, FS technique match requirements for high reliability while also drastically cutting down time preserving or improving

Язык: Английский

---

Enhanced DDoS Detection in Software Defined Networking Using Ensemble-Based Machine Learning

Опубликована: Май 2, 2024

The burgeoning adoption of Software Defined Networking (SDN) has revolutionized network management, yet it introduces unprecedented challenges, notably the susceptibility to Distributed Denial-of-Service (DDoS) attacks. Recognizing this imperative, our research delves into fortifying SDN security, proposing a novel approach that marries machine learning prowess with intricacies architecture. This study endeavors bolster DDoS detection within environments, strategically leveraging an ensemble-based Random Forest (RF) algorithm and Recursive Feature Elimination. overarching goal is enhance efficacy security measures, providing dynamic defense against evolving threats. An implementation process unfolds through comprehensive data preprocessing, featuring strategic selection key features via Central application algorithm, which been rigorously trained using dedicated dataset tailored for Networking. A assessment follows, where critical performance indicators such as Recall, Accuracy, Precision, F-1 Score, Area Under Curve (AUC) substantiate reliability method. outcome paradigm shift in SDN. Our RF not only exhibits commendable accuracy but also outperforms traditional methods across metrics. feature contributes heightened efficiency bolsters overall resilience networks incursions. Beyond confines conventional methodologies, model, attaining almost 100% accuracy, heralds milestone security.

Язык: Английский

---

Evaluating Machine Learning and Deep Learning Models for Enhanced DDoS Attack Detection

Mathematical Modelling and Engineering Problems, Год журнала: 2024, Номер 11(2), С. 493 - 499

Опубликована: Фев. 27, 2024

In the realm of network security, distributed denial service (DDoS) attacks pose a formidable threat, often resulting in operational disruptions and substantial financial losses.Traditional methods for DDoS detection struggle to adapt rapidly evolving attack methodologies, leading compromised robustness accuracy.The urgent need more sophisticated mechanisms is evident.This investigation explores effectiveness advanced deep learning ensemble machine models identifying threats.A comprehensive approach employed, leveraging multitude base classifiers construct robust precise system.Integral this study application convolutional neural networks (CNNs), variant, adept at discerning complex patterns relationships within traffic data.These excel autonomously extracting pertinent features, thereby enabling efficient intricate attacks.A critical step methodology involves collection dataset, encompassing both normal scenarios.This dataset undergoes rigorous preprocessing enhancement phase ensure balanced representative training set.Subsequently, augmented data utilized train proposed models.The performance these evaluated using variety metrics.Results from experiments demonstrate that significantly surpass existing techniques detection.By amalgamating strengths various networks, method enhances precision resistance diverse variations.Comparative analyses reveal impressive metrics, with such as CNN 1D Alex Net achieving high levels accuracy precision.The outcomes underscore superiority prevalent novel patterns, highlighting their potential countering cyber threats.The findings advocate enhanced adaptability detection, marking significant advancement field.

Язык: Английский

---

Effective DDoS attack detection in software-defined vehicular networks using statistical flow analysis and machine learning

PLoS ONE, Год журнала: 2024, Номер 19(12), С. e0314695 - e0314695

Опубликована: Дек. 18, 2024

Vehicular Networks (VN) utilizing Software Defined Networking (SDN) have garnered significant attention recently, paralleling the advancements in wireless networks. VN are deployed to optimize traffic flow, enhance driving experience, and ensure road safety. However, vulnerable Distributed Denial of Service (DDoS) attacks, posing severe threats contemporary Internet landscape. With surge traffic, this study proposes novel methodologies for effectively detecting DDoS attacks within Software-Defined (SDVN), wherein attackers commandeer compromised nodes monopolize network resources, disrupting communication among vehicles between infrastructure. The proposed methodology aims to: (i) analyze statistical flow compute entropy, (ii) implement Machine Learning (ML) algorithms SDN Intrusion Detection Systems Things (IoT) environments. Additionally, approach distinguishes reconnaissance, (DoS), by addressing challenges imbalanced overfitting dataset traces. One integration is managing computational load ensuring real-time performance. ML models, especially complex ones like Random Forest, require substantial processing power, which necessitates efficient data handling possibly leveraging edge computing resources reduce latency. Ensuring scalability maintaining high detection accuracy as grows evolves another critical challenge. By a minimal subset features from given dataset, comparative conducted determine optimal sample size maximizing model accuracy. Further, evaluates impact various attributes on performance thresholds. K -nearest Neighbor, Logistic Regression supervised classifiers assessed using BoT-IoT dataset. results indicate that Forest classifier achieves superior metrics, with Precision, F1-score, Accuracy, Recall rates 92%, 91%, 90%, respectively, over five iterations.

Язык: Английский

---

Enhancing Network Security in IoT Applications through DDoS Attack Detection Using ML

مجلة کلية دار العلوم, Год журнала: 2024, Номер 49(3)

Опубликована: Янв. 1, 2024

A significant issue that affects contemporary network infrastructures is the Distributed Denial of Service (DDoS) attack, which presents serious dangers to organizations, people, and even governments. By flooding a target server, network, or website with deceptive traffic, this kind cyberattack seeks prevent it from providing services legitimate users. For those in charge maintaining security, prevalence sophistication these attacks have both grown significantly. DDoS potential lead financial losses service interruptions. Anomaly-based systems, traffic filtering, Machine Learning (ML) algorithms are employed spot them lessen effects their influence. To successfully defend against attacks, it's imperative proactive attitude keep up new security risks. In study, CICDDoS 2019 dataset was used train evaluate different ML algorithms, including Stochastic Gradient Boosting (SGB), Decision Tree (DT), K Nearest Neighbour (K-NN), Naive Bayes (NB), Support Vector (SVM), Logistic Regression (LR). The results showed all effectively detected high accuracy, precision, recall. However, SVM algorithm outperformed other techniques, achieving highest accuracy =0.99%.

Язык: Английский

---