Denial of Service Attack Detection and Mitigation using Ensemble based ML in Software Defined Network

Опубликована: Июнь 5, 2024

Язык: Английский

---

Detecting DDoS Attacks using Machine Learning: Survey

Journal of Al-Qadisiyah for Computer Science and Mathematics, Год журнала: 2024, Номер 16(2)

Опубликована: Июнь 30, 2024

Phishing attacks have increased dramatically in recent years affecting many areas of society. attempts often use DDoS to flood a server with too requests, overwhelming it. represent major threat cybersecurity and pose significant risk computer networks. Creating solid defense system against these is essential but complex due the wide range attack methods networks communication protocols. Ransom demands, revenge, rivalry, or other motives may trigger attacks. This survey discusses attacks, advantages disadvantages detecting using machine deep learning, framework for detection learning learning. And their classifiers detect Furthermore, we explore datasets used related works. research necessary because are diverse

Язык: Английский

---

iCuSMAT-DT: A Two-Tier Detection Mechanism for High-Rate DDoS Attacks and Discriminating Benign Flash Traffic in Software-Defined Networks

Опубликована: Май 28, 2024

Язык: Английский

---

SDN-IDS: A Deep Learning Model for Detecting DDoS Attacks

International Journal of Electronics and Communication Engineering, Год журнала: 2024, Номер 11(6), С. 122 - 136

Опубликована: Июнь 30, 2024

The centralization of control and programmability in Software-Defined networking (SDN) have enhanced network functionality, but they also made it vulnerable to security threats like Distributed Denial Service (DDoS) attacks, which may target both the data planes. To detect mitigate DDoS attacks SDN's plane, a novel attack detection model is proposed this research. developed utilizing Deep Learning (DL) metaheuristic optimization algorithms. key objective research classify plane layer. model, SDN-Intrusion Detection System (SDN-IDS), includes four main phases: collection, preprocessing, feature selection classification. Initially, InSDN dataset collected train evaluate model. preprocessing phase cleaning, transformation, normalization processes. After Binary variant Ant Lion Optimizer (BALO) algorithm used for selecting optimal features from input dataset. Based on selected features, Attention-Based Bidirectional Long Short-Term Memory (ABiLSTM) implemented improve classification accuracy ABiLSTM Bayesian Optimization (BO) technique applied hyperparameter tuning. SDN-IDS assessed terms rate, accuracy, f1-score, FAR, precision. analysis, attained 99.61% 99.53% 99.70% precision, 99.58% 0.46% FAR. Overall, these results indicate that SDNIDS effectively detects classifies within SDN layer with higher while maintaining low FAR compared existing models.

Язык: Английский

---

IOTASDN: IOTA 2.0 Smart Contracts for Securing SDN Ecosystem

Опубликована: Июль 15, 2024

Software-Defined Networking (SDN) has revolutionized network management by providing unprecedented flexibility, control, and efficiency. However, its centralized architecture introduces critical security vulnerabilities. This paper presents an innovative approach to securing SDN environments using IOTA 2.0 smart contracts. The proposed system leverages the Tangle, a directed acyclic graph (DAG) structure, enhance scalability efficiency while eliminating transaction fees reducing energy consumption. We introduce three contracts—Authority, Access Control, DoS Detector—to ensure secure operations, prevent unauthorized access, mitigate denial-of-service attacks. Through comprehensive simulations Mininet ShimmerEVM Test Network, we demonstrate efficacy of our in enhancing security. Our findings highlight potential contracts provide robust, decentralized solution for environments, paving way further integration blockchain technologies management.

Язык: Английский

---