Vehicular Network Security Through Optimized Deep Learning Model with Feature Selection Techniques DOI Creative Commons

Fida Muhammad Khan,

Taj Rahman, Asim Zeb

и другие.

Опубликована: Дек. 31, 2024

In recent years, vehicular ad hoc networks (VANETs) have faced growing security concerns, particularly from Denial of Service (DoS) and Distributed (DDoS) attacks. These attacks flood the network with malicious traffic, disrupting services compromising resource availability. While various techniques been proposed to address these threats, this study presents an optimized framework leveraging advanced deep-learning models for improved detection accuracy. The Intrusion Detection System (IDS) employs Convolutional Neural Networks (CNN), Long Short-Term Memory (LSTM), Deep Belief (DBN) alongside robust feature selection techniques, Random Projection (RP) Principal Component Analysis (PCA). This extracts analyzes significant features using a publicly available application-layer DoS attack dataset, achieving higher accuracy than traditional methods. Experimental results indicate that combining CNN, LSTM networks, DBN like PCA in classification performance, 0.994, surpassing state-of-the-art machine learning models. novel approach enhances reliability safety vehicle communications by providing efficient, real-time threat detection. findings contribute significantly VANET security, laying foundation future advancements connected protection.

Язык: Английский

Vehicular Network Security Through Optimized Deep Learning Model with Feature Selection Techniques DOI Creative Commons

Fida Muhammad Khan,

Taj Rahman, Asim Zeb

и другие.

Опубликована: Дек. 31, 2024

In recent years, vehicular ad hoc networks (VANETs) have faced growing security concerns, particularly from Denial of Service (DoS) and Distributed (DDoS) attacks. These attacks flood the network with malicious traffic, disrupting services compromising resource availability. While various techniques been proposed to address these threats, this study presents an optimized framework leveraging advanced deep-learning models for improved detection accuracy. The Intrusion Detection System (IDS) employs Convolutional Neural Networks (CNN), Long Short-Term Memory (LSTM), Deep Belief (DBN) alongside robust feature selection techniques, Random Projection (RP) Principal Component Analysis (PCA). This extracts analyzes significant features using a publicly available application-layer DoS attack dataset, achieving higher accuracy than traditional methods. Experimental results indicate that combining CNN, LSTM networks, DBN like PCA in classification performance, 0.994, surpassing state-of-the-art machine learning models. novel approach enhances reliability safety vehicle communications by providing efficient, real-time threat detection. findings contribute significantly VANET security, laying foundation future advancements connected protection.

Язык: Английский

Процитировано

0