WOA-DNN for Intelligent Intrusion Detection and Classification in MANET Services

Abstract

Mobile ad-hoc networks (MANET) are garnering a lot of attention because of their potential to provide low-cost solutions to real-world communications. MANETs are more vulnerable to security threats. Changes in nodes, bandwidth limits, and centralized control and management are some of the characteristics. IDS (Intrusion Detection System) are the aid for detection, determination, and identification of illegal system activity such as use, copying, modification, and destruction of data. To address the identified issues, academics have begun to concentrate on building IDS-based machine learning algorithms. Deep learning is a type of machine learning that can produce exceptional outcomes. This study proposes that WOA-DNN be used to detect and classify incursions in MANET (Whale Optimized Deep Neural Network Model) WOA (Whale Optimization Algorithm) and DNN (Deep Neural Network) are used to optimize the preprocessed data to construct a system for classifying and predicting unanticipated cyber-attacks that are both effective and efficient. As a result, secure data transport to other nodes is provided, preventing intruder attacks. The invaders are found using the (Machine Learning) ML-IDS and WOA-DNN methods. The data is reduced in dimensionality using Principal Component Analysis (PCA), which improves the accuracy of the outputs. A classifier is used in forward propagation to predict whether a result is normal or malicious. To compare the traditional and proposed models' effectiveness, the accuracy of classification, detection of the attack rate, precision rate, and F-Measure, Recall are utilized. The proposed WOA-DNN model has higher assessment metrics and a 99.1% accuracy rate. WOA-DNN also has a greater assault detection rate than others, resulting in fewer false alarms. The classification accuracy of the proposed WOA-DNN model is 99.1%.

A Novel CNN Model with Dimensionality Reduction for WSN Intrusion Detection

“…Edwin Singh and Celestin Vigila [27] used WOA (Whale Optimization Algorithm) and DNN (Deep Neural Network) to optimize the pre-processed data to build a system for detecting and classifying incursions in MANET (Whale Optimized Deep Neural Network Model), with the goal of predicting unanticipated cyber-attacks. As a result, intruder-proof data transfer to other nodes is made possible.…”

“…Following training, the network is tested on an independent dataset to gauge its ability to detect outliers. Improve the CNN's ability to spot network abnormalities by expanding the size and diversity of the training dataset, tweaking hyperparameters like learning rate and regularization, and using data augmentation techniques to add variety to the training data [26,27].…”

Enhancing MANET Security: A Watch Dog Routing Algorithm Approach for Intruder and Black Hole Attack Detection

“…Intruder is a kind of attacker who tries to hold the packer or make a delay on forwarding the packet, whereas black hole attacker is a category of the attacker who drops the packers rather than forwarding to the next hope. Many research work was carried out for detection and preventing Intruder and Attackers in the MANET by introducing the novel techniques like deep learning based [2], trust-based [3], intrusion detection [4], crypto-based [5], and destination sequence number (DSN) [6] based methods and fuzzy logic [7], but still the MANET is lags on security.…”

“…Fuzzy based PCA-FELM scheme [4] for detecting intruder in MANET, Vijayalakshmi et al [8] proposed the IDS system based on the novel game theory with neighbor trust table approach which classifies the nodes in to defect node or cooperate node approach they achieved packet delivery ratio in 42%. Sultan et al [9] used deep learning based ANN technique to make detection of IDS.…”

Application of GA-WELM Model Based on Stratified Cross-Validation in Intrusion Detection

“…The meta-heuristic optimization algorithm uses an optimization model to iterate the hyperparameter values for a limited number of times in a certain range, and finally gets the optimal solution. Designing a good fitness function is very important for the optimization ability of meta-heuristic optimization algorithm [23].…”