Performance evaluation of deep learning techniques for DoS attacks detection in wireless sensor network

Abstract

Wireless sensor networks (WSNs) are increasingly being used for data monitoring and collection purposes. Typically, they consist of a large number of sensor nodes that are used remotely to collect data about the activities and conditions of a particular area, for example, temperature, pressure, motion. Each sensor node is usually small, inexpensive, and relatively easy to deploy compared to other sensing methods. For this reason, WSNs are used in a wide range of applications and industries. However, WSNs are vulnerable to different kinds of security threats and attacks. This is primarily because they are very limited in resources like power, storage, bandwidth, and processing power that could have been used in developing their defense. To ensure their security, an effective Intrusion detection system (IDS) need to be in place to detect these attacks even under these constraints. Today, traditional IDS are less effective as these malicious attacks are becoming more intelligent, frequent, and complex. Denial of service (DOS) attack is one of the main types of attacks that threaten WSNs. For this reason, we review related works that focus on detecting DoS attacks in WSN. In addition, we developed and implemented several Deep learning (DL) based IDS. These systems were trained on a specialized dataset for WSNs called WSN-DS in detecting four types of DoS attacks that affects WSNs. They include the Blackhole, Grayhole, Flooding, and Scheduling attacks. Finally, we evaluated and compared the results and we discuss possible future works.

Hybrid Approach to Classification of DDoS Attacks on a Computer Network Infrastructure

“…The model is noted for its reduced processing overhead, a validated solution on resource constraint hardware and achieved an accuracy of 0.9888 -0.9987 among the different datasets used to train the model. This study is supported by [10] in their study which sought to develop efficient deep learning-based algorithm for the detection of DDoS attacks in wireless sensor networks, reporting CNN as the best classifier which outperformed the other algorithms with an accuracy rate of 98.79%. The other algorithms, outperformed by the CNN classifier were DNN, RNN and CNN-RNN, trained on the WSN-DS.…”

“…The deep neural networks, with their capability to learn complex patterns in data makes them very effective models to deploy. In this review, [10] proposed model is one such model which showed a good classification accuracy with CNN classifier. Nonetheless, the hybrid model deployed in that study could yield an optimal outcome if feature selection is done for dimensionality reduction on the dataset coupled with extensive hyperparameter tuning.…”

“…Examples are studies conducted by Khempetch et al [8], Lopes et al [9], and [10] which deployed models such as Dense Neural Network (DNN), Long Short-Term Memory (LSTM), Convolutional Neural Networks (CNN) and Recurrent Neural Network (RNN) trained on a particular dataset, compare accuracies and rate of detection. From the various models deployed by the various researchers, there is still more to be done in DDoS attacks classification and mitigation as more and more sophisticated attacks are deployed by attackers every day.…”

“…Nonetheless, few researchers have proposed the use of hybrid model that utilizes more than one DL technique in the detection of DDoS attacks. Examples of such papers are the study by Salmi and Oughdir [10] and Sumathi et al [11] by combining CNN and LSTM in their study. These studies failed to apply feature selection techniques to include only important features to train the model which could yield much higher accuracy compared to what was achieved.…”

Data aggregation algorithm for wireless sensor networks with different initial energy of nodes

“…Due to the specific characteristics of node distribution and data transmission in sensor networks, attackers primarily launch attacks from two directions ( Yousefpoor et al, 2021 ; Salmi & Oughdir, 2023 ; Cao et al, 2022 ): Eavesdropping attacks are a prevalent form of attack in wireless sensor networks. In WSNs, where data transmission occurs wirelessly between nodes, attackers can intercept and eavesdrop on the communication channel.…”