Correlation between Deep Neural Network Hidden Layer and Intrusion Detection Performance in IoT Intrusion Detection System

Abstract

As the Internet of Things (IoT) continues to grow, a vast amount of data is generated. The IoT environment is quite sensitive to security challenges because personal information may be leaked or sensor data may be manipulated, which could cause accidents. Because traditional intrusion detection system (IDS) studies are often designed to work well on datasets, it is unknown whether they would work well in a changing network environment. In addition, IDSs for protecting IoT environments have been studied, but their performance was verified using datasets unrelated to the IoT, so it is not known whether the performance would be effective in an IoT environment. In this study, we propose an intrusion detection hyperparameter control system (ID-HyConSys) that automates the IDS using proximal policy optimization (PPO) to solve these problems and reliably protect the IoT environment. ID-HyConSys consists of an intrusion detection module consisting of a deep neural network (DNN) feature extractor that extracts efficient features from a changing network environment, a k-means cluster that clusters the extracted data, and a PPO agent that automates the IDS through learning and control. Through experimentation, it was confirmed that the hidden layer configuration, the number of feature extractions by the DNN feature extractor, and the number of clusters in the k-means cluster significantly affected the intrusion detection performance. The PPO directly controls these hyperparameters and determines the optimized value itself. The performance of ID-HyConSys was evaluated using the CICIDS2017 and MQTTset datasets. An F1-score of 0.9707 on CICIDS2017 and an F1-score of 0.9973 on the MQTTset were obtained. Finally, we merged the two datasets and obtained an F1-score of 0.9901. The superiority of the ID-HyConSys proposed in this study was confirmed because ID-HyConSys showed high performance on each dataset and, at the same time, very high performance on complex merged datasets. ID-HyConSys is expected to protect the IoT environment more quickly and safely by automatically learning network changes and adjusting the intrusion detection module accordingly.

Enhanced Black Widow Optimization With Hybrid Deep Learning Enabled Intrusion Detection in Internet of Things-Based Smart Farming

“…An extremely expandable Deep Neural Network (DNN) is projected to IoT networks which is proficient in headstrong recognition of the IoT botnet threats. In [13], an ID hyper-parameter control system (HyConSys) which systematizes the IDS employing Proximal Policy Optimization (PPO) is projected. ID-HyConSys consists of a DNN features separator that separates effective features.…”

Intrusion Detection Using Pareto Optimality Based Grasshopper Optimization Algorithm with Stacked Autoencoder in Cloud and IoT Networks

“…Han [16] developed an effective automated intrusion detection system based on proximal policy optimization (PPO) for protecting the IoT environments against cyber-attackers. At first, the discriminative features were obtained from the acquired database by implementing a deep neural network (DNN), and then the similar extracted features were clustered by using the k-means clustering technique.…”

“…Because of the virtualized and dispersed nature International Journal of Intelligent Engineering and Systems, Vol. 16 of cloud settings, it is difficult to create effective IDS. Attacks on systems and applications by cybercriminals lead to system and application failures, which is why cyber-attack protection is so important.…”

Network Intrusion Detection Method Using Stacked BILSTM Elastic Regression Classifier with Aquila Optimizer Algorithm for Internet of Things (IoT)

“…On identifying threats in IoT systems, many research investigations in the area of IoT security were conducted. Unfortunately, the majority of the research on IoT security that has been done so far has not primarily focused on the use of optimization-oriented To address the issue of complexity and effectively defend the IoT environment, [10] offer an intrusion prevention hyperparameter control system (ID-HyConSys) that regulates the IDS utilizing proximity policies optimization (PPO). A deep neural network (DNN) feature extractor that collects beneficial properties from a dynamic distributed system, a kmeans clustering that groups the collected information, and a PPO operator that automate the IDS via retraining and command ID-HyConSys' intrusion detection module.…”

“…This performance the Aquila to precisely investigate a given area. Equation (6) in AO simulates this tendency to limit the exploration when the randomly produced value is greater than 0.5 and n ) and a randomly generated value produced by Equation , the behaviour known as "walking and seizing the prey" occurs (10). (10) wherein…”