Identify malicious traffic on IoT infrastructure using neural networks and deep learning
Journal Title: Electronic and Cyber Defense - Year 2023, Vol 11, Issue 2
Abstract
The Internet of Things is a network of physical devices and equipment that includes sensors, software, and other technologies for exchanging data with other devices and systems over the Internet. The spread of the Internet of Things in the fields of smart health, smart agriculture, smart city, smart home, has revolutionized human life. Given the importance of the Internet of Things, identifying anomalies and malicious traffic is essential to maintaining privacy, network stability, and blocking unwanted behaviors. Due to the limited resources on IoT devices, traditional methods cannot be used directly to secure IoT devices and networks. To solve this problem, an artificial neural network-based identification method and in-depth learning has been developed to identify malformations and malicious traffic about which there is no predefined information. The data set used in this method is a combination of malicious and healthy traffic collected from related sources and feature extraction manually. Deep artificial neural network was applied to the data set and preprocessed and the results were analyzed with some conventional machine learning algorithms. The results show that the model designed using neural network and deep learning is able to detect anomalies and malicious traffic in the Internet of Things with an accuracy rate of more than 98.9% and an accuracy rate of 99.3%. In addition, the detection speed is 1.7 times faster than machine learning algorithms.
Authors and Affiliations
hamid tanha, mostafa abbasi
Keywords
Related Articles
- EP ID EP730056
- DOI -
- Views 61
- Downloads 1
Distributed Solving of Weapon Target Assignment Problem using Learning Automata
This article presents a method to solve the weapon target assignment problem, which is one of the problems of distributed constraint optimization. The previous methods do not guarantee the convergence problem properly an...
A method for quantitative evaluation of security risk in cyber-physical systems
Cyber-physical systems were introduced with the introduction of the cyber sector into physical systems and the emergence of Industry 4.0. Although the main purpose of this combination has been to increase the efficiency,...
Detection of Interfering Signals and Estimation of Their Carrier Frequency in CNC Satellite Communications using Cyclic Spectrum Density
Satellite communication is considered a significant part of the enemy's communication information in electronic warfare due to its unique features and widespread use in communication systems. Therefore, from the electron...
Reducing the Destructive Effect of Misbehaving Users in Cooperative Spectrum Sensing using Reinforcement Learning
The presence of misbehaving users in Cognitive Radio Networks (CRN) can disrupt the process of spectrum sensing and detecting the status of the Primary User (PU). In order to reduce the destructive effect of this group o...
Developing an Improved Method for Malware Attack Detection in Cloud Computing using Ensemble Learning
Nowadays, detecting unusual events in the network has been the subject of many researches. Network traffic is huge and very large, and this leads to high data size and increased noise, which makes it very difficult to ex...