Treffer: Securing 5G Networks: An Anomaly Detection System Empowered by Bidirectional 3D Quasi-Recurrent Neural Network.

An intrusion detection system (IDS) with powerful capabilities that the existing conventional systems are unable to sufficiently supply is required from a security perspective, according to studies of compromised ultra-densified ubiquitous wireless networks that resulted from 6G wireless communications. IDSs are still not strong enough to fend against persistent, unexpected attacks against networks used for wireless communication, particularly on the more recent, extremely susceptible networks. As a result, their accuracy and detection rates are low, and their false-positive and false-negative cases. In this paper, an anomaly detection system (ADS) empowered by a bidirectional 3D quasi-recurrent neural network for securing 5G networks is proposed (5G-ADS-Bi-3DQRNN). The proposed framework's various stages are intended to locate anomalies. At first, the CIC_IDS2017 dataset is utilized to assemble the information network. After that, preprocessing is performed on the network-sourced input data. The preprocessing stage comprises three primary stages: transformation, filtration and standardization using min-max normalization (MMN). The best arrangement of features is chosen utilizing the suggested A-CEWT strategy. In this manner, the picked features go through the utilization of a modern enhancement strategy, similar to the improved red panda optimization algorithm (IRPOA), which changes the weight boundary of A-CEWT to work with a compelling element streamlining technique. In conclusion, the framework utilizes updated features to utilize the Bi-3DQRNN to recognize attack types such as DDoS, savage power, XSS, SQL infusion, penetration, port sweep, botnet attack and normal. The recommended approach is done in Python, and basic assessment measurements like F-measure, MSE, accuracy, sensitivity, specificity and precision are utilized to assess the strategy's exhibition completely. The proposed method attains 21.83%, 26.46% and 30.84% securing superior accuracy over current methods by boosting security controls and making use of cutting-edge 5G and future networks, utilizing an innovative deep reinforcement learning technique (5G-ADS-DRL), deep learning (DL) and machine learning (ML) techniques to create a system for identifying dropping threats on 5G networks (5G-ADS-KNN), and elaborates the next-generation networks using an IDS with dimensionality reduction (5G-ADS-DNN), respectively. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Circuits, Systems & Computers is the property of World Scientific Publishing Company and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)