Treffer: Deep Learning Models in Network Intrusion Detection Systems.

Network intrusion detection technology is crucial for maintaining a stable network environment and defending against network attacks. This paper first normalizes and solo thermal codes the network intrusion data. Then, it uses the ResNet18 model to pull out the deep features in the data. The CEKL loss function is used to keep the data balance in the ResNet18 training process. Finally, the Softmax function is used to classify and detect the network intrusion data. The detection model is then used as the core technology to design the network intrusion detection system. After testing, the average accuracy of this paper's model in network intrusion datasets Bot-IoT and ToN-IoT is 99.02% and 99.06%, respectively. In addition, the network intrusion detection system has a high recognition rate (94.41%–97.92%) for known types of attacking network samples, with low false alarms and missed alarms, and the system stress test meets expectations. The research work in this paper aims to optimize the shortcomings common to existing intrusion detection algorithms and proposes a feasible modeling idea for existing network intrusion detection techniques, which has excellent potential for application. [ABSTRACT FROM AUTHOR]

Copyright of Applied Mathematics & Nonlinear Sciences is the property of Sciendo 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.)