Abstract:
The imperfection of existing intrusion detection methods and the changing nature of malicious actions on the attacker's part
led to the Internet of Things (IoT) network interaction in an unsafe state. The actual problem of improving the technology of the IOT
is counteracting malicious network impacts. In this regard, research and development aimed at creating effective tools for solving
applied problems within the framework of this problem are becoming increasingly important. This study seeks to develop tools for
detecting anomalous network conditions resulting from malicious attacks. In particular, the accuracy of the identification of DoS and
DDoS attacks is sufficient for operational use. This study analyzes various multi-level architectures, relevant communication protocols,
and different types of network attacks. The presented research was conducted on open datasets TON_IOT DATASETS, which include
multiple data sources collected from IoT sensors. The modified HyperNEAT algorithm was used as the basis for the development. The
NEAT methodology used in the study allows you to combine various network nodes. Results of the study: a neuro-evolutionary
algorithm for identifying DoS and DDoS attacks was implemented, integrated, and real-tested based on a multi-level analysis of network
traffic combined with various adaptive modules. The accuracy of identifying DoS and DDoS attacks is 0.9242 in the Accuracy metric.
The study implies that the proposed approach can be recommended for network intrusion detection, ensuring security when interacting
with the IoT.
