An optimized deep strategy for recognition and alleviation of DDoS attack in SD-IoT.
Network
; : 1-32, 2024 Jun 17.
Article
en En
| MEDLINE
| ID: mdl-38884373
ABSTRACT
The attacks like distributed denial-of-service (DDoS) are termed as severe defence issues in data centres, and are considered real network threat. These types of attacks can produce huge disturbances in information technologies. In addition, it is a complex task to determine and fully alleviate DDoS attacks. The new strategy is developed to identify and alleviate DDoS attacks in the Software-Defined Internet of Things (SD-IoT) model. SD-IoT simulation is executed to gather data. The data collected through nodes of SD-IoT are fed to the selection of feature phases. Here, the hybrid process is considered to select features, wherein features, like wrapper-based technique, cosine similarity-based technique, and entropy-based technique are utilized to choose the significant features. Thereafter, the attack discovery process is done with Elephant Water Cycle (EWC)-assisted deep neuro-fuzzy network (DNFN). The EWC is adapted to train DNFN, and here EWC is obtained by grouping Elephant Herd Optimization (EHO) and water cycle algorithm (WCA). Finally, attack mitigation is carried out to secure the SD-IoT. The EWC-assisted DNFN revealed the highest accuracy of 96.9%, TNR of 98%, TPR of 90%, precision of 93%, and F1-score of 91%, when compared with other related techniques.
Texto completo:
1
Colección:
01-internacional
Banco de datos:
MEDLINE
Idioma:
En
Revista:
Network
Asunto de la revista:
NEUROLOGIA
Año:
2024
Tipo del documento:
Article
País de afiliación:
India