.png){kind=icon}
.png){kind=icon}
Return
A Hybrid Intrusion Detection Model for Cloud Security: Feature Selection, Classification, and Authentication Using TFSEA Framework
.png){kind=icon}
PRE
AI
S
L
P
N
DOI：10.1016/j.cose.2026.105022.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
The emergence of Cloud Computing has revolutionized business operations by providing effective scalability and flexibility. Security concerns have intensified due to diverse data processed and stored in the cloud, hence protecting cloud infrastructure from cyber threats is crucial. Intrusion Detection System provides seamless monitoring and network traffic for exhibiting unauthenticated or malicious attempts. Recent advancements in Intrusion Detection Systems highlight certain issues such as low classification accuracy, high false positive rate as well as overfitting when processing various network data. Therefore, an effective optimal security solution named Threshold oriented Feature Selection with Efficient Authentication model is proposed in this paper via four layers. The perception layer of the IoT system utilizes diverse devices that send malicious attacks to the IoT devices. The network layer aggregates data from diverse intrusion detection datasets encompassing diverse ranges of attack scenarios. The data quality is ensured by preprocessing steps including missing data handling and normalization. The feature extraction uses Graylevel Radial Component Analysis to extract salient features, while dimensionality reduction is performed by introducing the Radial Basis Function Principal Component Analysis. In this work, the Crossover Boosted Dynamic Cheetah Optimization algorithm is employed in the feature selection process which integrates Cheetah Optimization with dynamic evolutionary strategies to improve the overall search efficiency and to tackle local optimal issues. The detection and classification of intrusion are performed by proposing a novel Threshold-based Kernel Extreme Learning Machine, which uses different thresholds to enhance generalization capability. Extensive experimental and statistical analysis is carried out and the results exhibit that the proposed framework achieves a classification accuracy, precision, recall, specificity, F1-score, and security rate of 98.78%, 98.65%, 98.70%, 98.20%, 98.67%, and 99.01% respectively on CIC IoT Dataset 2023 compared to all other existing models. Finally, the classified data is stored in cloud infrastructure that allows third-party monitoring services to assess and analyze critical intrusions and also provide threat analysis.
Journal
C
IF:
5.4
Papers:
164
Citations:
0
Organization
Cited Papers