Integration of metaheuristic based feature selection with ensemble representation learning models for privacy aware cyberattack detection in IoT environments

Abstract

The Internet of Things (IoT) connects virtual and physical objects inserted with software, devices, and other technology that interchange data utilizing the Internet. It enables diverse devices and individuals to exchange data, interconnect, and personalize services to ease usage. Despite IoT's merits, rising cyberthreats and the rapid growth of smart devices increase the risk of data breaches and security attacks. The increasing complexity of cyberattacks demands advanced intrusion detection systems (IDS) to defend crucial assets and data. AI techniques such as machine learning (ML) and deep learning (DL) have shown robust potential in improving IDS performance by accurately detecting and classifying malicious network behavior in IoT environments. This manuscript proposes an Adaptive Metaheuristic-Based Feature Selection with Ensemble Learning Model for Privacy-Preserving Cyberattack Detection (AMFS-ELPPCD) technique. The data normalization stage initially applies Z-score normalization to convert input data into a beneficial format. The AMFS-ELPPCD model utilizes the adaptive Harris hawk optimization (AHHO) model for the feature process selection of the subset. Furthermore, ensemble models such as bidirectional gated recurrent unit (BiGRU), Wasserstein autoencoder (WAE), and deep belief network (DBN) are used for the classification process. Finally, social group optimization (SGO) optimally adjusts the ensemble classifiers' hyperparameter values, resulting in better classification performance. A set of simulations is performed to exhibit the promising results of the AMFS-ELPPCD under dual datasets. The experimental validation of the AMFS-ELPPCD technique portrayed a superior accuracy value of 99.44% and 98.85% under the CICIDS-2017 and NSLKDD datasets over existing models.

Keywords: Cyberattack detection; Data normalization; Ensemble learning model; Feature selection; Social group optimization.

Fig. 1

Cyberattack detection in IoT networks.

Fig. 2

Overall process of AMFS-ELPPCD technique.

Fig. 3

Overall flow of the AHHO technique.

Fig. 4

BiGRU architecture.

Fig. 5

SGO flowchart.

Algorithm 1

SGO model

Fig. 6

CICIDS-2017 dataset (a-c) 80% and 70%TSPH and (b-d) 20% and 30%TSPH.

Fig. 7

Average of AMFS-ELPPCD model on the CICIDS-2017 dataset.

Fig. 8

analysis of AMFS-ELPPCD approach on the CICIDS-2017 dataset.

Fig. 9

Loss graph of AMFS-ELPPCD model on CICIDS-2017 dataset.

Fig. 10

Comparative analysis of AMFS-ELPPCD model on CICIDS-2017dataset.

Fig. 11

CT analysis of AMFS-ELPPCD method with existing models.

Fig. 12

Ablation study of AMFS-ELPPCD technique under CICIDS-2017 dataset.

Fig. 13

NSLKDD dataset (a-c) 80% and 70%TSPH and (b-d) 20% and 30%TSPH.

Fig. 14

Average of AMFS-ELPPCD model on NSLKDD dataset.

Fig. 15

curve of AMFS-ELPPCD method on NSLKDD dataset.

Fig. 16

Loss analysis of AMFS-ELPPCD method on the NSLKDD dataset.

Fig. 17

Comparative analysis of the AMFS-ELPPCD method on the NSLKDD dataset.

Fig. 18

CT evaluation of AMFS-ELPPCD methodology with the existing techniques.

Fig. 19

Ablation study of AMFS-ELPPCD approach under NSLKDD dataset.