• Home
  • Search
  • Interpretable intrusion detection for IoT: a CNN-BiLSTM permutation importance framework for deep feature selection
  • https://doi.org/10.3389/fdata.2026.1813265Copy DOI Icon

Interpretable intrusion detection for IoT: a CNN-BiLSTM permutation importance framework for deep feature selection

Show More
  • Abstract
  • Literature Map
  • References
  • Similar Papers
Abstract

Industrial intrusion detection systems (IDS) in Industrial Internet of Things (IIoT) environments have to address the problem of handling multi-feature temporally correlated network traffic and dynamic changes in attack patterns. Traditional filter-based feature selection methods, like Mutual Information (MI), only consider individual feature performance and may not be effective in dealing with non-linear feature dependencies. This may degrade detection performance, especially in class-imbalanced problems. To mitigate such challenges, this paper proposes a deep feature selection (DFS) framework that utilizes a hybrid Convolutional Neural Network (CNN) and Bidirectional Long Short-Term Memory (BiLSTM) model. The proposed framework assesses the importance of native features using permutation importance. In the proposed framework, the CNN model detects local features in the data, whereas the BiLSTM model detects bidirectional temporal features in the data. The importance of features is computed by assessing the performance degradation of the model using time-aware perturbations on individual features. These identified features that are most relevant are then used to train lightweight traditional machine learning models like decision tree, K-nearest neighbor (KNN), logistic regression, naïve Bayes, and random forest. This makes it easy to deploy in resource-constrained IIoT environments. The approach is tested on the CIC IIoT 2025 dataset. From the experimental results, it is clear that the CNN-BiLSTM DFS framework improves recall and F1-score compared to other feature selection approaches like MI. This is especially true in imbalanced settings. The decoupling of feature selection from offline and edge-side inference provides a balance between detection accuracy, robustness, and deployability in real-world IIoT settings.

Similar Papers
  • Research Article

Transforming IIoT Security Leveraging Deep Learning and Feature Selection for Superior Intrusion Detection

  • Oct 02, 2025
  • International Journal of Computing
  • Lahcen Idouglid +2
  • PDF
  • Research Article
  • Citations20

Integrated Genetic Algorithm and Deep Learning Approach for Effective Cyber-Attack Detection and Classification in Industrial Internet of Things (IIoT) Environments

  • Oct 21, 2024
  • Arabian Journal for Science and Engineering
  • Nadia Alkhafaji +2
  • PDF
  • Research Article
  • Citations31

Fuzzy Logic and Its Application in the Assessment of Information Security Risk of Industrial Internet of Things

  • Oct 23, 2023
  • Symmetry
  • Seyit Kerimkhulle +9
  • Research Article
  • Citations7

Modeling of Bayesian machine learning with sparrow search algorithm for cyberattack detection in IIoT environment

  • Nov 26, 2024
  • Scientific Reports
  • Faten Khalid Karim +4
  • Research Article
  • Citations26

Toward Computing Resource Reservation Scheduling in Industrial Internet of Things

  • Dec 15, 2020
  • IEEE Internet of Things Journal
  • Fan Liang +4
  • Research Article
  • Citations6

The Impact of Edge Computing on the Industrial Internet of Things

  • Feb 28, 2023
  • International Conference on Cyber Warfare and Security
  • Nkata Sekonya +1
  • Research Article
  • Citations31

A multi-point collaborative DDoS defense mechanism for IIoT environment

  • Apr 18, 2022
  • Digital Communications and Networks
  • Hongcheng Huang +3
  • Research Article
  • Citations2

A Robust Anomaly Detector for Imbalanced IIOT Data

  • Aug 12, 2025
  • Journal of Computational Design and Engineering
  • Rubina Riaz +4
  • Research Article
  • Citations50

FL-CTIF: A federated learning based CTI framework based on information fusion for secure IIoT

  • Oct 18, 2023
  • Information Fusion
  • Mikail Mohammed Salim +3
  • Book Chapter
  • Citations2

Feature Extraction from Radiology Images for Visual Question Answering System Using CNN and BiLSTM Model

  • Jan 01, 2022
  • Y I Jinesh Melvin +2
  • Research Article
  • Citations15

Impact load identification and localization method on thin-walled cylinders using machine learning

  • May 18, 2023
  • Smart Materials and Structures
  • Chenyu Guo +4
  • Research Article
  • Citations42

IIoT based Augmented Reality for Factory Data Collection and Visualization

  • Jan 01, 2021
  • Procedia Manufacturing
  • Jonathan Rosales +2
  • PDF
  • Supplementary Content
  • Citations15

Revisiting the Feasibility of Public Key Cryptography in Light of IIoT Communications

  • Mar 27, 2022
  • Sensors (Basel, Switzerland)
  • Jasone Astorga +3
  • PDF
  • Research Article
  • Citations10

A novel ensemble Wasserstein GAN framework for effective anomaly detection in industrial internet of things environments.

  • Jul 23, 2025
  • Scientific reports
  • Rubina Riaz +5
  • Research Article
  • Citations1

Norm Emergence through Conflict-Blocking Interactions in Industrial Internet of Things Environments.

  • Sep 19, 2024
  • Sensors (Basel, Switzerland)
  • Yuchen Wang +7
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.