Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Enhanced Intrusion Detection System for Multiclass Classification in UAV Networks

Safaa Menssouri, Mamady Delamou, Khalil Ibrahimi, El Mehdi Amhoud

TL;DR

The paper addresses security challenges in UAV networks by developing an intrusion detection system capable of both binary and multiclass classification. It introduces a PCA-1D CNN-LSTM architecture that uses cross-correlation-based feature selection and PCA for dimensionality reduction to capture temporal patterns in encrypted Wi-Fi traffic. Evaluated on the UAV-IDS-2020 dataset, the approach achieves near-perfect binary detection and up to 95% accuracy in multiclass UAV type identification, outperforming prior methods. The work demonstrates a scalable IDS approach suitable for 6G-era UAV networks and heterogeneous drone fleets.

Abstract

Unmanned Aerial Vehicles (UAVs) have become increasingly popular in various applications, especially with the emergence of 6G systems and networks. However, their widespread adoption has also led to concerns regarding security vulnerabilities, making the development of reliable intrusion detection systems (IDS) essential for ensuring UAVs safety and mission success. This paper presents a new IDS for UAV networks. A binary-tuple representation was used for encoding class labels, along with a deep learning-based approach employed for classification. The proposed system enhances the intrusion detection by capturing complex class relationships and temporal network patterns. Moreover, a cross-correlation study between common features of different UAVs was conducted to discard correlated features that might mislead the classification of the proposed IDS. The full study was carried out using the UAV-IDS-2020 dataset, and we assessed the performance of the proposed IDS using different evaluation metrics. The experimental results highlighted the effectiveness of the proposed multiclass classifier model with an accuracy of 95%.

Enhanced Intrusion Detection System for Multiclass Classification in UAV Networks

TL;DR

The paper addresses security challenges in UAV networks by developing an intrusion detection system capable of both binary and multiclass classification. It introduces a PCA-1D CNN-LSTM architecture that uses cross-correlation-based feature selection and PCA for dimensionality reduction to capture temporal patterns in encrypted Wi-Fi traffic. Evaluated on the UAV-IDS-2020 dataset, the approach achieves near-perfect binary detection and up to 95% accuracy in multiclass UAV type identification, outperforming prior methods. The work demonstrates a scalable IDS approach suitable for 6G-era UAV networks and heterogeneous drone fleets.

Abstract

Unmanned Aerial Vehicles (UAVs) have become increasingly popular in various applications, especially with the emergence of 6G systems and networks. However, their widespread adoption has also led to concerns regarding security vulnerabilities, making the development of reliable intrusion detection systems (IDS) essential for ensuring UAVs safety and mission success. This paper presents a new IDS for UAV networks. A binary-tuple representation was used for encoding class labels, along with a deep learning-based approach employed for classification. The proposed system enhances the intrusion detection by capturing complex class relationships and temporal network patterns. Moreover, a cross-correlation study between common features of different UAVs was conducted to discard correlated features that might mislead the classification of the proposed IDS. The full study was carried out using the UAV-IDS-2020 dataset, and we assessed the performance of the proposed IDS using different evaluation metrics. The experimental results highlighted the effectiveness of the proposed multiclass classifier model with an accuracy of 95%.
Paper Structure (10 sections, 6 equations, 9 figures, 4 tables)

This paper contains 10 sections, 6 equations, 9 figures, 4 tables.

Table of Contents

  1. Introduction And Related Works
  2. System Model And Problem Formulation
  3. UAV-IDS Dataset
  4. Principal Component Analysis (PCA)
  5. PCA-1D CNN-LSTM System
  6. Performance Evaluation Metrics
  7. Experimental Results
  8. Binary Classification
  9. Multiclass Classification
  10. Conclusion

Figures (9)

  • Figure 1: System model.
  • Figure 2: Preprocessing diagram where $m$, $n$, and $p$ are the number of features in the datasets.
  • Figure 3: Structure of the proposed 1D CNN-LSTM model.
  • Figure 4: The average accuracy and confusion matrix for the two-class model for parrot type in bidirectional flow (BF) and the combined dataset in unidirectional flow mode (UF).
  • Figure 5: Correlation between common features of the train and test datasets for bidirectional and unidirectional flow modes.
  • ...and 4 more figures