Effective Intrusion Detection for UAV Communications using Autoencoder-based Feature Extraction and Machine Learning Approach

Tuan-Cuong Vuong , Cong Chi Nguyen , Van-Cuong Pham , Thi-Thanh-Huyen Le , Xuan-Nam Tran , Thien Van Luong

The 2024 International Symposium on Nonlinear Theory and Its Applications (NOLTA2024) (2024) Conference

DOI

Abstract

This paper proposes a novel intrusion detection method for unmanned aerial vehicles (UAV) in the presence of recent actual UAV intrusion dataset. In particular, in the first stage of our method, we design an autoencoder architecture for effectively extracting important features, which are then fed into various machine learning models in the second stage for detecting and classifying attack types. To the best of our knowledge, this is the first attempt to propose such the autoencoder-based machine learning intrusion detection method for UAVs using actual dataset, while most of existing works only consider either simulated datasets or datasets irrelevant to UAV communications. Our experiment results show that the proposed method outperforms the baselines such as feature selection schemes in both binary and multi-class classification tasks.

Abstract

This paper proposes a novel intrusion detection method for unmanned aerial vehicles (UAV) in the presence of recent actual UAV intrusion dataset. In particular, in the first stage of our method, we design an autoencoder architecture for effectively extracting important features, which are then fed into various machine learning models in the second stage for detecting and classifying attack types.

To the best of our knowledge, this is the first attempt to propose such the autoencoder-based machine learning intrusion detection method for UAVs using actual dataset, while most of existing works only consider either simulated datasets or datasets irrelevant to UAV communications. Our experiment results show that the proposed method outperforms the baselines such as feature selection schemes in both binary and multi-class classification tasks.

Key Contributions

  1. Novel UAV Intrusion Detection: First autoencoder-based machine learning approach for UAV intrusion detection using actual datasets
  2. Two-Stage Architecture: Autoencoder for feature extraction followed by ML models for classification
  3. Real Dataset: Use of actual UAV intrusion dataset rather than simulated data
  4. Superior Performance: Outperforms baseline feature selection methods in both binary and multi-class tasks
  5. Comprehensive Evaluation: Evaluation on both binary and multi-class classification scenarios

Method Overview

  • Stage 1: Autoencoder-based feature extraction from UAV communication data
  • Stage 2: Machine learning models for attack detection and classification
  • Dataset: Recent actual UAV intrusion dataset
  • Evaluation: Binary and multi-class classification tasks

Conference Details

  • Conference: NOLTA2024 (International Symposium on Nonlinear Theory and Its Applications)
  • Date: October 1, 2024
  • arXiv Preprint: arXiv:2410.02827

Keywords

UAV Security, Intrusion Detection, Autoencoder, Feature Extraction, Machine Learning, Cybersecurity

Back to Publications