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
TL;DR
The paper tackles UAV intrusion detection using a real cyber-physical UAV dataset by introducing an autoencoder-based feature extractor that compresses the input from $M$ features to a bottleneck of size $N$, minimizing reconstruction loss $L$ before feeding the representations to multiple classifiers. The approach is evaluated on the hassler2024intrusion dataset, comparing 4- and 8-feature AE representations against SHAP-based feature selection baselines across binary and multiclass tasks. Results show the proposed method generally outperforms baselines, with DT best for binary detection and MLP best for multiclass classification, underscoring the value of deep feature extraction on real UAV data. This work demonstrates practical potential for robust UAV security using real-world intrusion data and provides a solid foundation for deploying AE-based IDS in real UAV systems.
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.