DUDE-IDS: A Framework for Efficiently Detecting Network-Related Drone Cyberattacks

Drones have become essential to various industries due to their capabilities in inspections, transportation, mapping, and delivery. As the drone market expands rapidly, so does the need for robust security measures to safeguard against cyberattacks. This paper introduces DUDE-IDS, a novel intrusion detection system (IDS) specifically designed for drones. Firstly, we introduce a time interval approach for generating labeled data. Then, we propose new features that can capture time-related patterns in drone network data. This approach enriches the representation of network flows, providing a better understanding of the dynamics of cyberattacks over time. DUDE-IDS takes advantage of knowledge derived from the time interval approach and the augmented feature set, which leads to improved detection capabilities. It utilizes supervised machine learning to analyze network traffic and detect anomalies, achieving high accuracy ($95.84 \%$), precision ($96.18 \%$), recall ($95.84 \%$), and F1 scores $\mathbf{(} \mathbf{9 5. 6 2 \%}$). Experimental results also demonstrate the efficiency of DUDE-IDS in real-time analysis, utilizing minimal memory resources. Through a series of experiments, the paper showcases the capability of DUDE-IDS to successfully detect and differentiate between various attack scenarios such as TCP SYN flood, Man-in-the-Middle (MITM), TCP reset, UDP flood, and deauthentication.