Efficient Malicious UAV Detection Using Autoencoder-TSMamba Integration

TL;DR

This paper introduces an integrated autoencoder and ResNet-based classifier using a novel TSMamba architecture to detect malicious UAVs with high accuracy and reduced computational complexity, suitable for large-scale deployment.

Contribution

The paper presents a new AE-TSMamba architecture combined with a ResNet classifier for efficient and accurate malicious UAV detection, improving upon existing methods in accuracy and scalability.

Findings

Achieved up to 99.8% recall in detection

Reduced computational complexity for large-scale deployment

Demonstrated robustness in binary and multi-class scenarios

Abstract

Malicious Unmanned Aerial Vehicles (UAVs) present a significant threat to next-generation networks (NGNs), posing risks such as unauthorized surveillance, data theft, and the delivery of hazardous materials. This paper proposes an integrated (AE)-classifier system to detect malicious UAVs. The proposed AE, based on a 4-layer Tri-orientated Spatial Mamba (TSMamba) architecture, effectively captures complex spatial relationships crucial for identifying malicious UAV activities. The first phase involves generating residual values through the AE, which are subsequently processed by a ResNet-based classifier. This classifier leverages the residual values to achieve lower complexity and higher accuracy. Our experiments demonstrate significant improvements in both binary and multi-class classification scenarios, achieving up to 99.8 % recall compared to 96.7 % in the benchmark. Additionally, our method reduces computational complexity, making it more suitable for large-scale deployment. These results highlight the robustness and scalability of our approach, offering an effective solution for malicious UAV detection in NGN environments.