CNN+Transformer Based Anomaly Traffic Detection in UAV Networks for Emergency Rescue

TL;DR

This paper tackles the security challenges of UAV networks used in emergency rescue, where heterogeneous devices are vulnerable to cyber attacks. It proposes an integrated SDN and blockchain security framework to provide centralized traffic control, decentralized identity, and immutable auditing, complemented by a CNN+Transformer-based anomaly detector (CTranATD) for time-series traffic. CTranATD combines a CNN front-end for local feature extraction with a Transformer back-end to capture long-range temporal dependencies, trained on the CICIDS2017 dataset and deployed on the SDN controller. Experimental results show near-perfect accuracy and AUC, with the detector outperforming CNN, Transformer, and LSTM baselines, indicating strong potential for real-time anomaly detection and secure, traceable UAV emergency communications.

Abstract

The unmanned aerial vehicle (UAV) network has gained significant attentions in recent years due to its various applications. However, the traffic security becomes the key threatening public safety issue in an emergency rescue system due to the increasing vulnerability of UAVs to cyber attacks in environments with high heterogeneities. Hence, in this paper, we propose a novel anomaly traffic detection architecture for UAV networks based on the software-defined networking (SDN) framework and blockchain technology. Specifically, SDN separates the control and data plane to enhance the network manageability and security. Meanwhile, the blockchain provides decentralized identity authentication and data security records. Beisdes, a complete security architecture requires an effective mechanism to detect the time-series based abnormal traffic. Thus, an integrated algorithm combining convolutional neural networks (CNNs) and Transformer (CNN+Transformer) for anomaly traffic detection is developed, which is called CTranATD. Finally, the simulation results show that the proposed CTranATD algorithm is effective and outperforms the individual CNN, Transformer, and LSTM algorithms for detecting anomaly traffic.

Figures (5)

• Figure 1: A communication security network for UAVs combining the SDN and blockchain in emergency rescue
• Figure 2: The CTranATD proposed for anomaly traffic detection based on time series.
• Figure 3: Performance of 3 Attacks.
• Figure 4: Performance of different algorithms with different attacks.
• Figure 5: ROC curves of different algorithms.