A Highly Interpretable Framework for Generic Low-Cost UAV Attack Detection

Shihao Wu, Yang Li, Zhaoxuan Wang, Zheng Tan, Quan Pan

Research output: Contribution to journalArticlepeer-review

15 Scopus citations

Abstract

The increasing prevalence of cyber-attacks on unmanned aerial vehicles (UAVs) has led to research on effective detection methods. However, current approaches often lack transferability and interoperability, which limits their effectiveness. This study proposes a CNN-BiLSTM-Attention (CBA) model for efficient attack detection using real-time UAV sensor data. Additionally, the SHapley Additive exPlanations (SHAP) method is used to improve the interpretability of the model. The proposed approach is tested on real attack scenarios, including denial-of-service (DoS) attacks and global positioning system (GPS) spoofing attacks, and demonstrates both effectiveness and interpretability.

Original languageEnglish
Pages (from-to)7288-7300
Number of pages13
JournalIEEE Sensors Journal
Volume23
Issue number7
DOIs
StatePublished - 1 Apr 2023

Keywords

  • Attack detection
  • deep learning
  • unmanned aerial vehicles (UAVs)

Fingerprint

Dive into the research topics of 'A Highly Interpretable Framework for Generic Low-Cost UAV Attack Detection'. Together they form a unique fingerprint.

Cite this