Time series data-driven UAV sensor attack detection: an adaptive graph-time-frequency hybrid approach

Key Points

• The study aims to develop an effective detection method for UAV sensor attacks using adaptive time series and hybrid techniques.
• Utilized time series data for analysis of UAV sensor behavior.
• Applied hybrid graph-time-frequency methods for improved detection accuracy.
• Tested the approach under various simulated attack scenarios.
• Achieved a detection accuracy of over 90% for various sensor attack types.
• Demonstrated a decrease in false positive rates with the hybrid approach, leading to more reliable UAV operations.