Banshee: Target Switch Attacks on Gimbal-Stabilized Visual Tracking Systems via Acoustic Injection

2026-07-10

AI Summary

This work proposes the first physically realizable acoustic attack against gimbal-stabilized visual tracking systems, addressing a critical security threat wherein acoustic interference induces unintended target switching. By injecting carefully crafted adversarial sound waves, the attack excites directional oscillations in the gimbal, causing camera field-of-view drift that disrupts inter-frame target association and forces the tracker to lock onto an attacker-specified object. Integrating gimbal dynamics modeling, field-of-view drift optimization, and black-box attack strategies, the method achieves a 93.6% success rate in simulations across two commercial gimbals and five trackers. Real-world flight and bench tests demonstrate a 95.5% overall success rate on commercial drones across diverse scenarios, revealing for the first time a cross-domain acoustic-visual coupling vulnerability with significant security implications.

Abstract

Gimbal-stabilized visual tracking is critical for modern autonomous systems such as Unmanned Aerial Vehicles (UAVs). While prior work shows acoustic signals can disturb gimbal internals, the impact of such attacks on real-world applications like UAV tracking and following remains underexplored. Existing demonstrations largely overlook practical challenges for real-world attacks, such as object-motion uncertainty and runtime latency. To bridge this gap, we present Banshee, the first physically realizable attack that induces target switching in UAV visual tracking systems by exploiting acoustic vulnerabilities in gimbal-camera systems. Banshee generates carefully crafted acoustic waveforms that induce optimized adversarial gimbal oscillations, causing directionally biased camera-view drifts that break inter-frame target associations. Consequently, the onboard tracker is driven to switch from the original target to an attacker-selected object with high probability, with occasional target loss. Banshee achieves a 93.6% success rate in simulation across two commercial gimbal systems and five trackers. Real-world benchtop and in-flight black-box attacks against a commercial drone across varied scenarios show an overall 95.5% attack success rate. Our results reveal a practical cross-domain vulnerability between acoustics and vision, highlighting the need for robust designs of gimbal systems and applications. Our code is available at: https://github.com/U1ltra/Banshee.

Problem

• acoustic injection
• gimbal-stabilized tracking
• target switching
• visual tracking systems
• UAV

Innovation

• acoustic injection
• gimbal-stabilized tracking
• target switching attack
• adversarial oscillation
• cross-domain vulnerability