Banshee: Target Switch Attacks on Gimbal-Stabilized Visual Tracking Systems via Acoustic Injection
Jiarui Li, Joseph Brewington, Qingzhao Zhang, Z. Morley Mao
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 Banshee11.Our attack is named after the banshee, a mythical spirit whose scream causes or signals harm, reflecting the attack's acoustic nature., 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.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
Lineage
- TCTrack: Temporal Contexts for Aerial Tracking cites Learning Spatio-Temporal Transformer for Visual Tracking
- TCTrack: Temporal Contexts for Aerial Tracking cites Learning Discriminative Model Prediction for Tracking
- Learning Spatio-Temporal Transformer for Visual Tracking cites Learning Discriminative Model Prediction for Tracking
Builds on19
- Learning Discriminative Model Prediction for TrackingGoutam Bhat, Martin Danelljan, Luc Van Gool, Radu TimofteICCV 2019 · 1,294 citations
- Learning Spatio-Temporal Transformer for Visual TrackingBin Yan, Houwen Peng, Jianlong Fu, Dong Wang et al.ICCV 2021 · 1,062 citations
- SCRDet: Towards More Robust Detection for Small, Cluttered and Rotated ObjectsXue Yang, Jirui Yang, Junchi Yan, Yue Zhang et al.ICCV 2019 · 865 citations
- TCTrack: Temporal Contexts for Aerial TrackingZiang Cao, Ziyuan Huang, Liang Pan, Shiwei Zhang et al.CVPR 2022 · 233 citations
- Injected and Delivered: Fabricating Implicit Control over Actuation Systems by Spoofing Inertial SensorsYazhou Tu, Zhiqiang Lin, Insup Lee, Xiali HeiUSENIX Security 2018 · 132 citations
Related papers
- FlyTrap: Physical Distance-Pulling Attack Towards Camera-based Autonomous Target Tracking SystemsShaoyuan Xie, Mohamad Habib Fakih, Junchi Lu, Fayzah Alshammari et al.NDSS 2026 · 5 citations
- Poltergeist: Acoustic Adversarial Machine Learning against Cameras and Computer VisionXiaoyu Ji, Yushi Cheng, Yuepeng Zhang, Kai Wang et al.S&P 2021 · 99 citations
- Physical Hijacking Attacks against Object TrackersRaymond Muller, Yanmao Man, Z. Berkay Celik, Ming Li et al.CCS 2022 · 12 citations
- Fooling Detection Alone is Not Enough: Adversarial Attack against Multiple Object TrackingYunhan Jia, Yantao Lu, Junjie Shen, Qi Alfred Chen et al.ICLR 2020 · 113 citations
- SoundBreak: A Systematic Study of Audio-Only Adversarial Attacks on Trimodal ModelsAafiya Shamshad Hussain, Gaurav Srivastava, Alvi Md. Ishmam, Zaber Ibn Abdul Hakim et al.ACL 2026 · 1 citation
