Phantom Force: Injecting Adversarial Tactile Perceptions into Embodied Intelligence via EMI
Zirui Kong, Youqian Zhang, Sze Yiu Chau
TLDR
This paper reveals how electromagnetic interference can inject "phantom forces" into robot tactile sensors, severely compromising embodied intelligence.
Key contributions
- Explores a novel vulnerability in Hall-effect fingertip tactile sensors to electromagnetic interference.
- Demonstrates EMI can induce "phantom forces," amplifying perceived force by 9x and deviating direction by 65°.
- Shows these perturbations can paralyze learning-based tactile classification models in robots.
- Highlights the risk of robots crushing objects or dropping dangerous payloads due to this attack.
Why it matters
This work is the first to expose a critical security vulnerability in robot tactile sensors, a previously unexplored area. It demonstrates how EMI can trick robots into perceiving phantom forces, leading to dangerous malfunctions like crushing objects. This highlights an urgent need for robust, EMI-resistant tactile sensor design in embodied AI.
Original Abstract
Embodied intelligent robots rely on tactile sensors to interact with the physical world safely. While the security of visual perception systems has been studied (e.g., adversarial samples), the integrity of the tactile sensory channel remains unexplored. This work explores a vulnerability in Hall-effect fingertip sensors, showing their susceptibility to intentional Electromagnetic Interference (EMI). We demonstrate that a targeted signal injection can induce strong ``phantom forces'', amplifying perceived force magnitude by over \textbf{9$\times$} and deviating the inferred force direction by \textbf{65$^\circ$}. Such perturbations can paralyze learning-based tactile classification models, seriously affecting robot movement. An attacker could exploit this vulnerability to coerce a robot hand into crushing fragile objects or dropping dangerous payloads.
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.