# GhostTac：无物理接触操纵触觉传感器

> 原文链接：https://robotics.hellobike.com/papers/2026-08-21-2608-20817
> 频道：papers | 更新日期：2026-08-21 | 标签：arxiv, cs.RO
> 核心摘要：GhostTac利用电磁干扰无接触操纵触觉传感输出，并在多种传感器、灵巧手及真实机器人任务案例中验证影响。

# GhostTac：无物理接触操纵触觉传感器

::: v-pre
> 原文链接：[GhostTac: Manipulating Tactile Sensors without Physical Contact](https://arxiv.org/abs/2608.20817)（arXiv 2608.20817 · 发布日期：2026-08-21）

**GhostTac: Manipulating Tactile Sensors without Physical Contact**

GhostTac利用电磁干扰无接触操纵触觉传感输出，并在多种传感器、灵巧手及真实机器人任务案例中验证影响。

## 核心要点

- 触觉传感器物理层安全此前关注较少，存在被非接触干扰操纵的风险。
- 方法利用非线性整流和有限带宽放大，使定制EMI转为可绕过滤波的稳定偏移。
- 可通过重塑空间分布和调节目标位置幅值，细粒度控制传感器输出。
- 在10个模块、2只灵巧手和15个触觉传感器上均显示一致攻击有效性。

**验证范围与局限**：验证范围为10个传感器模块、2只灵巧手，以及触觉抓取、滑移检测和材料分类三个案例。

## 英文摘要 (Abstract)

Tactile sensors are integral components of modern robotic systems, enabling robots to perceive and interact with the physical environment through tactile feedback. Despite their importance, the physical-layer security of tactile sensors has received little attention in prior work. In this paper, we present GhostTac, to the best of our knowledge, the first contactless attack that manipulates tactile sensing via electromagnetic interference (EMI). We identify that EMI exploits the nonlinear rectification and limited bandwidth amplification effects, allowing carefully crafted EMI signals to be converted into a persistent DC offset that bypasses on-board filtering and induces stable measurement deviations. Building on this mechanism, GhostTac enables fine-grained and controllable manipulation of sensor outputs by reshaping the spatial distribution and manipulating the magnitude at the targeted location. Such interference can induce unintended and harmful robot behaviors, such as causing a domestic robot to exert excessive force, resulting in physical damage or human injury. We evaluate GhostTac on 10 sensor modules and 2 dexterous hands, covering 15 tactile sensors of different types, and demonstrate consistent attack effectiveness across all tested devices. We further present three case studies on tactile grasping, slip detection, and material classification to illustrate practical impacts in real robotic tasks. We envision that our findings shed light on a new physical attack vector against tactile sensing in robotic systems.

作者：Kun Wang, Xuancun Lu, Ruochen Zhou, Kai Wang, Tongjun Ye, Yihao Shao, Chen Yan, Xiaoyu Ji, Wenyuan Xu
:::

## 原始参考来源 (Sources)

- [arXiv 2608.20817：GhostTac: Manipulating Tactile Sensors without Physical Contact](https://arxiv.org/abs/2608.20817)