Anti-Sensing: Defense against Unauthorized Radar-based Human Vital Sign Sensing with Physically Realizable Wearable Oscillators

2025-05-16

AI Summary

This work addresses privacy leakage risks arising from ultra-wideband (UWB) radar-based non-contact vital sign monitoring. We propose a wearable active defense method, introducing— for the first time—physiologically plausible oscillatory perturbation into radar privacy protection. Specifically, we design a micro-electromechanical oscillator that induces controlled, biomechanically constrained skin-surface vibrations to physically distort radar echoes and mislead heart-rate estimation. A gradient-based optimization algorithm is further developed to jointly optimize perturbation frequency and spatial amplitude, maximizing interference efficacy while ensuring human safety. Simulation and real-world experiments demonstrate that the method increases estimation errors of mainstream neural-network-based heart-rate estimators by 3–8×, reducing accuracy below random-chance levels. This significantly surpasses the limitations of existing passive shielding approaches.

Technology Category

• Machine Learning: Privacy
• Planning, Routing, and Scheduling: Activity and Plan Recognition
• Intelligent Robots: State Estimation

Application Category

• Security and Privacy: Large-scale security measurements
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Responsible Web: Data and user privacy-enhancing technologies for the Web

Abstract

Recent advancements in Ultra-Wideband (UWB) radar technology have enabled contactless, non-line-of-sight vital sign monitoring, making it a valuable tool for healthcare. However, UWB radar's ability to capture sensitive physiological data, even through walls, raises significant privacy concerns, particularly in human-robot interactions and autonomous systems that rely on radar for sensing human presence and physiological functions. In this paper, we present Anti-Sensing, a novel defense mechanism designed to prevent unauthorized radar-based sensing. Our approach introduces physically realizable perturbations, such as oscillatory motion from wearable devices, to disrupt radar sensing by mimicking natural cardiac motion, thereby misleading heart rate (HR) estimations. We develop a gradient-based algorithm to optimize the frequency and spatial amplitude of these oscillations for maximal disruption while ensuring physiological plausibility. Through both simulations and real-world experiments with radar data and neural network-based HR sensing models, we demonstrate the effectiveness of Anti-Sensing in significantly degrading model accuracy, offering a practical solution for privacy preservation.

Problem

• Prevent unauthorized radar-based vital sign sensing
• Disrupt radar sensing with wearable oscillatory motion
• Protect privacy by misleading heart rate estimations

Innovation

• Wearable oscillators disrupt radar sensing
• Gradient-based algorithm optimizes oscillation parameters
• Mimics cardiac motion to mislead HR estimation