Radio Frequency Identification (RFID) technology has emerged as a pervasive modality for human motion
sensing in applications such as smart environments and healthcare monitoring. However, the inherent
through-wall sensing capability of RFID technology raises critical privacy concerns regarding the
unintended leakage of human motion information, a challenge that has not been adequately addressed. To
fill this gap, we present a metasurface-based RFID sensing defence (Metafence), the
first system designed to protect human motion privacy against adversarial through-wall RFID sensing. To
this end, we first devise a programmable metasurface comprising 1-bit phase shifters that systematically
obfuscate motion-induced signal patterns. Through comprehensive theoretical modeling and empirical
investigations, we then characterize the metasurface's impact on RFID signals across temporal and spectral
domains. However, our analysis reveals that it is non-trivial to achieve effective signal obfuscation in
both domains, primarily due to a fundamental trade-off between increasing temporal signal variation and
masking human motion in its spectrum. To overcome this, we judiciously devise a metasurface controlling
strategy that jointly optimizes the signal entropy, variance, and spectrum distribution to reach a balance
between temporal and spectral motion obfuscation. Our comprehensive experiments demonstrate that Metafence
reduces adversarial through-wall motion detection rates to ≤6%, decreases the F1-score of human gesture
recognition to ≤0.11 on average, and amplifies respiration rate estimation errors by 3×, establishing a
robust defense mechanism for RFID-based motion privacy protection.
