HandPass: A Wi-Fi CSI Palm Authentication Approach for Access Control

TL;DR

This work demonstrates the feasibility of palm-based biometric authentication using Wi-Fi CSI collected by a low-power Raspberry Pi in a controlled environment. By extracting amplitude and phase features from 5-GHz CSI across subcarriers and applying a Random Forest classifier with 10-fold cross-validation, the system achieves near-perfect user discrimination among 20 participants. The approach emphasizes immobility-based biophysical palm characteristics as a robust authentication signal for physical access control, reducing reliance on conventional credentials. The study also outlines a practical data-processing pipeline, including CFR transformation, normalization, and feature selection, and discusses scalability, robustness, and potential extensions to dynamic environments and multi-modal biometrics.

Abstract

Wi-Fi Channel State Information (CSI) has been extensively studied for sensing activities. However, its practical application in user authentication still needs to be explored. This study presents a novel approach to biometric authentication using Wi-Fi Channel State Information (CSI) data for palm recognition. The research delves into utilizing a Raspberry Pi encased in a custom-built box with antenna power reduced to 1dBm, which was used to capture CSI data from the right hands of 20 participants (10 men and 10 women). The dataset was normalized using MinMax scaling to ensure uniformity and accuracy. By focusing on biophysical aspects such as hand size, shape, angular spread between fingers, and finger phalanx lengths, among other characteristics, the study explores how these features affect electromagnetic signals, which are then reflected in Wi-Fi CSI, allowing for precise user identification. Five classification algorithms were evaluated, with the Random Forest classifier achieving an average F1-Score of 99.82\% using 10-fold cross-validation. Amplitude and Phase data were used, with each capture session recording approximately 1000 packets per second in five 5-second intervals for each User. This high accuracy highlights the potential of Wi-Fi CSI in developing robust and reliable user authentication systems based on palm biometric data.

Figures (4)

• Figure 1: CSI Matrix adapted from YMa2019.
• Figure 2: Suggested model.
• Figure 3: Experiments.
• Figure 4: F1-Score performance between datasets.