Machine learning has become integral to Channel State Information (CSI)-based human sensing systems and is expected to power applications such as device-free activity recognition and identity detection in future cellular and Wi-Fi generations. However, these systems rely on models whose decisions can be subtly perturbed, raising concerns for security and reliability in ubiquitous sensing. Quantifying and understanding the robustness of such models, defined as their ability to maintain accurate predictions under adversarial perturbations, is therefore critical before wireless sensing can be safely deployed in real-world environments. This work presents a systematic evaluation of the robustness of CSI deep learning models under diverse threat models (white-box, black-box/transfer, and universal perturbations) and varying degrees of attack realism. We establish a framework to compare compact temporal autoencoder models with larger deep architectures across three public datasets, quantifying how model scale, training regime, and physical constraints influence robustness. Our experiments show that smaller models, while efficient and equally performant on clean data, are markedly less robust. We further confirm that physically realizable signal-space perturbations, designed to be feasible in real wireless channels, significantly reduce attack success compared to unconstrained feature-space attacks. Adversarial training mitigates these vulnerabilities, improving mean robust accuracy with only moderate degradation in clean performance across both model classes. As wireless sensing advances towards reliable, cross-domain operation, these findings provide quantitative baselines for robustness estimation and inform design principles for secure and trustworthy human-centered sensing systems.

Wi-Fi Channel State Information (CSI) has been repeatedly proposed as a biometric modality, often with reports of high accuracy and operational feasibility. However, the field lacks a consolidated understanding of its security properties, adversarial resilience, and methodological consistency. This Systematization of Knowledge (SoK) examines CSI-based biometric authentication through a security lens, analyzing how existing works diverge in sensing infrastructure, signal representations, feature pipelines, learning models, and evaluation methodologies. Our synthesis reveals systemic inconsistencies: reliance on aggregate accuracy metrics, limited reporting of FAR/FRR/EER, absence of per-user risk analysis, and scarce consideration of threat models or adversarial feasibility. To this end, we construct a unified evaluation framework to expose these issues empirically and demonstrate how security-relevant metrics such as per-class EER, Frequency Count of Scores (FCS), and the Gini Coefficient uncover risk concentration that remains hidden under traditional reporting practices. The resulting analysis highlights concrete attack surfaces--including replay, geometric mimicry, and environmental perturbation--and shows how methodological choices materially influence vulnerability profiles. Based on these findings, we articulate the security boundaries of current CSI biometrics and provide guidelines for rigorous evaluation, reproducible experimentation, and future research directions. This SoK offers the security community a structured, evidence-driven reassessment of Wi-Fi CSI biometrics and their suitability as an authentication primitive.

Abstract--Non-intrusive monitoring of vital signs has become increasingly important in a variety of healthcare settings. In this paper, we present PulseFi, a novel low-cost non-intrusive system that uses Wi-Fi sensing and artificial intelligence to accurately and continuously monitor heart rate and breathing rate, as well as detect apnea events. PulseFi operates using low-cost commodity devices, making it more accessible and cost-effective. It uses a signal processing pipeline to process Wi-Fi telemetry data, specifically Channel State Information (CSI), that is fed into a custom low-compute Long Short-T erm Memory (LSTM) neural network model. We evaluate PulseFi using two datasets: one that we collected locally using ESP32 devices and another that contains recordings of 118 participants collected using the Raspberry Pi 4B, making the latter the most comprehensive data set of its kind. Our results show that PulseFi can effectively estimate heart rate and breathing rate in a seemless non-intrusive way with comparable or better accuracy than multiple antenna systems that can be expensive and less accessible. Non-intrusive monitoring of vital signs (such as heart, breathing rate, and sleep apnea) has become increasingly important, particularly for home care, elderly care, and managing chronic conditions. As the global population ages and chronic disease rates increase, there is a growing need for continuous and accurate vital sign monitoring systems that can be easily deployed across the healthcare continuum, including hospitals, long-term care and home care settings [1]. Breathing and heart rate provides critical information about an individual's respiratory and cardiovascular health. Furthermore, detection of apnea, characterized by temporary pauses in breathing (typically lasting 10 seconds or longer) [2], is critical as conditions like sleep apnea affect millions worldwide and can lead to serious health complications if undiagnosed [3]. Thus, non invasive monitoring of these cardiopulmonary variables is necessary. Traditional approaches for vital sign monitoring have relied heavily on contact-based sensors such as pulse oximeters, heart rate belts, chest straps, or highly specialized medical equipment, such as polysomnography (PSG) or electrocardiogram (ECG) devices.

Sixth generation (6G) systems require environment-aware communication, driven by native artificial intelligence (AI) and integrated sensing and communication (ISAC). Radio maps (RMs), providing spatially continuous channel information, are key enablers. However, generating high-fidelity RM ground truth via electromagnetic (EM) simulations is computationally intensive, motivating machine learning (ML)-based RM construction. The effectiveness of these data-driven methods depends on large-scale, high-quality training data. Current public datasets often focus on single-input single-output (SISO) and limited information, such as path loss, which is insufficient for advanced multi-input multi-output (MIMO) systems requiring detailed channel state information (CSI). To address this gap, this paper presents UrbanMIMOMap, a novel large-scale urban MIMO CSI dataset generated using high-precision ray tracing. UrbanMIMOMap offers comprehensive complex CSI matrices across a dense spatial grid, going beyond traditional path loss data. This rich CSI is vital for constructing high-fidelity RMs and serves as a fundamental resource for data-driven RM generation, including deep learning. We demonstrate the dataset's utility through baseline performance evaluations of representative ML methods for RM construction. This work provides a crucial dataset and reference for research in high-precision RM generation, MIMO spatial performance, and ML for 6G environment awareness. The code and data for this work are available at: https://github.com/UNIC-Lab/UrbanMIMOMap.

--This paper introduces a deep learning framework for generating point clouds from WiFi Channel State Information data. We employ a two-stage autoencoder approach: a PointNet autoencoder with convolutional layers for point cloud generation, and a Convolutional Neural Network autoencoder to map CSI data to a matching latent space. By aligning these latent spaces, our method enables accurate environmental point cloud reconstruction from WiFi data. HE proliferation of wireless communication technologies has led to an increased interest in using WiFi signals for various sensing applications. Among these, Channel State Information (CSI) data from WiFi signals provides rich information about the environment, making it a valuable resource for tasks such as indoor localization [1], [2], activity recognition [3], [4], and environmental mapping [5], [6].

Joint communication and sensing (JC\&S) is emerging as a key component in 5G and 6G networks, enabling dynamic adaptation to environmental changes and enhancing contextual awareness for optimized communication. By leveraging real-time environmental data, JC\&S improves resource allocation, reduces latency, and enhances power efficiency, while also supporting simulations and predictive modeling. This makes it a key technology for reactive systems and digital twins. These systems can respond to environmental events in real-time, offering transformative potential in sectors like smart cities, healthcare, and Industry 5.0, where adaptive and multimodal interaction is critical to enhance real-time decision-making. In this work, we present a transformer-based architecture that processes temporal Channel State Information (CSI) data, specifically amplitude and phase, to generate 3D point clouds of indoor environments. The model utilizes a multi-head attention to capture complex spatio-temporal relationships in CSI data and is adaptable to different CSI configurations. We evaluate the architecture on the MM-Fi dataset, using two different protocols to capture human presence in indoor environments. The system demonstrates strong potential for accurate 3D reconstructions and effectively distinguishes between close and distant objects, advancing JC\&S applications for spatial sensing in future wireless networks.

This paper presents a collaborative fall detection and response system integrating Wi-Fi sensing with robotic assistance. The proposed system leverages channel state information (CSI) disruptions caused by movements to detect falls in non-line-of-sight (NLOS) scenarios, offering non-intrusive monitoring. Besides, a companion robot is utilized to provide assistance capabilities to navigate and respond to incidents autonomously, improving efficiency in providing assistance in various environments. The experimental results demonstrate the effectiveness of the proposed system in detecting falls and responding effectively.

Vision-based methods are commonly used in robotic arm activity recognition. These approaches typically rely on line-of-sight (LoS) and raise privacy concerns, particularly in smart home applications. Passive Wi-Fi sensing represents a new paradigm for recognizing human and robotic arm activities, utilizing channel state information (CSI) measurements to identify activities in indoor environments. In this paper, a novel machine learning approach based on discrete wavelet transform and vision transformers for robotic arm activity recognition from CSI measurements in indoor settings is proposed. This method outperforms convolutional neural network (CNN) and long short-term memory (LSTM) models in robotic arm activity recognition, particularly when LoS is obstructed by barriers, without relying on external or internal sensors or visual aids. Experiments are conducted using four different data collection scenarios and four different robotic arm activities. Performance results demonstrate that wavelet transform can significantly enhance the accuracy of visual transformer networks in robotic arms activity recognition.

Machine learning techniques have shown remarkable accuracy in localization tasks, but their dependency on vast amounts of labeled data, particularly Channel State Information (CSI) and corresponding coordinates, remains a bottleneck. Self-supervised learning techniques alleviate the need for labeled data, a potential that remains largely untapped and underexplored in existing research. Addressing this gap, we propose a pioneering approach that leverages self-supervised pretraining on unlabeled data to boost the performance of supervised learning for user localization based on CSI. We introduce two pretraining Auto Encoder (AE) models employing Multi Layer Perceptrons (MLPs) and Convolutional Neural Networks (CNNs) to glean representations from unlabeled data via self-supervised learning. Following this, we utilize the encoder portion of the AE models to extract relevant features from labeled data, and finetune an MLP-based Position Estimation Model to accurately deduce user locations. Our experimentation on the CTW-2020 dataset, which features a substantial volume of unlabeled data but limited labeled samples, demonstrates the viability of our approach. Notably, the dataset covers a vast area spanning over 646x943x41 meters, and our approach demonstrates promising results even for such expansive localization tasks.

This work presents a seminal approach for synthesizing images from WiFi Channel State Information (CSI) in through-wall scenarios. Leveraging the strengths of WiFi, such as cost-effectiveness, illumination invariance, and wall-penetrating capabilities, our approach enables visual monitoring of indoor environments beyond room boundaries and without the need for cameras. More generally, it improves the interpretability of WiFi CSI by unlocking the option to perform image-based downstream tasks, e.g., visual activity recognition. In order to achieve this crossmodal translation from WiFi CSI to images, we rely on a multimodal Variational Autoencoder (VAE) adapted to our problem specifics. We extensively evaluate our proposed methodology through an ablation study on architecture configuration and a quantitative/qualitative assessment of reconstructed images. Our results demonstrate the viability of our method and highlight its potential for practical applications.