Wi-Fi sensing based on Channel State Information (CSI) has witnessed considerable research activity in recent years. However, a critical literature analysis reveals that only a limited amount of proposals are potentially reproducible, with many works lacking essential experimental details, publicly available datasets, or accessible analysis code. This may impede the research progress and the subsequent transition of promising findings into practical applications. The objective of this work is to identify CSI-based sensing proposals that are potentially reproducible based on the published information. Our goal is to provide a focused review of resources that can serve as a concrete starting point for researchers and practitioners seeking to experiment with and advance the field of Wi-Fi sensing. We perform a comprehensive analysis of publicly available datasets (encompassing both the collection methodologies and the environmental characteristics) and existing sensing models, accompanied by their code, pre-processing steps, and evaluation procedures. Finally, we discuss what are the minimum requirements for truly verifiable contributions in this field, and outline the best practices for creating and sharing reproducible CSI-based sensing datasets and models.

We introduce EgoLife, a project to develop an egocentric life assistant that accompanies and enhances personal efficiency through AI-powered wearable glasses. To lay the foundation for this assistant, we conducted a comprehensive data collection study where six participants lived together for one week, continuously recording their daily activities—including discussions, shopping, cooking, social-izing, and entertainment—using AI glasses for multimodal person-view video references. This effort resulted in EgoLife Dataset, a comprehensive 300-hour egocentric, terpersonal, multiview, and multimodal daily life with intensive annotation. Leveraging this dataset, we troduce EgoLifeQA, a suite of long-context, life-oriented question-answering tasks designed to provide meaningful sistance in daily life by addressing practical questions as recalling past relevant events, monitoring health and offering personalized recommendations.To address the key technical challenges of 1) developing robust visual-audio models for egocentric data, 2) enabling identity recognition, and 3) facilitating long-context question answering over extensive temporal information, we introduce EgoBulter, an integrated system comprising EgoGPT and EgoRAG. EgoGPT is an omni-modal model trained on egocentric datasets, achieving state-of-the-art performance on egocentric video understanding. EgoRAG is a retrieval-based component that supports answering ultra-long-context questions. Our experimental studies verify their working mechanisms and reveal critical factors and bottlenecks, guiding future improvements. By releasing our datasets, models, and benchmarks, we aim to stimulate further research in egocentric AI assistants.

We propose a neuro-symbolic approach for learning causal complex event models from multi-source data, integrating causal discovery and temporal logic. Given resource constraints, we employ signal-level fusion by averaging the data from different antennas of the same WiFi receiver, followed by downsampling to reduce computational overhead. We consider a dataset of WiFi Channel State Information capturing human activities alongside video data from which we extract atomic symbolic activities such as “moving the upper arm.” The extracted symbolic information is processed through LPCMCI (Latent PCMCI). This causal discovery method extends PCMCI (Peter and Clark Momentary Conditional Independence) to handle latent dependencies across multiple time steps while mitigating false discoveries due to auto-correlations. The resulting causal structure is then translated into a temporal logic formula, which serves as a symbolic constraint in a neuro-symbolic learning pipeline. To efficiently process and learn from these structured constraints under resource limitations, we leverage Spiking Neural Networks, which offer energy-efficient computation while preserving temporal dynamics.

Wireless sensing based on Channel State Information (CSI) is rapidly spreading with the advent of 6G and newer Wi-Fi versions. Today, the CSI is regarded as one of the most promising elements for boosting service innovation on indoor device-free sensing. In addition, the wide adoption of the latest IEEE 802.11be standard, commonly known as Wi-Fi 7, might open up new possibilities for Wi-Fi sensing applications with even larger bandwidths, up to 320 MHz, and 4096 sub-carriers per spatial stream. However, researchers have still limited access to CSI extraction tools for such systems. In this work, we devise a framework based on software-defined radios to investigate the potential implications of the new Wi-Fi features, namely the wider channels and the higher number of sub-carriers, on a device-free positioning system based on position fingerprinting. In particular, we analyze the impact and the performance variations of this new technology across different bands in a position classification system, which has proven to be very accurate with previous versions of Wi-Fi. Our preliminary findings set some clear guidelines to direct future research efforts towards a better usage of newer Wi-Fi channels for sensing purposes. Furthermore, we publicly release our framework to the community of researchers and engineers for developing better Wi-Fi sensing solutions for smart homes, health care, and Internet-of- Things applications in general.

Channel State Information (CSI) sensing is now an established element of Integrated Sensing and Communication (ISAC) operations, but what is its real potential, and what are its limits? The literature focused more on sophisticated AI systems to exploit CSI variations imposed by different propagation scenarios, indeed achieving amazing results, but few, if any works tackled the topic of characterizing the long-term CSI behavior, its stability, and its stochastic properties to achieve insight in the potential and limits of CSI sensing. This work presents a first attempt in this direction, providing a framework that allows the comparison of CSIs quantifying the difference between CSI collected in different scenarios and showing that a quantitative analysis of the CSI is possible, and it can also help to explain the accuracy difference observed between distinct experiments with a CNN-based localization method taken from the literature.

Tomorrow’s massive-scale Internet-of-Things (IoT) sensor networks are poised to drive uplink traffic demand, especially in areas of dense deployment. To meet this demand, however, network designers leverage tools that often require accurate estimates of Channel State Information (CSI), which incurs a high overhead and thus reduces network throughput. Furthermore, the overhead generally scales with the number of clients, and so is of special concern in such massive IoT sensor networks. While prior work has used transmissions over one frequency band to predict the channel of another frequency band on the same link, this paper takes the next step in the effort to reduce CSI overhead: predict the CSI of a nearby but distinct link. We proposeCross-Link Channel Prediction(CLCP), a technique that leverages multi-view representation learning to predict the channel response of a large number of users, thereby reducing channel estimation overhead further than previously possible. CLCP’s design is highly practical, exploiting existing transmissions rather than dedicated channel sounding or extra pilot signals. We have implemented CLCP for two different Wi-Fi versions, namely 802.11n and 802.11ax, the latter being the leading candidate for future IoT networks. We evaluate CLCP in two large-scale indoor scenarios involving both line-of-sight and non-line-of-sight transmissions with up to 144 different 802.11ax users. Moreover, we measure its performance with four different channel bandwidths, from 20 MHz up to 160 MHz. Our results show that CLCP provides a 2x throughput gain over baseline and a 30% throughput gain over existing prediction algorithms.

Wi-Fi devices, akin to passive radars, can discern human activities within indoor settings due to the human body’s interaction with electromagnetic signals. Current Wi-Fi sensing applications predominantly employ data-driven learning techniques to associate the fluctuations in the physical properties of the communication channel with the human activity causing them. However, these techniques often lack the desired flexibility and transparency. This paper introduces DeepProbHAR, a neuro-symbolic architecture for Wi-Fi sensing, providing initial evidence that Wi-Fi signals can differentiate between simple movements, such as leg or arm movements, which are integral to human activities like running or walking. The neuro-symbolic approach affords gathering such evidence without needing additional specialised data collection or labelling. The training of DeepProbHAR is facilitated by declarative domain knowledge obtained from a camera feed and by fusing signals from various antennas of the Wi-Fi receivers. DeepProbHAR achieves results comparable to the state-of-the-art in human activity recognition. Moreover, as a by-product of the learning process, DeepProbHAR generates specialised classifiers for simple movements that match the accuracy of models trained on finely labelled datasets, which would be particularly costly.

Wi-Fi sensing applications have achieved remarkable results over the last decade, offering accurate device-free localization and gesture recognition capabilities. Indeed, Wi-Fi sensing has quickly become a critical field of research for future communication systems under the paradigm known as joint communication and sensing. However, device-free wireless sensing can also be exploited for malign purposes against unaware victims, and the omnipresence of Wi-Fi transceivers poses a significant threat to people’s privacy. Therefore, it is essential to develop functional solutions that can effectively thwart wireless sensing. All the current attempts to hinder illegitimate wireless sensing rely on specialized hardware deployed in the environment, but their cost and complexity can undermine widespread deployment. In this paper, we explore the possibility of using native capabilities of Wi-Fi systems, namely beamforming, to thwart wireless sensing. To this end, we propose for the first time a solution that enables complete control over the beamforming in commercial Wi-Fi devices. On top of that, we build BeamDancer, which randomizes beamforming vectors to inhibit channel fingerprinting. We empirically demonstrate the effectiveness of the proposed solution against three different wireless sensing techniques, both data-driven and model-based, while preserving almost entirely the legitimate Wi-Fi traffic at the same time.

Wi-Fi devices can effectively be used as passive radar systems that sense what happens in the surroundings and can even discern human activity. We propose, for the first time, a principled architecture which employs Variational Auto-Encoders for estimating a latent distribution responsible for generating the data, and Evidential Deep Learning for its ability to sense out-of-distribution activities. We verify that the fused data processed by different antennas of the same Wi-Fi receiver results in increased accuracy of human activity recognition compared with the most recent benchmarks, while still being informative when facing out-of-distribution samples and enabling semantic interpretation of latent variables in terms of physical phenomena. The results of this paper are a first contribution toward the ultimate goal of providing a flexible, semantic characterisation of black-swan events, i.e., events for which we have limited to no training data.

Tomorrow's massive-scale IoT sensor networks are poised to drive uplink traffic demand, especially in areas of dense deployment. To meet this demand, however, network designers leverage tools that often require accurate estimates of Channel State Information (CSI), which incurs a high overhead and thus reduces network throughput. Furthermore, the overhead generally scales with the number of clients, and so is of special concern in such massive IoT sensor networks. While prior work has used transmissions over one frequency band to predict the channel of another frequency band on the same link, this paper takes the next step in the effort to reduce CSI overhead: predict the CSI of a nearby but distinct link. We propose Cross-Link Channel Prediction (CLCP), a technique that leverages multi-view representation learning to predict the channel response of a large number of users, thereby reducing channel estimation overhead further than previously possible. CLCP's design is highly practical, exploiting existing transmissions rather than dedicated channel sounding or extra pilot signals. We have implemented CLCP for two different Wi-Fi versions, namely 802.11n and 802.11ax, the latter being the leading candidate for future IoT networks. We evaluate CLCP in two large-scale indoor scenarios involving both line-of-sight and non-line-of-sight transmissions with up to 144 different 802.11ax users and four different channel bandwidths, from 20 MHz up to 160 MHz. Our results show that CLCP provides a 2× throughput gain over baseline and a 30% throughput gain over existing prediction algorithms.

Thanks to the ubiquitous deployment of Wi-Fi hotspots, channel state information (CSI)-based Wi-Fi sensing can unleash game-changing applications in many fields, such as healthcare, security, and entertainment. However, despite one decade of active research on Wi-Fi sensing, most existing work only considers legacy IEEE 802.11n devices, often in particular and strictly-controlled environments. Worse yet, there is a fundamental lack of understanding of the impact on CSI-based sensing of modern Wi-Fi features, such as 160-MHz bandwidth, multiple-input multiple-output (MIMO) transmissions, and increased spectral resolution in IEEE 802.11ax (Wi-Fi 6). This work aims to shed light on the impact of Wi-Fi 6 features on the sensing performance and to create a benchmark for future research on Wi-Fi sensing. To this end, we perform an extensive CSI data collection campaign involving 3 individuals, 3 environments, and 12 activities, using Wi-Fi 6 signals. An anonymized ground truth obtained through video recording accompanies our 80-GB dataset, which contains almost two hours of CSI data from three collectors. We leverage our dataset to dissect the performance of a state-of-the-art sensing framework across different environments and individuals. Our key findings suggest that (i) MIMO transmissions and higher spectral resolution might be more beneficial than larger bandwidth for sensing applications; (ii) there is a pressing need to standardize research on Wi-Fi sensing because the path towards a truly environment-independent framework is still uncertain. To ease the experiments' replicability and address the current lack of Wi-Fi 6 CSI datasets, we release our 80-GB dataset to the community.

WiFi location systems are remarkably accurate, with decimeter-level errors for recent CSI-based systems. However, such high accuracy is achieved under Line-of-Sight (LOS) conditions and with an access point (AP) density that is much higher than that typically found in current deployments that primarily target good coverage. In contrast, when many of the APs within range are in Non-Line-of-Sight (NLOS), the location accuracy degrades drastically. In this paper we present UbiLocate, a WiFi location system that copes well with common AP deployment densities and works ubiquitously, i.e., without excessive degradation under NLOS. UbiLocate demonstrates that meter-level median accuracy NLOS localization is possible through (i) an innovative angle estimator based on a Nelder-Mead search, (ii) a fine-grained time of flight ranging system with nanosecond resolution, and (iii) the accuracy improvements brought about by the increase in bandwidth and number of antennas of IEEE 802.11ac. In combination, they provide superior resolvability of multipath components, significantly improving location accuracy over prior work. We implement our location system on off-the-shelf 802.11ac devices and make the implementation, CSI-extraction tool and custom Fine Timing Measurement design publicly available to the research community. We carry out an extensive performance analysis of our system and show that it outperforms current state-of-the-art location systems by a factor of 2--3, both under LOS and NLOS.

Bluetooth Classic (BT) remains the de facto connectivity technology in car stereo systems, wireless headsets, laptops, and a plethora of wearables, especially for applications that require high data rates, such as audio streaming, voice calling, tethering, etc. Unlike in Bluetooth Low Energy (BLE), where address randomization is a feature available to manufactures, BT addresses are not randomized because they are largely believed to be immune to tracking attacks. We analyze the design of BT and devise a robust de-anonymization technique that hinges on the apparently benign information leaking from frame encoding, to infer a piconet's clock, hopping sequence, and ultimately the Upper Address Part (UAP) of the master device's physical address, which are never exchanged in clear. Used together with the Lower Address Part (LAP), which is present in all frames transmitted, this enables tracking of the piconet master, thereby debunking the privacy guarantees of BT. We validate this attack by developing the first Software-defined Radio (SDR) based sniffer that allows full BT spectrum analysis (79 MHz) and implements the proposed de-anonymization technique. We study the feasibility of privacy attacks with multiple testbeds, considering different numbers of devices, traffic regimes, and communication ranges. We demonstrate that it is possible to track BT devices up to 85 meters from the sniffer, and achieve more than 80% device identification accuracy within less than 1 second of sniffing and 100% detection within less than 4 seconds. Lastly, we study the identified privacy attack in the wild, capturing BT traffic at a road junction over 5 days, demonstrating that our system can re-identify hundreds of users and infer their commuting patterns.