Low-Earth-Orbit (LEO) satellite constellations are becoming integral to 6G infrastructure, but increasing in-orbit computation accelerates battery degradation and raises sustainability concerns. Meanwhile, renewable-heavy regions worldwide experience persistent energy curtailment due to transmission bottlenecks, leaving substantial clean energy stranded near generation sites. We identify a satellite-grid co-design opportunity: adaptively offloading task-critical data from satellite to data centers co-located with renewable power plants. However, realizing this vision requires jointly considering intermittent and capacity-limited communication windows, as well as time-varying electricity budgets. In this paper, we propose SQSO, a Sustainable and QoS-aware Satellite Offloading framework that models per-interval task offloading as a constrained optimization over dynamic topology and electricity prices. Under this framework, we design $\text{AO}^2$, an adaptive offloading orchestration algorithm to solve the formulated optimization problem. Using Starlink-scale simulations and real-world electricity price traces, $\text{AO}^2$ reduces energy consumption by up to 76.03% and battery life consumption by up to 76.85% compared to state-of-the-art schemes, while also lowering task delay. This work highlights that sustainable scaling of LEO constellations requires co-design of space networking and renewable energy infrastructure, while our solution promotes renewable-aware task offloading and cross-domain collaboration for space-energy integration in the 6G era.

Respiratory monitoring using wireless technologies has garnered significant attention for its potential in healthcare, smart cockpits, and various applications. Though extensively studied, existing systems face practical challenges in adapting to new data domains without substantial customization efforts. Current solutions attempt to address this limitation through domain-independent feature extraction or cross-domain feature translation, employing either knowledge-based sensing models or data-driven neural networks. However, these approaches typically require additional data collection or model retraining for new domains, significantly hindering their practical deployment. This paper proposes RF-Carer, a fully zero-effort cross-domain respiration monitoring system. Our key innovation lies in building an explainable propagation model to transform any heterogeneous signals under unknown domains into a unified form in the signal processing layer. To further address accidental irrelevant factors, we propose to align the feature spaces while suppressing the noisy ones with contrastive learning. On this basis, we develop a one-fits-all model that requires only one-time training but can adapt to 12 domains with 57 cases like unconstrained movements, unknown users, untrained environments, etc.. To the best of our knowledge, RF-Carer is the first zero-effort cross-domain respiration monitoring work with wireless RF signals and would be a fundamental step toward real-world deployments.

Low Earth Orbit (LEO) satellite networks such as Starlink and Project Kuiper are increasingly integrated with cloud infrastructures, forming an important internet backbone for global web services. By extending connectivity to remote regions, oceans, and disaster zones, these networks enable reliable access to applications ranging from real-time WebRTC communication to emergency response portals. Yet the resilience of these web services is threatened by space radiation: it degrades hardware, drains batteries, and disrupts continuity, even if the space-cloud integrated providers use machine learning to analyze space weather and radiation data. Specifically, conventional fixes like altitude adjustments and thermal annealing consume energy; neglecting this energy use results in deep discharge and faster battery aging, whereas sleep modes risk abrupt web session interruptions. Efficient network-layer mitigation remains a critical gap. We propose RALT (Radiation-Aware LEO Transmission), a control-plane solution that dynamically reroutes traffic during radiation events, accounting for energy constraints to minimize battery degradation and sustain service performance. Our work shows that unlocking space-based web services' full potential for global reliable connectivity requires rethinking resilience through the lens of the space environment itself.

High-Throughput Satellites (HTS) use beam hopping to handle non-uniform and time-varying ground traffic demand. A significant technical challenge in beam hopping is the computation of effective illumination patterns. Traditional algorithms, like the genetic algorithm, require over 300 seconds to compute a single illumination pattern for just 37 cells, whereas modern HTS typically covers over 300 cells, rendering current methods impractical for real-world applications. Advanced approaches, such as multi-agent deep reinforcement learning, face convergence issues when the number of cells exceeds 40. In this paper, we introduce Tyche, a hybrid computation framework designed to address this challenge. Tyche incorporates a Monte Carlo Tree Search Beam Hopping (MCTS-BH) algorithm for computing illumination patterns and employs sliding window and pruning techniques to significantly reduce computation time. Specifically, MCTS-BH can compute one illumination pattern for 37 cells in just 12 seconds. To ensure real-time computation, we use a Greedy Beam Hopping (G-BH) algorithm, which provides a provisional solution while MCTS-BH completes its computation in the background. Our evaluation results show that MCTS-BH can increase throughput by up to 98.76%, demonstrating substantial improvements over existing solutions.

With the rise of mega-satellite constellations, the integration of hierarchical non-terrestrial and terrestrial networks has become a cornerstone of 6G coverage enhancements. In these hierarchical satellite networks, controllers manage satellite switches within their assigned domains. However, the high mobility of LEO satellites and field-of-view (FOV) constraints pose fundamental challenges to efficient domain partitioning. Centralized control approaches face scalability bottlenecks, while distributed architectures with onboard controllers often disregard FOV limitations, leading to excessive signaling overhead. LEO satellites outside a controller’s FOV require an average of five additional hops, resulting in a 10.6-fold increase in response time. To address these challenges, we propose Eunomia, a three-step domain-partitioning framework that leverages movement-aware FOV segmentation within a hybrid control plane combining ground stations and MEO satellites. Eunomia reduces control plane latency by constraining domains to FOV-aware regions and ensures single-hop signaling. It further balances traffic load through spectral clustering on a Control Overhead Relationship Graph and optimizes controller assignment via the Kuhn-Munkres algorithm. We implement Eunomia on the Plotinus emulation platform with realistic constellation parameters. Experimental results demonstrate that Eunomia reduces request loss by up to 58.3%, control overhead by up to 50.3%, and algorithm execution time by 77.7%, significantly outperforming current state-of-the-art solutions.

Traditional CAPTCHA (Completely Automated Public Turing Test to Tell Computers and Humans Apart) schemes are increasingly vulnerable to automated attacks powered by deep neural networks (DNNs). Existing adversarial attack methods often rely on the original image characteristics, resulting in distortions that hinder human interpretation and limit their applicability in scenarios where no initial input images are available. To address these challenges, we propose the Unsourced Adversarial CAPTCHA (DAC), a novel framework that generates high-fidelity adversarial examples guided by attacker-specified semantics information. Leveraging a Large Language Model (LLM), DAC enhances CAPTCHA diversity and enriches the semantic information. To address various application scenarios, we examine the white-box targeted attack scenario and the black-box untargeted attack scenario. For target attacks, we introduce two latent noise variables that are alternately guided in the diffusion step to achieve robust inversion. The synergy between gradient guidance and latent variable optimization achieved in this way ensures that the generated adversarial examples not only accurately align with the target conditions but also achieve optimal performance in terms of distributional consistency and attack effectiveness. In untargeted attacks, especially for black-box scenarios, we introduce bi-path unsourced adversarial CAPTCHA (BP-DAC), a two-step optimization strategy employing multimodal gradients and bi-path optimization for efficient misclassification. Experiments show that the defensive adversarial CAPTCHA generated by BP-DAC is able to defend against most of the unknown models, and the generated CAPTCHA is indistinguishable to both humans and DNNs.

Blood pressure (BP) is a critical indicator for life-threatening conditions. While invasive catheter-based methods offer high accuracy, non-invasive techniques typically require placement on specific body areas, introducing discomfort and rendering their accuracy sensitive to wearing conditions. To overcome these limitations, recent efforts have explored contactless BP monitoring using RF sensing. However, existing approaches often rely on deep learning models without grounding in physiological principles, resulting in poor generalization and limited clinical trustworthiness. In this paper, we proposehBP-Fi, a contactless BP measurement system driven byhemodynamicsacquired via RF sensing. In addition to its contactless convenience,hBP-Fi outperforms existing RF-based approaches by i) employing a physiologically grounded hemodynamic model of pulse generation that forms the basis for RF-based BP estimation, ii) enabling super-resolution arterial pulse tracking via beam-steerable RF scanning, iii) ensuring output trustworthiness through an interpretable (transparent-by-design) deep learning model, and iv) achieving robust generalizability to unseen users and scenarios via a CycleGAN-based training strategy. Extensive experiments with 35 subjects under practical scenarios demonstrate thathBP-Fi can achieve errors of -2.95$\pm$7.66 mmHg and 2.63$\pm$6.05 mmHg for systolic and diastolic blood pressures, respectively.

Performance Enhancement Proxies (PEPs) are widely used to improve TCP performance in geostationary orbit (GEO) satellite networks, which experience long RTT (approximately 500 ms). As a split TCP-based solution, PEP divides the end-to-end connection into multiple sub-connections, each independently managing its own rate control, including both congestion and flow control. This independence naturally leads to rate imbalances, manifested as an abnormal on-off traffic pattern-a phenomenon confirmed by our experimental observations in real-world GEO satellite networks. Furthermore, we demonstrate that this on-off traffic pattern not only undermines fairness but also reduces throughput, particularly for small-sized flows. To address this problem, we propose PEP-Policer, an automatic rate limiter for PEP to limit the link with higher rate to the lower one. Unlike traditional rate limiting methods that require manual configuration of the target rate, PEP-Policer employs a finite state machine to automatically determine and enforce the appropriate target rate. Moreover, as an add-on, PEP-Policer is compatible with all PEP-based solutions and can be integrated without modifying existing systems. Extensive evaluations in an emulated GEO satellite network show that PEP-Policer improves TCP's fairness and increases goodput by up to 63.0% for Cubic, 49.6% for BBR, and 88.6% for Hybla.

Recently, there has been a surge in the development of advanced intelligent generative content (AIGC), especially large language models (LLMs). For many downstream tasks, it is necessary to fine-tune LLMs using private data. While federated learning offers a promising privacy-preserving solution to LLM fine-tuning, the substantial size of an LLM, combined with high computational and communication demands, makes it hard to apply to handle downstream tasks. More importantly, private edge servers often possess varying computing and network resources in real-world scenarios, introducing additional complexities to LLM fine-tuning. To tackle these problems, we design and implement an automated federated pipeline, named, to fine-tune LLMs on heterogeneous edge servers with minimal training cost and no additional inference latency. firstly identifies the weights to be fine-tuned based on their contributions to the LLM training. It then configures a low-rank adapter for each selected weight within the resource constraints of the edge server and aggregates these local adapters from all edge servers to fine-tune the whole LLM. Finally, it appropriately quantizes the parameters of LLM to reduce memory consumption according to the requirements of edge servers. Extensive experiments demonstrate that expedites model training and achieves higher accuracy than the state-of-the-art benchmarks.

Reusing Wi-Fi communication packets for sensing purpose has been regarded as one of the most cost-effective ways to realize integrated sensing and communication (ISAC) on commodity Wi-Fi. However, the channel state information (CSI) measured from these packets can be heavily compromised by modern Wi-Fi beamforming protocols tailored primarily to maximize communication throughput, hence inadvertently affecting Wi-Fi sensing performance. Existing approach attempts to mitigate this negative impact through passive signal processing in single-user sensing scenarios, but it fails to fundamentally resolve the problem. In contrast, we actively leverage beamforming, transforming its adverse effects into positive gains, and propose VersaBeam, a practical Wi-Fi ISAC system that simultaneously supports multiple sensing and communication users. Specifically, for multi-user scenarios, we design a correlation-based user pairing algorithm to ensure that the reused communication packets of each sensing receiver are transmitted with sufficiently high power along the sensing direction. Building on this, a novel ISAC-oriented beamforming strategy is proposed to balance the requirements of both sensing and communication. To further provide consistent inputs for sensing tasks, a CSI unification method is developed to remove inconsistencies resulting from diverse beamforming matrices when reusing packets from different communication users. Finally, a prototype of VersaBeam is implemented on commodity Wi-Fi devices, and its effective ness is validated through micro-benchmarking and real-world experiments across three representative sensing applications.

New Wi-Fi systems have leveraged beamforming to manage a significant portion of traffic for achieving high throughput and reliability. Unfortunately, this has amplified certain security risks since beamforming critically relies on theclear-textbeamforming feedback information (BFI): though similar risks have been exposed using emulation platforms (e.g., USRP), they have never proven realistic till this day. In this paper, we propose BeamCraft, thefirstattack to manipulate traffic incommodityWi-Fi systems; it differs significantly from existing attacks either staying only on emulation platforms with limited real-world applicability or jamming communications by brute force. The core idea of BeamCraft involves corrupting beamforming decisions by injecting crafted BFIs that feed an access point (AP) with erroneous information on channel states. To mount a covert yet purposeful attack, we develop i) a joint location and transmit power selection strategy to evade detection by victims and ii) a novel BFI forgery method to effectively manipulate AP's beamforming decisions. We implement BeamCraft using commodity Wi-Fi devices and perform extensive evaluations with it; the results reveal that BeamCraft effectively manipulates Wi- Fi traffic while maintaining a low exposure rate. Furthermore, we also introduce a defense strategy, namely BeamCrypt, that jointly leverages reciprocity and similarity of the channel within the coherence time to authenticate the legitimate user with low overhead. We implement it using WARP and evaluation results verify the effectiveness.

Split federated learning (SFL) has emerged as a promising paradigm to democratize machine learning (ML) on edge devices by enabling layer- wise model partitioning. However, existing SFL approaches suffer significantly from the straggler effect due to the heterogeneous capabilities of edge devices. To address the fundamental challenge, we propose adaptively controlling batch sizes (BSs) and model splitting (MS) for edge devices to overcome resource heterogeneity. We first derive a tight convergence bound of SFL that quantifies the impact of varied BSs and MS on learning performance. Based on the convergence bound, we propose HASFL, a heterogeneity-aware SFL framework capable of adaptively controlling BS and MS to balance communication-computing latency and training convergence in heterogeneous edge networks. Extensive experiments with various datasets validate the effectiveness of HASFL and demonstrate its superiority over state-of-the-art benchmarks.

Recently, the increasing deployment of LEO satellite systems has enabled various space analytics (e.g., crop and climate monitoring), which heavily relies on the advancements in deep learning (DL). However, the intermittent connectivity between LEO satellites and ground station (GS) significantly hinders the timely transmission of raw data to GS for centralized learning, while the scaled-up DL models hamper distributed learning on resource-constrained LEO satellites. Thoughsplit learning(SL) can be a potential solution to these problems by partitioning a model and offloading primary training workload to GS, the labor-intensive labeling process remains an obstacle, with intermittent connectivity and data heterogeneity being other challenges. In this paper, we propose LEO-Split, asemi-supervised(SS) SL design tailored for satellite networks to combat these challenges. Leveraging SS learning to handle (labeled) data scarcity, we construct an auxiliary model to tackle the training failure of the satellite-GS non-contact time. Moreover, we propose a pseudo-labeling algorithm to rectify data imbalances across satellites. Lastly, an adaptive activation interpolation scheme is devised to prevent the overfitting of server-side sub-model training at GS. Extensive experiments with real-world LEO satellite traces (e.g., Starlink) demonstrate that our LEO-Split framework achieves superior performance compared to state-of-the-art benchmarks.

The increasing processing demands of today's mobile deep learning applications impose stringent requirements on edge devices. Offloading these tasks to the cloud, while being a potential solution, often results in significant data transfer overhead, as well as privacy and connectivity concerns. To address these challenges, split machine learning (split ML) has emerged as an innovative paradigm, enabling task distribution among edge devices themselves. However, split ML systems inherently exhibit instability due to the hardware and communication limitations of mobile devices, which frequently result in failures and malfunctions of client nodes. In light of these challenges, we present Axolotl, a fault-tolerant edge split ML inference system for addressing node failure with minimal performance impact. Specifically, we first design a novel curriculum dropout mechanism to enhance the model's resilience by gradually exposing it to potential server node failures. We then design inverse-proximal weight consolidation to mitigate catastrophic forgetting caused by curriculum dropout. To further tackle potential node failures, we innovate in a resource-aware substitution module that offload the functions of a failed node to neighboring ones, ensuring efficient information flow. Extensive experiments demonstrate the effectiveness and robustness of Axolotl in various deep learning networks and tasks in edge environments.

The rapid deployment of low Earth orbit (LEO) satellite systems has propelled various space-based applications (e.g., agricultural monitoring and disaster response), which increasingly rely on advancements in deep learning (DL). However, ground stations (GS) cannot download such massive raw data for centralized training due to intermittent connectivity between satellites and GS, while the scaled-up DL models pose substantial barriers to distributed training on resource-constrained satellites. Although split learning (SL) has emerged as a promising solution to offload major training workloads to GS via model partitioning while retaining raw data on satellites, limited satellite-GS connectivity and heterogeneity of satellite resources remain substantial barriers. In this paper, we propose S-Leon, an SL framework tailored to tackle these challenges within heterogeneous LEO satellite networks. We develop a satellite early-exit model to eliminate training disruptions during non-contact periods and employ online knowledge distillation to incorporate ground knowledge, further enhancing satellite local training. Moreover, we devise a satellite model customization method that simultaneously accommodates the heterogeneous computation and communication capabilities of individual satellites. Lastly, we develop a partial model-agnostic training strategy to optimize the collaborative training effectiveness across customized satellite models. Extensive experiments with real-world LEO satellite networks demonstrate that S-Leon outperforms state-of-the-art benchmarks.

The rapid development of service computing has led to the emergence of scalable and flexible architectures such as microservices and Artificial Intelligence as a Service (AaaS), enabling the orchestration of AI-driven intelligent applications. However, existing work on intelligent applications orchestration overlooked essential microservice components that support AI services, resulting in coarse-grained and incomplete models. To ensure system integrity and enhance QoS, fine-grained collaborative orchestration of microservices and AI services is crucial. However, this poses significant challenges due to complex service dependencies, high request concurrency, and heterogeneous resource demands in edge environments. Moreover, the strong coupling between service deployment and request routing complicates their joint optimization, since effective decisions in one depend on the other. To address these challenges, we propose a collaborative orchestration framework that jointly optimizes the deployment of microservices and AI services along with probabilistic request routing in edge environments. We formulate the problem as a mixed-integer nonlinear program and leverage Jackson queuing networks for accurate delay modeling. To solve this, we develop a dual time scale hybrid greedy proximal policy optimization (DTS-HGPPO) algorithm that performs instance-level deployment and adaptive routing, enhanced with iterative instance planning, action masking and intrinsic motivation mechanisms. Extensive trace-driven experiments demonstrate that our method significantly reduces both response delay and service cost compared to state-of-the-art baselines.

Recent progress on large language models (LLMs) has spurred interest in scaling up recommendation systems, yet two practical obstacles remain. First, training and serving cost on industrial Recommenders must respect strict latency bounds and high QPS demands. Second, most human-designed feature-crossing modules in ranking models were inherited from the CPU era and fail to exploit modern GPUs, resulting in low Model Flops Utilization (MFU) and poor scalability. We introduce RankMixer, a hardware-aware model design tailored towards a unified and scalable feature-interaction architecture. RankMixer retains the transformer's high parallelism while replacing quadratic self-attention with multi-head token mixing module for higher efficiency. Besides, RankMixer maintains both the modeling for distinct feature subspaces and cross-feature-space interactions with Per-token FFNs. We further extend it to one billion parameters with a Sparse-MoE variant for higher ROI. A dynamic routing strategy is adapted to address the inadequacy and imbalance of experts training. Experiments show RankMixer's superior scaling abilities on a trillion-scale production dataset. By replacing previously diverse handcrafted low-MFU modules with RankMixer, we boost the model MFU from 4.5% to 45%, and scale our online ranking model parameters by two orders of magnitude while maintaining roughly the same inference latency. We verify RankMixer's universality with online A/B tests across two core application scenarios (Recommendation and Advertisement). Finally, we launch 1B Dense-Parameters RankMixer for full traffic serving without increasing the serving cost, which improves user active days by 0.3% and total in-app usage duration by 1.08%.

Clustered federated learning (CFL) addresses the performance challenges posed by data heterogeneity in federated learning (FL) by organizing edge devices with similar data distributions into clusters, enabling collaborative model training tailored to each group. However, existing CFL approaches strictly limit knowledge sharing to within clusters, lacking the integration of global knowledge with intra-cluster training, which leads to suboptimal performance. Moreover, traditional clustering methods incur significant computational overhead, especially as the number of edge devices increases. In this paper, we propose LCFed, an efficient CFL framework to combat these challenges. By leveraging model partitioning and adopting distinct aggregation strategies for each sub-model, LCFed effectively incorporates global knowledge into intra-cluster co-training, achieving optimal training performance. Additionally, LCFed customizes a computationally efficient model similarity measurement method based on low-rank models, enabling real-time cluster updates with minimal computational overhead. Extensive experiments show that LCFed outperforms state-of-the-art benchmarks in both test accuracy and clustering computational efficiency.

With the increasing deployment of Low Earth Orbit (LEO) satellites (e.g., Starlink), rate adaptation has been widely applied in satellite communication systems to rapidly adapt changing satellite-ground channel. However, the state-of-the-art rate adaptation solutions still do not approach the Shannon capacity, since they always operates in discrete steps (e.g., switching between fixed modulation orders and coding rates), leading to abrupt performance deterioration when the channel fluctuates between two thresholds. We propose a new plug-and-play rate adaptation, called ERA-LEO integrated to satellite communication systems without any extra hardware modification. For adapting smoothly to changes in channels, we first design a probabilistic constellation shaping enabled system to provide a continuous and more granular adjustment of the constellation by tuning the probability distribution of symbols. Second, to avoid the frequent feedback, used to select a target probability distribution based on the channel condition, we establish a theoretical model to demonstrate that the SNR of the return link can reliably predict that of the forward link, and present a lightweight prediction mechanism based on neural network. We also implement ERA-LEO prototype using FPGA-based software defined radio platforms. The extensive evaluations demonstrate ERA-LEO achieves an average gain of 2.19 dB compared to state-of-the-art baselines and a 43.08% improvement in network throughput.

Recently, large vision-language models (LVLMs) unleash powerful analysis capabilities for low Earth orbit (LEO) satellite Earth observation images in the data center. However, fast satellite motion, brief satellite-ground station (GS) contact windows, and large size of the images pose a data download challenge. To enable near real-time Earth observation applications (e.g., disaster and extreme weather monitoring), we should explore how to deploy LVLM in LEO satellite networks, and design SpaceVerse, an efficient satellite-ground synergistic LVLM inference system. To this end, firstly, we deploy compact LVLMs on satellites for lightweight tasks, whereas regular LVLMs operate on GSs to handle computationally intensive tasks. Then, we propose a computing and communication co-design framework comprised of a progressive confidence network, and an attention-based multi-scale preprocessing, used to identify on-satellite inferring data, and reduce data redundancy before satellite-GS transmission, separately. We implement, and evaluate SpaceVerse on real-world LEO satellite constellations and datasets, achieving a 31.2% average gain in accuracy and a 51.2% reduction in latency compared to state-of-the-art baselines.

Wireless respiratory monitoring has garnered significant attention for its potential in various applications. However, existing systems face practical challenges in adapting to new data domains without substantial customization efforts. Current solutions attempt to address this limitation through domain-independent feature extraction or cross-domain feature translation, employing either knowledge-based sensing models or data-driven neural networks. However, these approaches typically require additional data collection or model retraining for new domains, significantly hindering their practical deployment. This paper proposes RF-Carer, a fully zero-effort cross-domain respiration monitoring system. Our key innovation lies in building an explainable propagation model to transform any heterogeneous signals under unknown domains into a unified form in the signal processing layer. To further address accidental irrelevant factors, we propose to align the feature spaces while suppressing the noisy ones with contrastive learning. On this basis, we develop a one-fits-all model that requires only one-time training but can adapt to unknown scenarios with unconstrained user movements, postures, positions, etc. To the best of our knowledge, RF-Carer is the first zero-effort cross-domain respiration monitoring work with wireless RF signals and would be a fundamental step toward real-world deployments.Chen

While unencrypted information inspection in physical layer (e.g., open headers) can provide deep insights for optimizing wireless networks, the state-of-the-art (SOTA) methods heavily depend on full sampling rate (a.k.a Nyquist rate), and high-cost radios, due to terrestrial and non-terrestrial networks densely occupying multiple bands across large bandwidth (e.g., from 4G/5G at 0.4–7 GHz to LEO satellite at 4–40 GHz). To this end, we present SigChord, an efficient physical layer inspection system built on low-cost and sub-Nyquist sampling radios. We first design a deep and rule-based interleaving algorithm based on Transformer network to perform spectrum sensing and signal recovery under sub-Nyquist sampling rate, and second, cascade protocol identifier and decoder based on Transformer neural networks to help physical layer packets analysis. We implement SigChord using software-defined radio platforms, and extensively evaluate it on over-the-air terrestrial and non-terrestrial wireless signals. The experiments demonstrate that SigChord delivers over 99% accuracy in detecting and decoding, while still decreasing 34% sampling rate, compared with the SOTA approaches.

As a technology with ubiquitous presence in unlicensed spectrum, Wi-Fi has demonstrated prominent capabilities in both communication and sensing. However, since the bandwidth requirements for communication and sensing differ significantly, channel bandwidths excessive for communication (e.g., 160 MHz) still fail to achieve multi-person sensing. Though stitching multiple consecutive channels to expand the effective bandwidth sounds plausible, it may never reachultra-wideband(UWB) in practice. To this end, we propose UWB-Fi as a novel Wi-Fi sensing framework with ultra-wide bandwidth, leveraging only discrete and irregular channel samples. We first design a fast channel hopping scheme to enable arbitrary channel sampling across 4.7GHz bandwidth on commodityWi-Fi hardware without interrupting default communications. As no algorithm exists to exploit such channel samples, we establish a theoretical analysis driven bycompressive sensing, so as to enable anexplainabledeep learning model. This model transforms sparse channel samples into high-dimensional (position) spectra, effectively avoiding thebias-variance dilemmain parameter estimation while encoding sufficient information for general sensing. Our extensive evaluations demonstrate that UWB-Fi successfully achieves centimeter-level fine-granularity multi-person sensing.

This paper presents GBSense, an innovative compressed spectrum sensing system designed for GHz-bandwidth signals in dynamic spectrum access (DSA) applications. GBSense introduces an efficient approach to periodic non-uniform sampling, capturing wideband signals using significantly lower sampling rates compared to traditional Nyquist sampling. By integrating time-interleaved analog-to-digital conversion, GBSense overcomes the hardware complexity typically associated with traditional multicoset sampling, providing precise, adjustable sampling patterns without the need for analog delay circuits. The system’s ability to process signals with a 2 GHz radio frequency bandwidth using only a 400 MHz average sampling rate enables more efficient spectrum monitoring and access in wideband cognitive radios. Lab tests demonstrate 100% accurate spectrum detection when the spectrum occupancy is below 100 MHz and over 80% accuracy for occupancy up to 200 MHz. Additionally, an integrated system utilizing a low-power Raspberry Pi processor achieves a low processing latency of around 30 ms per frame, demonstrating the system’s potential for DSA applications in next-generation wireless networks.

Biometrics has been increasingly integrated into wearables for enhanced data security in recent years. Meanwhile, wearable popularity offers a unique chance to capture novel biometrics via embedded sensors. In this article, we study new intracorporal biometrics combining the uniqueness of heart motion, bone conduction, and body asymmetry. Specifically, we introduce HeartPrint, a passive yet secure user authentication system exploiting the bone-conducted heart sounds captured by (widely available) dualin-ear microphones (IEMs). To eliminate interference, we devise a novel method combining modified non-negative matrix factorization and adaptive filtering. This extracts clean heart sounds while addressing interference of body sounds and audio produced by the earphones. We further explore the uniqueness of IEM-recorded heart sounds in three aspects to extract a novel biometric representation, based on which HeartPrint leverages a convolutional neural model equipped with a continual learning method to achieve accurate authentication under drifting body conditions. Furthermore, user-friendly registration and energy-effective authentication are facilitated by a data augmentation method using transformer-based GAN and an authentication interval control method. Extensive experiments with 45 participants confirm that HeartPrint can achieve 1.6% FAR and 1.8% FRR, while effectively coping with major attacks, complicated interference, and hardware diversity, while exhibiting robustness in real-world environments.

In the field of digital security, Reversible Adversarial Examples (RAE) combine adversarial attacks with reversible data hiding techniques to effectively protect sensitive data and prevent unauthorized analysis by malicious Deep Neural Networks (DNNs). However, existing RAE techniques primarily focus on white-box attacks, lacking a comprehensive evaluation of their effectiveness in black-box scenarios. This limitation impedes their broader deployment in complex, dynamic environments. Furthermore, traditional black-box attacks are often characterized by poor transferability and high query costs, significantly limiting their practical applicability. To address these challenges, we propose the Dual-Phase Merging Transferable Reversible Attack method, which generates highly transferable initial adversarial perturbations in a white-box model and employs a memory-augmented black-box strategy to effectively mislead target models. Experimental results demonstrate the superiority of our approach, achieving a 99.0% attack success rate and 100% recovery rate in black-box scenarios with the DN-121 target model and 1000 attack iterations, highlighting its robustness in privacy protection. Moreover, we successfully implemented a black-box attack on a commercial model, further substantiating the potential of this approach for practical use.

Given the wide adoption of multimodal sensors (e.g., camera, lidar, radar) byautonomous vehicles (AVs), deep analytics to fuse their outputs for a robust perception become imperative. However, existing fusion methods often make two assumptions rarely holding in practice: i) similar data distributions for all inputs and ii) constant availability for all sensors. Because, for example, lidars have various resolutions and failures of radars may occur, such variability often results in significant performance degradation in fusion. To this end, we present t-READi, an adaptive inference system that accommodates the variability of multimodal sensory data and thus enables robust and efficient perception. t-READi identifies variation-sensitive yetstructure-specificmodel parameters; it then adapts only these parameters while keeping the rest intact. t-READi also leverages a cross-modality contrastive learning method to compensate for the loss from missing modalities. Both functions are implemented to maintain compatibility with existing multimodal deep fusion methods. The extensive experiments evidently demonstrate that compared with the status quo approaches, t-READi not only improves the average inference accuracy by more than 6% but also reduces the inference latency by almost 15× with the cost of only 5% extra memory overhead in the worst case under realistic data and modal variations.

Recently, a large number of Low Earth Orbit (LEO) satellites have been launched and deployed successfully in space. Due to multimodal sensors equipped by the LEO satellites, they serve not only for communications but also for various machine learning applications. However, a ground station (GS) may be incapable of downloading such a large volume of raw sensing data for centralized model training due to the limited contact time with LEO satellites (e.g. 5 minutes). Therefore,federated learning(FL) has emerged as the promising solution to address this problem via on-device training. Unfortunately, enabling FL on LEO satellites still face three critical challenges: i) heterogeneous computing and memory capabilities, ii) limited downlink/uplink rate, and iii) model staleness. To this end, we proposeFedSNas a general FL framework to tackle the above challenges. Specifically, we first present a novel sub-structure scheme to enable heterogeneous local model training considering different computing, memory, and communication constraints on LEO satellites. Additionally, we propose a pseudo-synchronous model aggregation strategy to dynamically schedule model aggregation for compensating model staleness. Extensive experiments with real-world satellite data demonstrate that FedSN framework achieves higher accuracy, lower computing, and communication overhead than the state-of-the-art benchmarks.

As AI models expand in size, it has become increasingly challenging to deploy federated learning (FL) on resource-constrained edge devices. To tackle this issue,split federated learning(SFL) has emerged as an FL framework with reduced workload on edge devices via model splitting; it has received extensive attention from the research community in recent years. Nevertheless, most prior works on SFL focus only on a two-tier architecture without harnessing multi-tier cloud-edge computing resources. In this paper, we intend to analyze and optimize the learning performance of SFL under multi-tier systems. Specifically, we propose the hierarchical SFL (HSFL) framework and derive its convergence bound. Based on the theoretical results, we formulate a joint optimization problem for model splitting (MS) and model aggregation (MA). To solve this rather hard problem, we then decompose it into MS and MA sub-problems that can be solved via an iterative descending algorithm. Simulation results demonstrate that the tailored algorithm can effectively optimize MS and MA in multi-tier systems and significantly outperform existing schemes.

The low-orbit mega-constellation network (LMCN) is an important part of the space-air-ground integrated network system. An effective satellite-ground interconnection design can result in a stable constellation topology for LMCNs. A naïve solution is accessing the satellite with the longest remaining service time (LRST), which is widely used in previous designs. The Coordinated Satellite-Ground Interconnecting (CSGI), the state-of-the-art algorithm, coordinates the establishment of ground-satellite links (GSLs). Compared with existing solutions, it reduces latency by 19% and jitter by 70% on average. However, CSGI only supports the scenario where terminals access only one satellite, and cannot fully utilize the multi-access capabilities of terminals. Additionally, CSGI's high computational complexity poses deployment challenges. To overcome these problems, we propose the Classification-based Longest Remaining Service Time (C-LRST) algorithm. C-LRST supports the actual scenario with multi-access capabilities. It adds optional paths during routing with low computational complexity, improving end-to-end communications quality. We conduct our 1000 s simulation from Brazil to Lithuania on the open-source platform Hypatia. Experiment results show that compared with CSGI, C-LRST reduces the latency and increases the throughput by approximately 60% and 40%, respectively. In addition, C-LRST's GSL switchings number is 14, whereas CSGI is 23. C-LRST has better link stability than CSGI.

Due to sophisticated deployments of all kinds of wireless networks (e.g., 5G, Wi-Fi, Bluetooth, LEO satellite, etc.), multiband signals distribute in a large bandwidth (e.g., from 70 MHz to 8 GHz). Consequently, for network monitoring and spectrum sharing applications, a sniffer for extracting physical layer information, such as structure of packet, with low sampling rate (especially, sub-Nyquist sampling) can significantly improve their cost- and energy-efficiency. However, to achieve a multiband signals sniffer is really a challenge. To this end, we propose Sums, a system that can sniff and analyze multiband signals in a blind manner. Our Sums takes advantage of hardware and algorithm co-design, multi-coset sub-Nyquist sampling hardware, and a multi-task deep learning framework. The hardware component breaks the Nyquist rule to sample GHz bandwidth, but only pays for a 50 MSPS sampling rate. Our multi-task learning framework directly tackles the sampling data to perform spectrum sensing, physical layer protocol recognition, and demodulation for deep inspection from multiband signals. Extensive experiments demonstrate that Sums achieves higher accuracy than the state-of-the-art baselines in spectrum sensing, modulation classification, and demodulation. As a result, our Sums can help researchers and end-users to diagnose or troubleshoot their problems of wireless infrastructures deployments in practice.

Object identification is a pivotal enabling technique for smart home and manufacturing applications. Traditional methodologies for object identification predominantly rely on a singular sensor modality, which inherently limits their ability to furnish a detailed characterization of the target object. Addressing this deficiency, in this paper, we fill this gap by introducing CRFUSION, the first-of-its-kind system that integrates the object RGB image and the radio frequency (RF) signal reflected by the object for fine-grained object identification. CRFUSION leverages the complementary characteristics between visible light and radio frequency modalities to simultaneously determine the category and material of target objects. We design a multifaceted object feature from the RF signal, called the Energy Reflection Factor (ERF), which not only reveals the object texture but complements the image modality for identifying the object category. By integrating the characteristics of radar, we obtain radar feature maps based on the ERF of target objects. Additionally, we have developed a modality fusion network to comprehensively integrate the image and ERF features. We conducted a comprehensive evaluation of CRFUSION using a commercial mmWave radar development board and camera. The results show that CRFUSION achieves a classification accuracy of over 96%, demonstrating its robustness, and potential for application.

With the increasing popularity of virtual reality applications, there is an increasing demand for more interactive entertainment, learning, social interactions, and other activities on eyewear devices. Recognizing users’ emotion and providing reliable feedback can significantly improve the immersive experience for users. However, previous works in emotion recognition required modifications to existing eyewear devices and the integration of additional sensors, or relied on specialized sensors in expensive commercial-grade eyewear devices, making direct deployment on existing consumer-grade eyewear devices challenging. In this paper, we proposeAccEmo, the first system that analyzes the data from the built-in accelerometer sensor on eyewear devices to accurately recognize human emotion.AccEmofirst employs signal processing technologies to process raw accelerometer data, and then uses a binary classification network to determine whether the accelerometer data is influenced by emotional changes. Subsequently,AccEmoproposes a network architecture based on residual neural network and channel-wise attention mechanism as a universal feature extractor to extract complex features related to human emotions from the accelerometer data. Finally,AccEmouses personalized classifiers to achieve emotion recognition for different users. Extensive performance evaluation ofAccEmoacross diverse users demonstrates an exceptional average accuracy of 94.3%. Additionally, the robustness ofAccEmois validated through evaluations in various scenarios, yielding promising results.

Blood pressure (BP) measurement is significant to the assessment of many dangerous health conditions. Apart from invasively inserting catheters into arteries, non-invasive approaches typically rely on wearing devices on specific skin areas with consistent pressure. However, this can be uncomfortable and unsuitable for certain individuals, and the accuracy of these methods may significantly decrease due to improper device placements and wearing states. Recently, contactless methods leveraging RF technology have emerged as a potential alternative. However, these methods suffer from the drawback of overfitting deep learning (DL) models without a sound physiological basis, resulting in a lack of clear explanations for their outputs. Consequently, such limitations lead to skepticism and distrust among medical experts. In this paper, we propose hBP-Fi, a contactless BP measurement system driven by hemodynamics acquired via RF sensing. In addition to its contactless convenience, hBP-Fi is superior to other RF sensing approaches in i) grounding on hemodynamics as the key physical process of heart-pulse activities, ii) exploiting beam-steerable RF devices to achieve a super-resolution scan on the fine-grained pulse activities along arm arteries, and iii) ensuring the trustworthiness of system outputs via an explainable (decision-understandable) DL model. Extensive experiments with 35 subjects demonstrate that hBP-Fi can achieve the error of -2.05±6.83 mmHg and 1.99 ± 6.30 mmHg for monitoring systolic and diastolic blood pressures, respectively.

Wi-Fi signals are commonly used for conventional communication, yet they can also realize low-cost and non-invasive human sensing. However, Wi-Fi sensing in Multi-person scenarios is still a challenging problem. In this paper, we propose M2-Fi to achieve multi-person respiration monitoring using a handheld device. M2-Fi leverages Wi-Fi BFI (beamforming feedback information) performs respiration monitoring. As a compressed version of the uplink CSI (channel state information), BFI transmission is unencrypted, easily obtained using frame capture, and does not require specific firmware to obtain. M2-Fi is based on an interesting experiment phenomenon that when a Wi-Fi device is very close to a subject, near-field channel changes caused by the subject significantly cancel out changes from other subjects. We employed VMD (Variational Mode Decomposition) to eliminate the interference caused by hand movement in the BFI time series. Subsequently, we devised a deep learning architecture based on GAN (Generative Adversarial Networks) to recover fine-grained respiration waveforms from the respiration patterns extracted from the BFI time series. Our experiments on collected 50-hour data from 8 subjects show that M2-Fi can accurately recover the respiration waveforms of multiple persons with handheld devices.

New Wi-Fi systems have leveraged beamforming to manage a significant portion of traffic for achieving high throughput and reliability. Unfortunately, this has amplified certain security risks since beamforming critically relies on the clear-text beamforming feedback information (BFI): though similar risks have been exposed using emulation platforms (e.g., USRP), they have never proven realistic till this day. In this paper, we propose BeamCraft, the first attack to manipulate traffic in commodity Wi-Fi systems; it differs significantly from existing attacks either staying only on emulation platforms with limited real-world applicability or jamming communications by brute force. The core idea of BeamCraft involves corrupting beamforming decisions by injecting crafted BFIs that feed an access point (AP) with erroneous information on channel states. To mount a covert yet purposeful attack, we develop i) a joint location and transmit power selection strategy to evade detection by victims and ii) a novel BFI forgery method to effectively manipulate AP's beamforming decisions. We implement BeamCraft using commodity Wi-Fi devices and perform extensive evaluations with it; the results reveal that BeamCraft effectively manipulates Wi-Fi traffic while maintaining a low exposure rate.

The limited bandwidth of Wi-Fi severely confines the granularity (especially in differentiating multiple subjects) of Wi-Fi sensing, posing a significant challenge for its wide adoption. Though utilizing multiple channels to expand the effective bandwidth sounds plausible, continuous spectrum stitching towards ultra-wideband (UWB) is far from practical given various constraints (e.g., the runtime channel availability and inconsistent channel responses across a wide bandwidth). To this end, we propose UWB-Fi as a novel Wi-Fi sensing system with ultra-wide bandwidth, leveraging only discrete and irregular channel sampling. We first design a fast channel hopping scheme to perform arbitrary sampling across 4.7GHz (i.e., 2.4 to 7.1GHz) bandwidth on commodity Wi-Fi hardware without interrupting default communications. As no signal processing tool is available to handle such channel samples, we innovate in a model-based deep learning approach that translates discrete channel samples to high-dimensional spectral parameters; this method successfully avoids the bias-variance tradeoff in parameter estimation, while filtering out hardware-related offsets inherent to Wi-Fi. Through extensive evaluations, we demonstrate that UWB-Fi successfully achieves fine-granularity sensing, enabling centimeter-level resolution for indoor multi-person sensing.

Wi-Fi signals may help realize low-cost and noninvasive human sensing, yet it can also be exploited by eavesdroppers to capture private information. Very few studies rise to handle this privacy concern so far; they either jam all sensing attempts or rely on sophisticated technologies to support only a single sensing user, rendering them impractical for multi-user scenarios. Moreover, these proposals all fail to exploit Wi-Fi’s multiple-in multiple-out (MIMO) capability. To this end, we propose MIMOCrypt, a privacy-preserving Wi-Fi sensing framework to support realistic multi-user scenarios. To thwart unauthorized eavesdropping while retaining the sensing and communication capabilities for legitimate users, MIMOCrypt innovates in exploiting MIMO to physically encrypt Wi-Fi channels, treating the sensed human activities as physical plaintexts. The encryption scheme is further enhanced via an optimization framework, aiming to strike a balance among i) risk of eavesdropping, ii) sensing accuracy, and iii) communication quality, upon securely conveying decryption keys to legitimate users. We implement a prototype of MIMOCrypt on an SDR platform and perform extensive experiments to evaluate its effectiveness in common application scenarios, especially privacy-sensitive human gesture recognition.

Stress tracing is an important research domain that supports many applications, such as health care and stress management; and its closest related works are derived from stress detection. However, these existing works cannot well address two important challenges facing stress detection. First, most of these studies involve asking the users to wear physiological sensors to detect their stress states, which has a negative impact on the user experience. Second, these studies have failed to effectively utilize the multimodal physiological signals, which results in less satisfactory detection results. This article formally defines the stress tracing problem, which emphasizes the continuous detection of human stress states. A novel deep stress tracing (DST) method, named DST, is presented. Note that, DST proposes tracing human stress based on the physiological signals collected by a noncontact ultrawideband radar, which is more friendly to users when collecting their physiological signals. In DST, a signal extraction module is carefully designed at first to robustly extract the multimodal physiological signals from the raw RF data of the radar, even in the presence of body movement. Afterward, a multimodal fusion module is proposed in DST to ensure that the extracted multimodal physiological signals can be effectively fused and utilized. Extensive experiments are conducted on the three real-world data sets, including one self-collected data set and two publicity data sets. Experimental results show that the proposed DST method significantly outperforms all the baselines in terms of tracing human stress states. On average, DST averagely provides a 6.31% increase in detection accuracy on all the data sets, compared with the best baselines.

Hand pose estimation (HPE), which aims to identify and recover the keypoints of a hand, is essential to many potential applications. Conventional computer vision (CV) methods extract visible features from images or videos captured by cameras. However, they are heavily affected by low image contrast, fail to work under occluded scenarios, and inevitably incur privacy concerns. Fortunately, CV leveraging widely available radio frequency (RF) signals (also known as RF vision) can fully address the problem with much lower computational complexity. In this article, we propose Ske-Fi as an avatar of hand pose estimation (HPE) enabled by RF vision, which uses the emerging impulse radio ultrawide band (IR-UWB) available on smart devices (e.g., Apple air tag) to sense the reflected RF signals of a hand to extract the hand skeleton features for pose estimation. Whereas Ske-Fi is apparently immune to low contrast and occlusion, its substantially reduced resolution provided by IR-UWB signal makes the resulting RF image incomprehensible by human eyes and thus negating offline labeling. To address the challenge, Ske-Fi involves a deep complex-valued neural network Ske-Net trained via a cross-modal supervision framework; it uses a synchronized camera assisted by a state-of-the-art vision network as a teacher to teach Ske-Net as a student in independently performing HPE afterward. Furthermore, for occlusion cases, Ske-Fi adopts an adversarial learning scheme to distill HPE features regardless of diversified occlusions. Our extensive evaluations evidently demonstrate that Ske-Fi outperforms conventional CV solutions which achieves a comparable HPE accuracy under normal circumstances and maintains this accuracy under adverse scenarios.

The contact-free sensing nature of Wi-Fi has been leveraged to achieve privacy breaches such askeystroke inference(KI). However, the use ofchannel state information(CSI) in existing attacks is highly questionable due to its signal instability and hardness to acquire. Moreover, such Wi-Fi-based attacks are confined to only one victim because Wi-Fi sensing offers insufficient range resolution to physically differentiate multiple victims. To this end, we propose MuKI-Fi to enable, for the first time,multi-personKI, leveragingbeamforming feedback information(BFI), a new feature offered by latest Wi-Fi hardware, transmitted in clear-text by smartphones. BFI's characteristics, clear-text communication and signal stability, make it readily acquirable and usable by any other Wi-Fi devices switching to monitor mode without the need forlow-levelhacking on hardware. Moreover, to improve upon existing KI methods offering very limited generalizability across diversified application scenarios, MuKI-Fi innovates in an adversarial learning scheme to enable its inference generalizable towards unseen scenarios. Finally, we discover that, as a smartphone is in close proximity to a victim, the variations of BFI caused by that victim's keystrokes in suchnear-fieldsubstantially outweigh those caused by other distant victims; this phenomenon naturally allows for multi-person KI. Our extensive evaluations clearly demonstrate that MuKI-Fi can effectively eavesdrop on the keystrokes of multiple subjects, achieving 87.1% accuracy for individual keystrokes and up to 81% top-100 accuracy for stealing passwords from mobile applications(e.g., WeChat) on average.

Introduction to the Special Section on Contact-free Smart Sensing in AloTArtificial Intelligence (AI) and the Internet of Things (IoT) are two powerful forces that have been reshaping our world in recent years.When they converge, they create a new field of AIoT that enables ubiquitous intelligence through the integration of smart algorithms and connected devices.One of the key enablers of AIoT is contact-free sensing, which leverages the availability of portable and highly integrated WiFi, radar, and sonar-style devices to monitor humans and environments without physical contact.This technology has transformed the traditional computer vision-based paradigms and opened up novel possibilities for data collection and analysis.However, contactfree sensing also poses new challenges and risks for AIoT applications.The dynamic and complex wireless environments require innovative solutions for efficient data processing and interpretation.The security and privacy issues of WiFi, radar, and sonar-enabled sensing devices also demand urgent attention, as they may expose sensitive information to malicious attacks.Therefore, it is imperative to explore the potential and pitfalls of contact-free sensing in AIoT and to develop effective strategies for ensuring the robustness and reliability of AIoT applications.This special issue is dedicated to highlighting the cutting-edge methods and latest research in the field of contact-free sensing, which leverages WiFi, radar, and sonar-style devices to monitor humans and environments without physical contact.The main focus of this issue is to explore the latest machine learning analytics to extract information from the sensory data and to investigate the potential risks and countermeasures to ensure the security and privacy of sensing devices.The call for papers attracted with 44 submissions and after a rigorous review, 18 papers have been accepted for this special issue.A brief summary of some papers in this special issue is presented in the following:In "Feasibility of Remote Blood Pressure Estimation via Narrow-band Multi-wavelength Pulse Transit Time, " the authors investigate the feasibility of estimating blood pressure (BP) via pulse transit time (PTT) in a novel remote single-site manner using a modified RGB camera.A narrowband triple band-pass filter makes it possible to measure the PTT between different skin layers, harvesting information from green and near-infrared wavelengths.They design a color-channel model and a novel channel-separation method to further resolve the inter-channel influence and band overlap.The results showed a good absolute Pearson's correlation coefficient between both MW PTT and systolic BP as well as diastolic BP, pointing to the feasibility of the proposed novel remote MW BP estimation via PTT.In "LiteWiSys: A Lightweight System for WiFi-based Dual-task Action Perception, " Sheng et al. propose a lightweight system named LiteWiSys that can simultaneously detect and recognize WiFi-based human actions.This work addresses two major drawbacks of existing methods: heavy

The contact-free sensing nature of Wi-Fi has been leveraged to achieve privacy breaches, yet existing attacks relying on Wi-Fi CSI (channel state information) demand hacking Wi-Fi hardware to obtain desired CSIs. Since such hacking has proven prohibitively hard due to compact hardware, its feasibility in keeping up with fast-developing Wi-Fi technology becomes very questionable. To this end, we propose WiKI-Eve to eavesdrop keystrokes on smartphones without the need for hacking. WiKI-Eve exploits a new feature, BFI (beamforming feedback information), offered by latest Wi-Fi hardware: since BFI is transmitted from a smartphone to an AP in clear-text, it can be overheard (hence eavesdropped) by any other Wi-Fi devices switching to monitor mode. As existing keystroke inference methods offer very limited generalizability, WiKI-Eve further innovates in an adversarial learning scheme to enable its inference generalizable towards unseen scenarios. We implement WiKI-Eve and conduct extensive evaluation on it; the results demonstrate that WiKI-Eve achieves 88.9% inference accuracy for individual keystrokes and up to 65.8% top-10 accuracy for stealing passwords of mobile applications (e.g., WeChat).

Metamaterial-based reconfigurable holographic surfaces (RHSs) have been proposed as novel cost-efficient antenna arrays, which are promising for improving the positioning and communication performance of integrated sensing and communications (ISAC) systems. However, due to the high frequency selectivity of the metamaterial elements, RHSs face challenges in supporting ultra-wide bandwidth (UWB), which significantly limits the positioning precision. In this paper, to avoid the physical limitations of UWB RHS while enhancing the performance of RHS-based ISAC systems, we propose a multi-band (MB) RHS based ISAC system. We analyze its positioning precision and propose an efficient algorithm to optimize the large number of variables in analog and digital beamforming. Through comparison with benchmark results, simulation results verify the efficiency of our proposed system and algorithm, and show that the system achieves 42% less positioning error, which reduces 82% communication capacity loss.

Hand Pose Estimation (HPE) is crucial to many applications, but conventional cameras-based CM-HPE methods are completely subject to Line-of-Sight (LoS), as cameras cannot capture occluded objects. In this paper, we propose to exploit Radio-Frequency-Vision (RF-vision) capable of bypassing obstacles for achieving occluded HPE, and we introduce OCHID-Fi as the first RF-HPE method with 3D pose estimation capability. OCHID-Fi employs wideband RF sensors widely available on smart devices (e.g., iPhones) to probe 3D human hand pose and extract their skeletons behind obstacles. To overcome the challenge in labeling RF imaging given its human incomprehensible nature, OCHID-Fi employs a cross-modality and cross-domain training process. It uses a pre-trained CM-HPE network and a synchronized CM/RF dataset, to guide the training of its complex-valued RF-HPE network under LoS conditions. It further transfers knowledge learned from labeled LoS domain to unlabeled occluded domain via adversarial learning, enabling OCHID-Fi to generalize to unseen occluded scenarios. Experimental results demonstrate the superiority of OCHID-Fi: it achieves comparable accuracy to CM-HPE under normal conditions while maintaining such accuracy even in occluded scenarios, with empirical evidence for its generalizability to new domains.

Having been studied for more than a decade, Wi-Fi human sensing still faces a major challenge in the presence of multiple persons, simply because the limited bandwidth of Wi-Fi fails to provide a suficient range resolution to physically separate multiple subjects. Existing solutions mostly avoid this challenge by switching to radars with GHz bandwidth, at the cost of cumbersome deployments. Therefore, could Wi-Fi human sensing handle multiple subjects remains an open question. This paper presents MUSE-Fi, the first Wi-Fi multi-person sensing system with physical separability. The principle behind MUSE-Fi is that, given a Wi-Fi device (e.g., smartphone) very close to a subject, the near-field channel variation caused by the subject significantly overwhelms variations caused by other distant subjects. Consequently, focusing on the channel state information (CSI) carried by the trafic in and out of this device naturally allows for physically separating multiple subjects. Based on this principle, we propose three sensing strategies for MUSE-Fi: i) uplink CSI, ii) downlink CSI, and iii) downlink beamforming feedback, where we specifically tackle signal recovery from sparse (per-user) trafic under realistic multi-user communication scenarios. Our extensive evaluations clearly demonstrate that MUSE-Fi is able to successfully handle multi-person sensing with respect to three typical applications: respiration monitoring, gesture detection, and activity recognition.

Object detection with on-board sensors (e.g., lidar, radar, and camera) is crucial to autonomous driving (AD), and these sensors complement each other in modalities. While crowdsensing may potentially exploit these sensors (of huge quantity) to derive more comprehensive knowledge, federated learning (FL) appears to be the necessary tool to reach this potential: it enables autonomous vehicles (AVs) to train machine learning models without explicitly sharing raw sensory data. However, the multimodal sensors introduce various data heterogeneity across distributed AVs (e.g., label quantity skews and varied modalities), posing critical challenges to effective FL. To this end, we present AutoFed as a heterogeneity-aware FL framework to fully exploit multimodal sensory data on AVs and thus enable robust AD. Specifically, we first propose a novel model leveraging pseudo labeling to avoid mistakenly treating unlabeled objects as the background. We also propose an autoencoder-based data imputation method to fill missing data modality (of certain AVs) with the available ones. To further reconcile the heterogeneity, we finally present a client selection mechanism based on client model similarities to improve training stability and convergence rate. Our experiments confirm that AutoFed substantially improves over status quo in both precision and recall, while demonstrating strong robustness to adverse weather.

With the help of machine learning, models are trained to recognize human activity based on radio frequency signals, which are widely used in human-computer interaction, healthcare, etc. Cross-domain human activity recognition (HAR) aims to adapt a model trained in a specific source domain (including environment and user) for another target domain. Most existing cross-domain recognition methods are proposed under an ideal closed-set assumption, which means the training set and the testing set contain the same categories of human activities. However, when a model is applied in practice for HAR, it often encounters new categories of activities which are not contained in the training set. Under such open-set condition, the traditional closed-set cross-domain recognition model usually incorrectly identifies the new activity as a known activity, which decline the recognition accuracy. In this article, a model is proposed for open-set cross-domain HAR. The model is established based on generative adversarial network, and a unique generation module is designed to generate confusing samples whose features are similar to known classes. Thanks to such design, the proposed model can autonomously select appropriate unlabeled samples under the open-set condition to improve the open-set recognition ability of the model in the target domain. Extensive experiments are conducted based on four real data sets, one is collected by ourselves and the other three are public. The results show that the proposed model outperforms other state-of-the-art methods in the open-set and the cross-domain contexts.

Positioning is an essential service for various applications and is expected to be integrated with existing communication infrastructures in 5G and 6G. Though current Wi-Fi and cellular base stations (BSs) can be used to support this integration, the resulting precision is unsatisfactory due to the lack of precise control of the wireless signals. Recently, BSs adopting reconfigurable holographic surfaces (RHSs) have been advocated for positioning as RHSs’ large number of antenna elements enable generation of arbitrary and highly-focused signal beam patterns. However, existing designs face two major challenges: i) RHSs only have limited operating bandwidth, and ii) the positioning methods cannot adapt to the diverse environments encountered in practice. To overcome these challenges, we present HoloFed, a system providing high-precision environment-adaptive user positioning services by exploitingmulti-band(MB)-RHS andfederated learning(FL). For improving the positioning performance, a lower bound on the error variance is obtained and utilized for guiding MB-RHS’s digital and analog beamforming design. For better adaptability while preserving privacy, an FL framework is proposed for users to collaboratively train a position estimator, where we exploit the transfer learning technique to handle the lack of position labels of the users. Moreover, a scheduling algorithm for the BS to select which users train the position estimator is designed, jointly considering the convergence and efficiency of FL. Our performance evaluation based on simulations confirms that HoloFed achieves a 57% lower positioning error variance compared to a beam-scanning baseline and can effectively adapt to diverse environments.

Human activity recognition (HAR) plays a critical role in a wide range of real-world applications, and it is traditionally achieved via wearable sensing. Recently, to avoid the burden and discomfort caused by wearable devices, device-free approaches exploiting radio-frequency (RF) signals arise as a promising alternative for HAR. Most of the latest device-free approaches require training a large deep neural network model in either time or frequency domain, entailing extensive storage to contain the model and intensive computations to infer human activities. Consequently, even with some major advances on device-free HAR, current device-free approaches are still far from practical in real-world scenarios where the computation and storage resources possessed by, for example, edge devices, are limited. To overcome these weaknesses, we introduce HAR-SAnet which is a novel RF-based HAR framework. It adopts an original signal adapted convolutional neural network architecture: instead of feeding the handcraft features of RF signals into a classifier, HAR-SAnet fuses them adaptively from both time and frequency domains to design an end-to-end neural network model. We apply point-wise grouped convolution and depth-wise separable convolutions to confine the model scale and to speed up the inference execution time. The experiment results show that the recognition accuracy of HAR-SAnet substantially outperforms the state-of-the-art algorithms and systems.

Continuous respiration monitoring is significant for real-life healthcare applications, but realizing it is extremely hard as wearable sensors are cumbersome and contact-free sensors largely fail to tolerate user movements. Meanwhile, tracking users indoors mostly demands user-held devices, while device-free localization can barely tell what and who it tracks. Fortunately, as both contact-free respiration monitoring and device-free localization may rely on Radio-Frequency (RF) sensing, fusing them together creates a novel system capable of continuously tracking users while recovering their fine-grained respiratory waveforms. To this end, we propose BreathCatcher as a continuous human respiration tracking system for indoor applications. To build this system, we employ commercial-grade compact radar pairs to capture RF reflections containing respiratory signals. We then propose a hybrid human respiration and position tracking algorithm to locate and identify respiratory signals from complex RF reflection mixtures. Finally, we design an encoder-decoder deep neural network driven by variational inference to recover fine-grained respiratory waveforms. Essentially, BreathCatcher cannot only obtain respiratory waveforms from multiple walking users, but also identify each user according to the latent properties of the respiratory signals. We evidently demonstrate the accuracy of both tracking and respiration monitoring via experiments involving 12 subjects and 80 man-hour data.

Authentication mechanisms deployed on access control systems undertake the responsibility of judging user identity to prevent unauthorized individuals from illegally approaching. In this article, we propose LIPAuth leveraging hand-dependent L ight I ntensity P attern to Auth enticate users. To be specific, lights released by a screen, are blocked and reflected by one hand above it; in this propagation process, hands exhibit user-specific ability in driving light absorption and attenuation due to owning unique structures, thereby outputting discriminative intensity patterns representing user identity. To implement LIPAuth , we first study the impact of screen contents on light intensity patterns, also explore the possibility of embedding hand structure biometrics into these patterns. We then design a customized dynamic stimulus-response mechanism for LIPAuth and make it resilient to the risks of potential registration profile leakage. Subsequently, we construct a joint pipeline consisting of signal processing and a learning-based generative adversarial network to overcome interference from variable user behaviors. More importantly, LIPAuth just utilizes common sensors to capture light signals, hence achieving low cost. We finally conduct extensive experiments in three scenarios to evaluate the authentication performance of LIPAuth prototype.

Contact-free vital-signs monitoring enabled by radio frequency (RF) sensing is gaining increasing attention, thanks to its non-intrusiveness, noise-resistance, and low cost. Whereas most of these systems only perform respiration monitoring or retrieve heart rate, few can recover fine-grained heartbeat waveform. The major reason is that, though both respiration and heartbeat cause detectable micro-motions on human bodies, the former is so strong that it overwhelms the latter. In this paper, we aim to answer the question in the paper title, by demystifying how heartbeat waveform can be extracted from RF-sensing signal. Applying several mainstream methods to recover heartbeat waveform from raw RF signal, our results reveal that these methods may not achieve what they have claimed, mainly because they assume linear signal mixing whereas the composition between respiration and heartbeat can be highly nonlinear. To overcome the difficulty of decomposing nonlinear signal mixing, we leverage the power of a novel deep generative model termed variational encoder-decoder (VED). Exploiting the universal approximation ability of deep neural networks and the generative potential of variational inference, VED demonstrates a promising capability in recovering fine-grained heartbeat waveform from RF-sensing signal; this is firmly validated by our experiments with 12 subjects and 48-hour data.

Proliferation of smart environments entails the need for real-time and ubiquitous human-machine interactions through, mostly likely, hand/arm motions. Though a few recent efforts attempt to track hand/arm motions in real-time with COTS devices, they either obtain a rather low accuracy or have to rely on a carefully designed infrastructure and some heavy signal processing. To this end, we propose SoM (Sound of Motion) as a lightweight system for wrist tracking. Requiring only a smart watch-phone pair, SoM entails very light computations that can operate in resource constrained smartwatches. SoM uses embedded IMU sensors to perform basic motion tracking in the smartwatch, and it depends on the fixed smartphone to act as an "acoustic anchor": regular beacons sent by the phone are received in an irregular manner due to the watch motion, and such variances provide useful hints to adjust the drifting of IMU tracking. Using extensive experiments on our SoM prototype, we demonstrate that the delicately engineered system achieves a satisfactory wrist tracking accuracy and strikes a good balance between complexity and performance.

Optical camera communication (OCC) enabled by LED and embedded cameras has attracted extensive attention, thanks to its rich spectrum availability and ready deployability. However, the close interactions between OCC and the indoor spaces have created two major challenges. On one hand, the stripe pattern incurred by OCC may greatly damage the accuracy of image-based object recognition. On the other hand, the patterns inherent to indoor spaces can significantly degrade the decoding performance of reflected OCC. To this end, we propose CORE-Lens as a pipeline to make the mutual interference transparent to existing OR and OCC algorithms. Essentially, CORE-Lens treats the two challenges as two sides of a signal mixture issue: the signals transmitted by OCC get mixed with background images so well that their features become entangled. Consequently, CORE-Lens exploits the idea of disentangled representation learning to separate the mixed signals in the feature space: while the GAN-reconstructed clean background images are used to perform object recognition, OCC decoding is conducted on the residual of the original image after subtracting the reconstructed background. Our extensive experiments on evaluating the real-life performance of CORE-Lens evidently demonstrate its superiority over conventional approaches.

Recent years have witnessed a growing interest in contact-free respiration monitoring leveraging radio-frequency (RF) technologies. However, the proposed solutions mostly consider single-person scenarios, whereas a few multi-person monitoring proposals simply apply blind source separation to handle inter-person interference, without drawing a clear line between physical and algorithmic separability. In this paper, we set out to answer: under what condition(s) one may physically separate multiple respiration signals sensed by diversified RF technologies? Drawing inspiration from conventional signal processing, we propose respiration-to-interference-plus-noise ratio (RINR) as a novel metric, taking into account the impact from both background noise and various interfering sources. Instead of attenuation in Euclidean distance, RINR has to be evaluated upon range/angle bins where physical separation actually take place. As signal attenuation has never been modeled in this manner, we rise to this challenge by levering a deep learning model to fit a spread function upon range/angle bins. The resulting RINR model allows us to concretely indicate the limit of physical separability of RF-based multi-person respiration monitoring. Our extensive experiments firmly validate the RINR model, thus evidently demonstrating the benefits of employing RINR model as a guideline for conducting respiration monitoring with different RF technologies.

Aerial acoustic communication attracts substantial attention for its simplicity and cost-effectiveness. Unfortunately, the preferred inaudible transmission has to strike a balance between the transmission rate and communication range, when the Bit-Error-Rate (BER) is under a certain threshold. Additionally, the performance of previous proposals can be deteriorated by dynamic channel conditions including near-far problem, device heterogeneity, and multipath fading. To this end, we propose a High-speed, long-range, and Robust Chirp Spread Spectrum (HRCSS) scheme for inaudible aerial acoustic communication under dynamic channels. HRCSS innovates in the definition of a loose orthogonality condition, and it leverages this orthogonality to overlap multiple chirp carriers in a single time duration to form a data symbol representing multiple bits, thereby substantially promoting the data rate. To further enhance system robustness in long communication ranges and dynamic channel conditions, we construct a lightweight rate adaptation algorithm and design a simple yet efficient normalization method. Experiment results reveal that HRCSS achieves a significant improvement in data rate over existing methods: it delivers 500 bps data rate with a BER of 0.24 percent at 10 m, and achieves 125 bps with zero BER at 20 m. Meanwhile, HRCSS can work adaptively under dynamic channel conditions while still retaining a BER below 3 percent.

Radio frequency (RF) technologies have achieved a great success in data communication. In recent years, pervasive RF signals are further exploited for sensing; RF sensing has since attracted attentions from both academia and industry. Existing developments mainly employ commodity Wi-Fi hardware or rely on sophisticated SDR platforms. While promising in many aspects, there still remains a gap between lab prototypes and real-life deployments. On one hand, due to its narrow bandwidth and communication-oriented design, Wi-Fi sensing offers a coarse sensing granularity and its performance is very unstable in harsh real-world environments. On the other hand, SDR-based designs may hardly be adopted in practice due to its large size and high cost. To this end, we propose, design, and implement Octopus, a compact and flexible wideband MIMO sensing platform, built using commercial-grade low-power impulse radio. Octopus provides a standalone and fully programmable RF sensing solution; it allows for quick algorithm design and application development, and it specifically leverages the wideband radio to achieve a competent and robust performance in practice. We evaluate the performance of Octopus via micro-benchmarking, and further demonstrate its applicability using representative RF sensing applications, including passive localization, vibration sensing, and human/object imaging.

Vital signs are crucial indicators for human health, and researchers are studying contact-free alternatives to existing wearable vital signs sensors. Unfortunately, most of these designs demand a subject human body to be relatively static, rendering them very inconvenient to adopt in practice where body movements occur frequently. In particular, radio-frequency (RF) based contact-free sensing can be severely affected by body movements that overwhelm vital signs. To this end, we introduce MoVi-Fi as a motion-robust vital signs monitoring system, capable of recovering fine-grained vital signs waveform in a contact-free manner. Being a pure software system, MoVi-Fi can be built on top of virtually any commercial-grade radars. What inspires our design is that RF reflections caused by vital signs, albeit weak, do not totally disappear but are composited with other motion-incurred reflections in a nonlinear manner. As nonlinear blind source separation is inherently hard, MoVi-Fi innovatively employs deep contrastive learning to tackle the problem; this self-supervised method requires no ground truth in training, and it exploits contrastive signal features to distinguish vital signs from body movements. Our experiments with 12 subjects and 80hour data demonstrate that MoVi-Fi accurately recovers vital signs waveform under severe body movements.

Being able to see into walls is crucial for diagnostics of building health; it enables inspections of wall structure without undermining the structural integrity. However, existing sensing devices do not seem to offer a full capability in mapping the in-wall structure while identifying their status (e.g., seepage and corrosion). In this paper, we design and implement SiWa as a low-cost and portable system for wall inspections. Built upon a customized IR-UWB radar, SiWa scans a wall as a user swipes its probe along the wall surface; it then analyzes the reflected signals to synthesize an image and also to identify the material status. Although conventional schemes exist to handle these problems individually, they require troublesome calibrations that largely prevent them from practical adoptions. To this end, we equip SiWa with a deep learning pipeline to parse the rich sensory data. With innovative construction and training, the deep learning modules perform structural imaging and the subsequent analysis on material status, without the need for repetitive parameter tuning and calibrations. We build SiWa as a prototype and evaluate its performance via extensive experiments and field studies; results evidently confirm that SiWa accurately maps in-wall structures, identifies their materials, and detects possible defects, suggesting a promising solution for diagnosing building health with minimal effort and cost.

Crucial for healthcare and biomedical applications, respiration monitoring often employs wearable sensors in practice, causing inconvenience due to their direct contact with human bodies. Therefore, researchers have been constantly searching for contact-free alternatives. Nonetheless, existing contact-free designs mostly require human subjects to remain static, largely confining their adoptions in everyday environments where body movements are inevitable. Fortunately, radio-frequency (RF) enabled contact-free sensing, though suffering motion interference inseparable by conventional filtering, may offer a potential to distill respiratory waveform with the help of deep learning. To realize this potential, we introduce MoRe-Fi to conduct fine-grained respiration monitoring under body movements. MoRe-Fi leverages an IR-UWB radar to achieve contact-free sensing, and it fully exploits the complex radar signal for data augmentation. The core of MoRe-Fi is a novel variational encoder-decoder network; it aims to single out the respiratory waveforms that are modulated by body movements in a non-linear manner. Our experiments with 12 subjects and 66-hour data demonstrate that MoRe-Fi accurately recovers respiratory waveform despite the interference caused by body movements. We also discuss potential applications of MoRe-Fi for pulmonary disease diagnoses.

Owing to the ubiquitous penetration of Wi-Fi in our daily lives, Wi-Fi indoor localization has attracted intensive attentions in the last decade or so. Despite some significant progresses, the high accuracy of existing systems is still achieved at the cost of dense access point (AP) deployment. The more practical single AP localization is largely left as an open problem because the hardware-induced time delay “contaminates” the measurement of signal propagation time in the air. In this article, we design and implement M3to tackle this challenge with commodity Wi-Fi cards. M3exploits a multipath-assisted approach that turns the harmful multipath from foe to friend to enable single AP localization: a device can be pinpointed through the combination of azimuths and the relative time of flight (ToF) of Line-of-Sight (LoS) signal and reflection signals, eliminating the need for multiple APs along with their absolute ToF measurements. M3further utilizes frequency hopping to combine multiple channels to form a virtually wider-spectrum channel for higher ToF resolution. As a prominent feature of M3, the channels do not need to be adjacent. Comprehensive experiments demonstrate that M3outperforms the state-of-the-art systems and achieves a median localization accuracy of 71 cm in three environments with a single AP.

In theory, the capacity of a wireless network grows linearly with the number of users and antennas equipped at the communication devices, and hence large-scale MU-MIMO can scale up the network throughput. However, three main challenges are impeding the implementation of this promising technology in the state-of-the-art WLANs. Firstly, the current large-scale MU-MIMO technology demands a large number of high-priced RF chains. Secondly, the wireless access points (APs) are overwhelmed by channel state information (CSI) feedback for nulling multi-user and -antenna interference. Thirdly, the lack of scalable user selection scheme limits the capability of APs to serve a large user population. To address these problems, we design BUSH, a large-scale MU-MIMO prototype that performs scalable beam user selection with hybrid beamforming for phased-array antennas in legacy WLANs. We design a low complexity algorithm that assigns each pair of RF chain and analog beam to the users to effectively reduce channel correlation and cross-talk interference without instantaneous CSI feedbacks. As a prerequisite of user selection, BUSH presents a low-overhead probing scheme in multi-carrier WLANs and designs a highly accurate blind Power Azimuth Spectrum (PAS) estimation algorithm using a single RF chain. For reducing the number of RF-chains used, the phased-array antennas use analog beamforming to steer beams toward each selected downlink user, and multiple RF chains use beamforming to further mitigate the interference among users. We implement BUSH on a software-defined radio platform and evaluate its performance in more than 30 indoor scenarios. The experimental results reveal that for throughput, BUSH outperforms the legacy 802.11ac by 2.08×, and an alternative benchmark system by 1.22× on average.

Though measuring ambient temperature is often deemed as an easy job, collecting large-scale temperature readings in real-time is still a formidable task. The recent boom of network-ready (mobile) devices and the subsequent mobile crowdsourcing applications do offer an opportunity to accomplish this task, yet equipping commodity devices with ambient temperature sensing capability is highly non-trivial and hence has never been achieved. In this paper, we propose Acoustic Thermometer (AcuTe) as the first ambient temperature sensor empowered by a single commodity smartphone. AcuTe utilizes on-board dual microphones to estimate air-borne sound propagation speed, thereby deriving ambient temperature. To accurately estimate sound propagation speed, we leverage the phase of chirp signals to circumvent the low sample rate on commodity hardware. In addition, we propose to use both structure-borne and air-borne propagations to address the multipath problem. Furthermore, to prevent disruptive audible transmissions, we convert chirp signals into white noises and propose a pipeline of signal processing algorithms to denoise received samples. As a mobile, economical, highly accurate sensor, AcuTe may potentially enable many relevant applications, in particular large-scale indoor/outdoor temperature monitoring in real-time. We conduct extensive experiments on AcuTe; the results demonstrate a robust performance, a median accuracy of 0.3° C even at a varying humidity level, and the ability to conduct distributed temperature sensing in real-time.

Radio-Frequency (RF) based device-free Human Activity Recognition (HAR) rises as a promising solution for many applications. However, device-free (or contactless) sensing is often more sensitive to environment changes than device-based (or wearable) sensing. Also, RF datasets strictly require on-line labeling during collection, starkly different from image and text data collections where human interpretations can be leveraged to perform off-line labeling. Therefore, existing solutions to RF-HAR entail a laborious data collection process for adapting to new environments. To this end, we propose RF-Net as a meta-learning based approach to one-shot RF-HAR; it reduces the labeling efforts for environment adaptation to the minimum level. In particular, we first examine three representative RF sensing techniques and two major meta-learning approaches. The results motivate us to innovate in two designs: i) a dual-path base HAR network, where both time and frequency domains are dedicated to learning powerful RF features including spatial and attention-based temporal ones, and ii) a metric-based meta-learning framework to enhance the fast adaption capability of the base network, including an RF-specific metric module along with a residual classification module. We conduct extensive experiments based on all three RF sensing techniques in multiple real-world indoor environments; all results strongly demonstrate the efficacy of RF-Net compared with state-of-the-art baselines.

An ability to detect, classify, and locate complex acoustic events can be a powerful tool to help smart systems build context-awareness, e.g., to make rich inferences about human behaviors in physical spaces. Conventional methods to measure acoustic signals employ microphones as sensors. As signals from multiple acoustic sources are blended during propagation to a sensor, such methods impose a dual challenge of separating the signal for an acoustic event from background noise and from other acoustic events of interest. Recent research has proposed using radio-frequency (RF) signals, e.g., Wi-Fi and millimeter-wave (mmWave), to sense sound directly from source vibrations. Whereas these works allow separating an acoustic event from background noise, they cannot monitor multiple sound sources simultaneously. In this paper, we present UWHear, a system that simultaneously recovers and separates sounds from multiple sources. Unlike previous works using continuous-wave RF, UWHear employs Impulse Radio Ultra-Wideband (IR-UWB) technology, in order to construct an enhanced audio sensing system tackling the above challenges. Further, IR-UWB radios can penetrate light building materials, which enables UWHear to operate in some non-line-of-sight (NLOS) conditions. In addition to providing a theoretical guarantee for audio recovery using RF pulses, we also implement an audio sensing prototype exploiting a commercial-off-the-shelf IR-UWB radar. Our experiments show that UWHear can effectively separate the content of two speakers that are placed only 25cm apart. UWHear can also capture and separate multiple sounds and vibrations of household appliances while being immune to non-target noise coming from other directions.

Multiuser MIMO (MU-MIMO) empowers access points (APs) with multiple antennas to transmit multiple data streams concurrently to users by exploiting spatial multiplexing. In MU-MIMO, users need to estimate channel state information (CSI) and report it to APs, thus opening a backdoor to attackers who may forge CSI to eavesdrop the content of victims. In this paper, we explore the eavesdropping attack in a novel and practical context in which CSI forgery entangles MU-MIMO user selection in a many-users regime. The attacker hopes to optimize both the eavesdropping opportunity of being selected with the victim and the corresponding decoding quality. We propose new attack and defense mechanisms: (1) USE Attack that enables attackers to achieve near optimal eavesdropping opportunity and high decoding quality through constructing orthogonal CSI against victims followed by stepwise refinements; (2) AngleSec that exploits channel reciprocity for attacker detection without any modification to legacy CSI feedback in which CSI forgery induces a mismatching of downlink and uplink angular spectra at the AP. We implement and evaluate USE Attack and AngleSec in a software defined radio platform WARPv3. Extensive experiments manifest that USE Attack significantly improves the overall eaves-dropping quality compared with state-of-the-art counterparts and AngleSec is able to detect CSI forgery attackers almost for sure.

Owing to great potential in smart home and human-computer interactive applications, WiFi indoor localization has attracted extensive attentions in the past several years. The state-of-the-art systems have successfully achieved decimeter-level accuracies. However, the high accuracy is acquired at the cost of dense access point (AP) deployment, employing large size of frequency bandwidths or special-purpose radar signals which are not compatible with existing WiFi protocol, limiting their practical deployments. This paper presents the design and implementation of AWL, an accurate indoor localization system that enables a single WiFi AP to achieve decimeter-level accuracy with only one channel hopping. The key enabler of the system is we novelly employ channel hopping to create virtual antennas, without the need of adding more antennas or physically move the antennas' positions for a larger antenna array. We successfully utilize the widely known "bad" spatial aliasing to improve the AoA estimation accuracy. A novel multipath suppression scheme is also proposed to combat the severe multipath issue indoors. We build a prototype of AWL on WARP software-defined radio platform. Comprehensive experiments manifest that AWL achieves a median localization accuracy of 38 cm in a rich multipath indoor environment with only a single AP equipped with 6 antennas. In a small scale area, AWL is able to accurately track a moving device's trajectory, enabling applications such as writing/drawing in the air.

Large-scale MU-MIMO is a promising technology to scale network capacity and the capacity gain grows linearly with the numbers of antennas and users in theory. However, its practical deployment faces three critical challenges in the state-of-the-art WLANs: i) the demand of a large number of expensive RF chains; ii) the linear growth of feedback overheads with the number of antennas; iii) the lack of scalable user selection scheme for a large user population. In this paper, we design BUSH, a large-scale MU-MIMO prototype that performs scalable beam user selection with hybrid beamforming for phased-array antennas in legacy WLANs. The architecture of BUSH consists of three components. Firstly, a low complexity algorithm assigns each pair of RF chain and analog beam to the users to effectively reduce channel correlation and cross-talk interference without instantaneous CSI feedbacks. Secondly, as a prerequisite of user selection, BUSH presents a low-overhead probing scheme in multi-carrier WLANs, and designs a highly accurate blind Power Azimuth Spectrum (PAS) estimation algorithm using a single RF chain. Thirdly, the phased-array antennas use analog beamforming to steer spatial beams toward each selected downlink user, and the finite number of RF chains use beamforming to further mitigate the interference among users. We implement BUSH on the WARPv3 boards and evaluate its performance in more than 30 indoor scenarios. The experimental results show that in terms of total throughput BUSH outperforms the legacy 802.11ac by 2.08×, and an alternative benchmark system by 1.22× on average.

Multiview video is essential for various mobile three-dimensional (3D) and immersive applications that can capture scenes from multiple angles for better user experience. However, robust transmission of multiview video is very challenging in wireless networks due to high bandwidth requirement and time-varying channel quality. Though the up-to-date 802.11 system enables spatial multiplexing MIMO to enhance transmission capacity, it is still agnostic to 3D source coding structure in the transmission. In this paper, we study the optimal resource allocation problem in MIMO systems that deliver 3D content with multiview video coding. The basic idea is to exploit the channel diversity of multiple antennas and the source coding characteristics so as to achieve unequal error protection against channel errors. To achieve this goal, we develop a nonlinear mixed integer programming framework to perform antenna selection and power allocation, and propose low-complexity algorithms to assign these resources. We implement a proof-of-concept system, namely MuVi, on the software-defined-radio platform, WARP, to evaluate the proposed algorithms. MuVi is the practical system to tackle 3D multiview streaming in the latest Wi-Fi networks such as IEEE 802.11ac under realistic channel conditions. Extensive experimental results demonstrate that the peak signal-to-noise-ratio of MuVi significantly outperforms that of the conventional power allocation scheme in a variety of indoor environments.

Multi-view video streaming is essential for various mobile 3D and immersive applications that can capture the same scene from multiple angles. However, the large traffic volume of multi-view streaming will drain the battery power quickly. This paper studies the power efficient delivery of 3D content with multi-view video coding (MVC) in the emerging 802.11-like MIMO wireless systems, and the purpose is to minimize the power consumption with the video quality guarantee. We propose an efficient algorithm to perform antenna assignment and transmission power allocation, by exploiting both the source coding characteristics of MVC and channel diversity of multiple antennas. A proof-of-concept system, namely PoM, is designed on the software radio platform and is evaluated in realistic indoor environments. To the best of our knowledge, this is the first practical system for energy efficient multi-view video streaming. Experimental results show that PoM can significantly save energy in the transmission by 12% ~ 65% on average when the required PSNR decreases from 45dB to 35dB.