MobiCom 2020 Papers

Facial authentication mechanisms are gaining traction on smartphones because of their convenience and increasingly good performance of face recognition systems. However, mainstream systems use traditional 2D face recognition technologies, which are vulnerable to various spoofing attacks. Existing systems perform liveness detection via specialized hardware, such as infrared dot projectors and dedicated cameras. Although effective, such methods do not align well with the smartphone industry's desire to maximize screen space.

Social scientists, psychologists, and epidemiologists use empirical human interaction data to research human behaviour, social bonding, and disease spread. Historically, systems measuring interactions have been forced to choose between deployability and measurement fidelity---they operate only in instrumented spaces, under line-of-sight conditions, or provide coarse-grained proximity data. We introduce SociTrack, a platform for autonomous social interaction tracking via wireless distance measurements. Deployments require no supporting infrastructure and provide sub-second, decimeter-accurate ranging information over multiple days. The key insight that enables both deployability and fidelity in one system is to decouple node mobility and network management from range measurement, which results in a novel dual-radio architecture. SociTrack leverages an energy-efficient and scalable ranging protocol that is accurate to 14.8 cm (99th percentile) in complex indoor environments and allows our prototype to operate for 12 days on a 2000 mAh battery. Finally, to validate its deployability and efficacy, SociTrack is used by early childhood development researchers to capture caregiver-infant interactions.

Despite the soaring use of convolutional neural networks (CNNs) in mobile applications, uniformly sustaining high-performance inference on mobile has been elusive due to the excessive computational demands of modern CNNs and the increasing diversity of deployed devices. A popular alternative comprises offloading CNN processing to powerful cloud-based servers. Nevertheless, by relying on the cloud to produce outputs, emerging mission-critical and high-mobility applications, such as drone obstacle avoidance or interactive applications, can suffer from the dynamic connectivity conditions and the uncertain availability of the cloud. In this paper, we propose SPINN, a distributed inference system that employs synergistic device-cloud computation together with a progressive inference method to deliver fast and robust CNN inference across diverse settings. The proposed system introduces a novel scheduler that co-optimises the early-exit policy and the CNN splitting at run time, in order to adapt to dynamic conditions and meet user-defined service-level requirements. Quantitative evaluation illustrates that SPINN outperforms its state-of-the-art collaborative inference counterparts by up to 2× in achieved throughput under varying network conditions, reduces the server cost by up to 6.8× and improves accuracy by 20.7% under latency constraints, while providing robust operation under uncertain connectivity conditions and significant energy savings compared to cloud-centric execution.

The seismocardiogram (SCG) is a recording of a human heart's mechanical activity. It captures fine-grained cardiovascular events such as the opening and closing of heart valves and the contraction and relaxation of heart chambers. Today, SCG recordings are obtained by strapping an accelerometer at the apex of the heart to measure chest wall vibrations. These recordings can be used to diagnose and monitor various cardiovascular conditions including myocardial infarction (heart attack), coronary heart disease, and ischemia.

The Internet Para Todos program is working to provide sustainable mobile broadband to 100 M unconnected people in Latin America. In this paper we present our commercial deployment in thousands remote small communities and describe the unique experience of maintaining this infrastructure. We describe the challenges related to managing operations containing the cost in these extreme geographical conditions. We also analyze operational data to understand outage patterns and present typical operational issues in this unique remote community environment. Finally, we present an extension of the operations support system (OSS) leveraging advanced analytics and machine learning with the goal of optimizing network maintenance while reducing costs.

We propose Nephelai, a Compressive Sensing-based Cloud Radio Access Network (C-RAN), to reduce the uplink bit rate of the physical layer (PHY) between the gateways and the cloud server for multi-channel LPWANs. Recent research shows that single-channel LPWANs suffer from scalability issues. While multiple channels improve these issues, data transmission is expensive. Furthermore, recent research has shown that jointly decoding raw physical layers that are offloaded by LPWAN gateways in the cloud can improve the signal-to-noise ratio (SNR) of week radio signals. However, when it comes to multiple channels, this approach requires high bandwidth of network infrastructure to transport a large amount of PHY samples from gateways to the cloud server, which results in network congestion and high cost due to Internet data usage. In order to reduce the operation's bandwidth, we propose a novel LPWAN packet acquisition mechanism based on Compressive Sensing with a custom design dictionary that exploits the structure of LPWAN packets, reduces the bit rate of samples on each gateway, and demodulates PHY in the cloud with (joint) sparse approximation. Moreover, we propose an adaptive compression method that takes the Spreading Factor (SF) and SNR into account. Our empirical evaluation shows that up to 93.7% PHY samples can be reduced by Nephelai when SF = 9 and SNR is high without degradation in the packet reception rate (PRR). With four gateways, 1.7x PRR can be achieved with 87.5% PHY samples compressed, which can extend the battery lifetime of embedded IoT devices to 1.7.

THz communication has the potential to realize an order of magnitude increase in data rates due to the availability of wide THz-scale spectral bands. Unfortunately, establishing and managing highly directional beams in THz networks is challenging as links lack the "pseudo-omni" reception capability of lower bands and the product of AP-client beam resolution is high due to narrow beams of only a few degrees. In this paper, we present One-shot Path discovEry with a THz RAinbow (OPERA), a novel system that identifies dominant paths between the AP and all clients in order to efficiently steer directional beams. The key idea is to embed path direction into the inherent characteristics of signals traveling along each path. To do so, we exploit a single leaky wave antenna and create a THz Rainbow. A THz Rainbow transmission consists of distinct signals with unique spectral characteristics across the angular domain. Leveraging the spatial-spectral signatures in the THz Rainbow, all receivers can correlate the measured signal with the known transmission signatures to discover the sender's path directions in one-shot. Our experiments demonstrate that OPERA achieves average direction estimates within 2° of ground truth for LOS and reflected paths.

This paper aims to use modern earphones as a platform for acoustic augmented reality (AAR). We intend to play 3D audio-annotations in the user's ears as she moves and looks at AAR objects in the environment. While companies like Bose and Microsoft are beginning to release such capabilities, they are intended for outdoor environments. Our system aims to explore the challenges indoors, without requiring any infrastructure deployment. Our core idea is two-fold. (1) We jointly use the inertial sensors (IMUs) in earphones and smartphones to estimate a user's indoor location and gazing orientation. (2) We play 3D sounds in the earphones and exploit the human's responses to (re)calibrate errors in location and orientation. We believe this fusion of IMU and acoustics is novel, and could be an important step towards indoor AAR. Our system, Ear-AR, is tested on 7 volunteers invited to an AAR exhibition - like a museum - that we set up in our building's lobby and lab. Across 60 different test sessions, the volunteers browsed different subsets of 24 annotated objects as they walked around. Results show that Ear-AR plays the correct audio-annotations with good accuracy. The user-feedback is encouraging and points to further areas of research and applications.

The recent innovation of frequency-shifted (FS) backscatter allows for backscattering with commodity devices, which are inherently half-duplex. However, their reliance on oscillators for generating the frequency-shifting signal on the tag, forces them to incur the transient phase of the oscillator before steady-state operation. We show how the oscillator's transient phase can pose a fundamental limitation for battery-less tags, resulting in significantly low bandwidth efficiencies, thereby limiting their practical usage.

This paper presents the design, implementation and evaluation of In-N-Out, a software-hardware solution for far-field wireless power transfer. In-N-Out can continuously charge a medical implant residing in deep tissues at near-optimal beamforming power, even when the implant moves around inside the human body. To accomplish this, we exploit the unique energy ball pattern of distributed antenna array and devise a backscatter-assisted beamforming algorithm that can concentrate RF energy on a tiny spot surrounding the medical implant. Meanwhile, the power levels on other body parts stay in low level, reducing the risk of overheating. We proto-type In-N-Out on 21 software-defined radios and a printed circuit board (PCB). Extensive experiments demonstrate that In-N-Out achieves 0.37 mW average charging power inside a 10 cm-thick pork belly, which is sufficient to wirelessly power a range of commercial medical devices. Our head-to-head comparison with the state-of-the-art approach shows that In-N-Out achieves 5.4X-18.1X power gain when the implant is stationary, and 5.3X-7.4X power gain when the implant is in motion.

Federated learning was proposed with an intriguing vision of achieving collaborative machine learning among numerous clients without uploading their private data to a cloud server. However, the conventional framework requires each client to leverage the full model for learning, which can be prohibitively inefficient for large-scale learning tasks and resource-constrained mobile devices. Thus, we proposed a submodel framework, where clients download only the needed parts of the full model, namely, submodels, and then upload the submodel updates. Nevertheless, the "position" of a client's truly required submodel corresponds to its private data, while the disclosure of the true position to the cloud server during interactions inevitably breaks the tenet of federated learning. To integrate efficiency and privacy, we designed a secure federated submodel learning scheme coupled with a private set union protocol as a cornerstone. The secure scheme features the properties of randomized response, secure aggregation, and Bloom filter, and endows each client with customized plausible deniability (in terms of local differential privacy) against the position of its desired submodel, thereby protecting private data. We further instantiated the scheme with Alibaba's e-commerce recommendation, implemented a prototype system, and extensively evaluated over 30-day Taobao user data. Empirical results demonstrate the feasibility and scalability of the proposed scheme as well as its remarkable advantages over the conventional federated learning framework, from model accuracy and convergency, practical communication, computation, and storage overhead.

Instant delivery is an important urban service in recent years because of the increasing demand. An important issue for delivery platforms is to keep updating the status of couriers especially the real-time locations, which is challenging when they are in an indoor environment. We argue the previous indoor localization techniques cannot be applied in the instant delivery scenario because they require extra deployed infrastructures and extensive labor work. In this work, we perform the couriers' indoor localization transparently in a predictive manner without extra actions of couriers by existing data from the platform including order progress reports and couriers' trajectories. Specifically, we present TransLoc to predict couriers' indoor locations by addressing two challenges including uncertain reporting behaviors and uncertain indoor mobility behaviors. Our key idea lies in two insights (i) couriers' behaviors are consistent in indoor/outdoor environments; (ii) localization, as a spatial inference problem, could be converted to a temporal inference problem. We evaluate TransLoc on 565 couriers from an instant delivery company, which improves baselines by at most 72%, and achieves a competitive result compared to a label-extensive approach. As a case study, we apply TransLoc to optimize the order dispatching strategy, which reduces the delivery time by 24%.

We present GROOT, a mobile volumetric video streaming system that delivers three-dimensional data to mobile devices for a fully immersive virtual and augmented reality experience. The system design for streaming volumetric videos should be fundamentally different from conventional 2D video streaming systems. First, the amount of data required to deliver the 3D volume is considerably larger than conventional videos with frames of 2D images, even compared to high-resolution 2D or 360° videos. Second, the 3D data representation, which encodes the surface of objects within the volume, is a sparse and unorganized data structure with varying scales, whereas a conventional video is composed of a sequence of images with the fixed-size 2D grid structure. GROOT is a streaming framework with a novel data structure that enables not only real-time transmission and decoding on mobile devices but also continuous on-demand user view adaptation. Specifically, we modify the conventional octree to introduce the independence of leaf nodes with minimal memory overhead, which enables parallel decoding of highly irregular 3D data. We also developed a suite of techniques to compress color information and filter out 3D points outside of a user's view, which efficiently minimizes the data size and decoding cost. Our extensive evaluation shows that GROOT achieves more stable but faster frame rates compared to any previous method to stream and visualize volumetric videos on mobile devices.

Recent years have seen dramatic advances in low-power neural accelerators that aim to bring deep learning analytics to IoT devices; simultaneously, there have been considerable advances in the design of low-power radios to enable efficient compute offload from IoT devices to the cloud. Neither is a panacea --- deep learning models are often too large for low-power accelerators and bandwidth needs are often too high for low-power radios. While there has been considerable work on deep learning for smartphone-class devices, these methods do not work well for small battery-powered IoT devices that are considerably more resource-constrained.

Molecular communication has recently gained a lot of interest due to its potential to enable micro-implants to communicate by releasing molecules into the bloodstream. In this paper, we aim to explore the molecular communication channel through theoretical and empirical modeling in order to achieve a better understanding of its characteristics, which tend to be more complex in practice than traditional wireless and wired channels. Our study reveals two key new characteristics that have been overlooked by past work. Specifically, the molecular communication channel exhibits non-causal inter-symbol-interference and a long delay spread, that extends beyond the channel coherence time, which limit decoding performance. To address this, we design, μ-Link a molecular communication protocol and decoder that accounts for these new insights. We build a testbed to experimentally validate our findings and show that μ-Link can improve the achievable data rates with significantly lower bit error rates.

mm-Wave has emerged as an attractive high-speed wireless communication paradigm owing to the high available bandwidth at mm-wave frequencies. Full-Duplex has the potential to double the available capacity in the mm-wave bands by enabling simultaneous radio transmission and reception. While full-duplex has been extensively studied in sub-6 GHz bands, this paper exposes the unique challenges in porting this capability to mm-wave frequencies.

We present EagleEye, an AR-based system that identifies missing person (or people) in large, crowded urban spaces. Designing EagleEye involves critical technical challenges for both accuracy and latency. Firstly, despite recent advances in Deep Neural Network (DNN)-based face identification, we observe that state-of-the-art models fail to accurately identify Low-Resolution (LR) faces. Accordingly, we design a novel Identity Clarification Network to recover missing details in the LR faces, which enhances true positives by 78% with only 14% false positives. Furthermore, designing EagleEye involves unique challenges compared to recent continuous mobile vision systems in that it requires running a series of complex DNNs multiple times on a high-resolution image. To tackle the challenge, we develop Content-Adaptive Parallel Execution to optimize complex multi-DNN face identification pipeline execution latency using heterogeneous processors on mobile and cloud. Our results show that EagleEye achieves 9.07X faster latency compared to naive execution, with only 108 KBytes of data offloaded.

Conventional road signs convey very concise and static visual information to human drivers, and bear retroreflective coating for better visibility at night. This paper introduces RetroI2V - a novel infrastructure-to-vehicle (I2V) communication and networking system that renovates conventional road signs to convey additional and dynamic information to vehicles while keeping intact their original functionality. In particular, RetroI2V exploits the retroreflective coating of road signs and establishes visible light backscattering communication (VLBC), and further coordinates multiple concurrent VLBC sessions among road signs and approaching vehicles. RetroI2V features a suite of novel VLBC designs including late-polarization, complementary optical signaling and polarization-based differential reception which are crucial to avoid flickering and achieve long VLBC range, as well as a decentralized MAC protocol that make practical multiple access in highly mobile and transient I2V settings. Experimental results from our prototyped system show that RetroI2V supports up to 101 m communication range and efficient multiple access at scale.

IMS (IP Multimedia Subsystem) is an essential framework for providing 4G/5G multimedia services. It has been deployed worldwide to support two call services: VoLTE (Voice over LTE) and VoWi-Fi (Voice over Wi-Fi). VoWi-Fi enables telephony calls over the Wi-Fi network to complement VoLTE. In this work, we uncover that the VoWi-Fi signaling session can be hijacked to maliciously manipulate the IMS call operation. An adversary can easily make ghost calls to launch a stealthy call DoS (Denial of Service) attack against specific cellular users. Only phone numbers, but not any malware or network information, are required from the victims. This sophisticated attack harnesses a design defect of the IMS call state machine, but not simply flooding or a crash trigger. To stealthily detect attackable phones at run time, we exploit a vulnerability of the 4G network infrastructure, call information leakage, which we explore using machine learning. We validate these vulnerabilities in operational 4G networks of 4 top-tier carriers across Asia and North America countries with 7 phone brands. Our result shows that the call DoS attack can prevent the victims from receiving incoming calls up to 99.0% time without user awareness. We finally propose and evaluate recommended solutions.