INFOCOM 2022 论文列表

Communication scheduling is crucial to improve the efficiency of training large deep learning models with data parallelism, in which the transmission order of layer-wise deep neural network (DNN) tensors is determined for a better computation-communication overlap. Prior approaches adopt tensor partitioning to enhance the priority scheduling with finer granularity. However, a startup time slot inserted before each tensor partition will neutralize this scheduling gain. Tuning the optimal partition size is difficult and the application-layer solutions cannot eliminate the partitioning overhead. In this paper, we propose Mercury, a simple transport layer scheduler that does not partition the tensors, but moves the priority scheduling to the transport layer at the packet granularity. The packets with the highest priority in the Mercury buffer will be transmitted first. Mercury achieves the near-optimal overlapping between communication and computation. It leverages immediate aggregation at the transport layer to enable the coincident gradient push and parameter pull. We implement Mercury in MXNet and conduct comprehensive experiments on five DNN models in an 8-node cluster with 10Gbps Ethernet. Experimental results show that Mercury can achieve about 1.18 ~ 2.18 × speedup over vanilla MXNet, and 1.08 ~ 2.04× speedup over the state-of-the-art tensor partitioning solution.

RFID shows great potentials to build useful sensing applications. However, current RFID sensing can obtain mainly a single-dimensional sensing measurement from each reader-to-tag query, such as phase, RSS, etc. This is sufficient to fulfill the designs that are bounded to the tag’s own movement, e.g., the localization of tags. However, it imposes inevitable uncertainty to many sensing tasks relying on the features extracted from the RFID signals, which limits the fidelity of RFID sensing fundamentally and prevents its broader usage in more sophisticated sensing scenarios. This paper presents RF-Wise to push the limit of the RFID-based sensing, motivated by an insightful observation to customize RFID signals. RF-Wise can enrich the existing single-dimensional feature measure to a channel state information (CSI)-like measure with up to 150 dimensional samples across different frequencies concurrently. More importantly, RF-Wise is a software solution atop the standard EPC Gen2 protocol without using any extra hardware, requires only one tag for sensing and works within the ISM band. RF-Wise, so far as we know, is the first system of such a kind. Extensive experiments show that RF-Wise does not impact underlying RFID communications, while by using the features extracted by RF-Wise, applications’ sensing performance can be improved remarkably. The source codes of RF-Wise are available at https://cui-zhao.github.io/RF-WISE/.

Internet card (IC) as a new business model emerges, which penetrates rapidly and holds the potential to foster a great business market. However, the understanding of IC user portraits is insufficient, which is the building block to boost the IC business. In this paper, we take the lead to bridge the gap by studying one large-scale dataset collected from a provincial network operator of China, which contains about 4 million IC users and 22 million traditional card (TC) users. Particularly, we first conduct a systematical analysis on usage data by investigating the difference of two types of users, examining the impact of user properties, and characterizing the spatio-temporal networking patterns. After that, we shed light on one specific business case of churn prediction by devising an IC user Churn Prediction model, named ICCP, which consists of a feature extraction component and a learning architecture design. In ICCP, both the static portrait features and temporal sequential features are extracted, and one principal component analysis block and the embedding/transformer layers are devised to learn the respective information of two types of features, which are collectively fed into the classification multilayer perceptron layer for prediction. Extensive experiments corroborate the efficacy of ICCP.

Reconfigurable intelligent surfaces (RISs) have been proposed to increase coverage in millimeter-wave networks by providing an indirect path from transmitter to receiver when the line-of-sight (LoS) path is blocked. In this paper, the problem of optimizing the locations and orientations of multiple RISs is considered for the first time. An iterative coverage expansion algorithm based on gradient descent is proposed for indoor scenarios where obstacles are present. The goal of this algorithm is to maximize coverage within the shadowed regions where there is no LoS path to the access point. The algorithm is guaranteed to converge to a local coverage maximum and is combined with an intelligent initialization procedure to improve the performance and efficiency of the approach. Numerical results demonstrate that, in dense obstacle environments, the proposed algorithm doubles coverage compared to a solution without RISs and provides about a 10% coverage increase compared to a brute force sequential RIS placement approach.

Recently, there have been renewed interests in applying machine learning (ML) techniques to wireless systems. Nevertheless, ML-based approaches often require a large amount of data in training, and prior ML-based MIMO symbol detectors usually adopt offline learning approaches, which are not applicable to real-time signal processing. This paper adopts echo state network (ESN), a prominent type of reservoir computing (RC), to the real-time symbol detection task in MIMO-OFDM systems. Two novel ESN training methods, namely recursive-least-square and generalized adaptive weighted recursive-least-square, are introduced to enhance the performance of ESN training. Furthermore, a decision feedback mechanism is adopted to improve training efficiency and BER performance. Simulation studies show that the proposed methods perform better than previous conventional and ML-based MIMO symbol detectors. Finally, the effectiveness of our RC-based approach is validated with a software-defined radio (SDR) transceiver and extensive field tests in various real-world scenarios. To the best of our knowledge, this is the first real-time SDR implementation for ML-based MIMO-OFDM symbol detectors. Our work strongly indicates that ML-based signal processing could be a promising and critical approach for future wireless networks.

Nowadays, the rapid development of self-driving technology and its fusion with the current vehicle electrification process has given rise to electric self-driving taxis (es-taxis). Foreseeably, es-taxis will become a major force that serves the massive urban mobility demands not far into the future. Though promising, it is still a fundamental unsolved problem of effectively deciding when and where a city-scale fleet of es-taxis should be charged, so that enough es-taxis will be available whenever and wherever ride requests are submitted. Furthermore, charging decisions are far from isolated, but tightly coupled with the order dispatch process that matches orders with es-taxis. Therefore, in this paper, we investigate the problem of joint order dispatch and charging in es-taxi systems, with the objective of maximizing the ride-hailing platform’s long-term cumulative profit. Technically, such problem is challenging in a myriad of aspects, such as long-term profit maximization, partial statistical information on future orders, etc. We address the various arising challenges by meticulously integrating a series of methods, including distributionally robust optimization, primal-dual transformation, and second order conic programming to yield far-sighted decisions. Finally, we validate the effectiveness of our proposed methods though extensive experiments based on two large-scale real-world online ride-hailing order datasets.

This paper studies the problem of 6D pose estimation, which is practically important in various application scenarios such as robotic-based object grasping, obstacle avoidance in autonomous driving scene, and object integration in mixed reality. However, existing methods suffer from at least one of the five major limitations: dependence on object identification, complex deployment, difficulty in data collection, low accuracy, and incomplete estimation. To overcome the above limitations, this paper proposes an RC6D system, which is the first to estimate 6D poses by fusing RFID and Computer Vision (CV) data with multi-modal deep learning techniques. In RC6D, we first detect 2D keypoints through a deep learning approach. We then propose a novel RFID-CV fusion neural network to predict the depth of the scene, and use the estimated depth information to expand the 2D keypoints to 3D keypoints. Finally, we model the coordinate correspondences between the detected 2D-3D keypoints, which is applied to estimate the 6D pose of the target object. When implementing RC6D, we mainly address the following three technical challenges. (i) To predict 6D poses without using the CAD model, we propose a network architecture for monocular depth estimation. (ii) To train the neural network for 6D pose estimation without time-consuming 6D labeling, we use an unsupervised learning algorithm based on 2D-3D point pair matching. (iii) To detect the subject of the object without identification, we leverage optical flow to restrict the object and RFID to directly obtain its information. The experimental results show that the localization error of RC6D is less than 10 cm with a probability higher than 90.64% and its orientation estimation error is less than 10° with a probability higher than 79.63%. Hence, the proposed RC6D system performs much better than the state-of-the-art related solutions.

ABR algorithms dynamically select the bitrate of chunks based on the network capacity. To estimate the network capacity, most ABR algorithms use throughput prediction while recent works start to leverage delivery time prediction. We in this paper examine all components of the predictor for ABR algorithms, i.e., input features, mapping function and output target. We build an automated video streaming measurement platform, and collect extensive dataset under various network environments, containing 2500+ video sessions. Through analysis, we find that most of previous works failed to achieve accurate prediction due to ignoring how application behavior influences application throughput, e.g., the strong correlation between chunk size and throughput. Then we identify underlying factors affecting this correlation, and consider them as features for more accurate prediction. Moreover, we show that throughput is a better target for data-driven predictors than delivery time in terms of prediction error, due to the long tail distribution of delivery time. Based on those above, we propose a decision-tree-based throughput predictor, named Lumos, which acts as a plug-in for ABR algorithms. Extensive experiments in real-world Internet demonstrate that Lumos achieves high prediction accuracy and improves the QoE of ABR algorithms when integrated into them.

With the development of smart indoor environments, user authentication becomes an essential mechanism to support various secure accesses. Although recent studies have shown initial success on authenticating users with human activities or gestures using WiFi, they rely on predefined body gestures and perform poorly when meeting undefined body gestures. This work aims to enable WiFi-based user authentication with undefined body gestures rather than only predefined body gestures, i.e., realizing a gesture-independent user authentication. In this paper, we first explore physiological characteristics underlying body gestures, and find that statistical distributions under WiFi signals induced by body gestures can exhibit invariant individual uniqueness unrelated to specific body gestures. Inspired by this observation, we propose a user authentication system, which utilizes WiFi signals to identify individuals in a gesture-independent manner. Specifically, we design an adversarial learning-based model, which suppresses specific gesture characteristics, and extracts invariant individual uniqueness unrelated to specific body gestures, to authenticate users in a gesture-independent manner. Extensive experiments in indoor environments show that the proposed system is feasible and effective in gesture-independent user authentication.

Mobile Crowdsensing (MCS) with smart devices has become an appealing paradigm for urban sensing. With the development of 5G-and-beyond technologies, unmanned aerial vehicles (UAVs) become possible for real-time applications, including wireless coverage, search and even disaster response. In this paper, we consider to use a group of UAVs as aerial base stations (BSs) to move around and collect data from multiple MCS users, forming a UAV crowdsensing campaign (UCS). Our goal is to maximize the collected data, geographical coverage whiling minimizing the age-of-information (AoI) of all mobile users simultaneously, with efficient use of constrained energy reserve. We propose a model-based deep reinforcement learning (DRL) framework called "GCRL-min(AoI)", which mainly consists of a novel model-based Monte Carlo tree search (MCTS) structure based on state-of-the-art approach MCTS (AlphaZero). We further improve it by adding a spatial UAV-user correlation extraction mechanism by a relational graph convolutional network (RGCN), and a next state prediction module to reduce the dependance of experience data. Extensive results and trajectory visualization on three real human mobility datasets in Purdue University, KAIST and NCSU show that GCRL-min(AoI) consistently outperforms five baselines, when varying different number of UAVs and maximum coupling loss in terms of four metrics.

LoRa is widely deploying in aquatic environments to support various Internet of Things applications. However, floating LoRa networks suffer from serious performance degradation due to the polarization loss caused by the swaying antenna. Existing methods that only control the transmission starting from the aligned attitude have limited improvement due to the ignorance of aligned period length. In this paper, we propose PolarScheduler, a dynamic transmission control method for floating LoRa networks. PolarScheduler actively controls transmission configurations to match polarization aligned periods. We propose a V-zone model to capture diverse aligned periods under different configurations. We also design a low-cost model establishment method and an efficient optimal configuration searching algorithm to make full use of aligned periods. We implement PolarScheduler on commercial LoRa platforms and evaluate its performance in a deployed network. Extensive experiments show that PolarScheduler can improve the packet delivery rate and throughput by up to 20.0% and 15.7%, compared to the state-of-the-art method.

Message Queuing Telemetry Transport (MQTT) is a popular communication protocol used to interconnect devices with considerable network restraints, such as those found in Internet of Things (IoT). MQTT directly impacts a large number of devices, but the software security of its server ("broker") implementations is not well studied. In this paper, we design, implement, and evaluate a novel fuzz testing model for MQTT. The fuzzer combines aspects of mutation guided fuzzing and generation guided fuzzing to rigorously exhaust the MQTT protocol and identify vulnerabilities in servers. We introduce Markov chains for mutation guided fuzzing and generation guided fuzzing that model the fuzzing engine according to a finite Bernoulli process. We implement "response feedback", a novel technique which monitors network and console activity to learn which inputs trigger new responses from the broker. In total, we found 7 major vulnerabilities across 9 different MQTT implementations, including 6 zero-day vulnerabilities and 2 CVEs. We show that when fuzzing these popular MQTT targets, our fuzzer compares favorably with other state-of-the-art fuzzing frameworks, such as BooFuzz and AFLNet.

RFID technologies have been widely used for item-level object monitoring and tracking in industrial applications. In this paper, we study the problem of range detection in a commodity RFID system, which aims to quickly figure out whether there are any target tags that hold specific data between a lower and upper boundary. This is important to help users pinpoint tagged objects of interest (if any) and give an early warning for reducing the potential risk, e.g., temperature monitoring for fire safety. We propose a time-efficient protocol called encoding range query (EnRQ). The basic idea is to use a sparse vector to separate target tags from the others with a few select commands. The sparse vector is specifically designed by encoding the tag’s data based on notational systems. We implement EnRQ in commodity RFID systems with no need for any hardware modifications. Extensive experiments show that EnRQ can improve the time efficiency by more than 40% on average, compared with the state-of-the-art.

Given the power efficiency and Tbps throughput of packet processing, several works are proposed to offload the decision tree (DT) to programmable switches, i.e., in-network intelligence. Though the DT is suitable for the switches’ match-action paradigm, it has several limitations. E.g., its range match rules may not be supported well due to the hardware diversity; and its implementation also consumes lots of switch resources (e.g., stages and memory). Moreover, as learning algorithms (particularly deep learning) have shown their superior performance, some more complicated learning models are emerging for networking. However, their high computational complexity and large storage requirement are cause challenges in the deployment on switches. Therefore, we propose Mousika, an in-network intelligence framework that addresses these drawbacks successfully. First, we modify the DT to the Binary Decision Tree (BDT). Compared with the DT, our BDT supports faster training, generates fewer rules, and satisfies switch constraints better. Second, we introduce the teacher-student knowledge distillation in Mousika, which enables the general translation from other learning models to the BDT. Through the translation, we can not only utilize the super learning capabilities of complicated models, but also avoid the computation/memory constraints when deploying them on switches directly for line-speed processing.

Federated Learning (FL) is susceptible to gradient leakage attacks, as recent studies show the feasibility of obtaining private training data on clients from publicly shared gradients. Existing work solves this problem by incorporating a series of privacy protection mechanisms, such as homomorphic encryption and local differential privacy to prevent data leakage. However, these solutions either incur significant communication and computation costs, or significant training accuracy loss. In this paper, we show that the sensitivity of gradient changes w.r.t. training data is an essential measure of information leakage risk. Based on this observation, we present a novel defense, whose intuition is perturbing gradients to match information leakage risk such that the defense overhead is lightweight while privacy protection is adequate. Our another key observation is that global correlations of gradients could compensate for this perturbation. Based on such compensation, training can achieve guaranteed accuracy. We conduct experiments on MNIST, Fashion-MNIST and CIFAR-10 for defending against two gradient leakage attacks. Without sacrificing accuracy, the results demonstrate that our lightweight defense can decrease the PSNR and SSIM between the reconstructed images and raw images by up to more than 60% for both two attacks, compared with baseline defensive methods.

Recent years have witnessed tremendous growth of video streaming applications. To describe users’ expectations of videos, QoE was proposed, which is critical for content providers. Current video delivery systems optimize QoE with ABR algorithms. However, ABR is usually designed for an abstract "average user" without considering that QoE varies with users. In this paper, to investigate the difference in user preferences, we conduct a user study with 90 subjects and find that the average user can not represent all users. This observation inspires us to propose Ruyi, a video streaming system that incorporates preference awareness into the QoE model and the ABR algorithm. Ruyi profiles QoE preference of users and introduces preference-aware weights over different quality metrics into the QoE model. Based on this QoE model, Ruyi’s ABR is designed to directly predict the influence on metrics after taking different actions. With these predicted metrics, Ruyi chooses the bitrate that maximizes user-specific QoE once the preference is given. Consequently, Ruyi is scalable to different user preferences without re-training the learned models for each user. Simulation results show that Ruyi increases QoE for all users with up to 65.22% improvement. Testbed experimental results show that Ruyi has the highest ratings from subjects.

Voice has become a fundamental method for human-computer interactions and person identification these days. Benefit from the rapid development of deep learning, speaker recognition exploiting voice biometrics has achieved great success in various applications. However, the shadow of adversarial example attacks on deep neural network-based speaker recognition recently raised extensive public concerns and enormous research interests. Although existing studies propose to generate adversarial examples by iterative optimization to deceive speaker recognition, these methods require multiple iterations to construct specific perturbations for a single voice, which is input-specific, time-consuming, and non-transferable, hindering the deployment and application for non-professional adversaries. In this paper, we propose PhoneyTalker, an out-of-the-box toolkit for any adversary to generate universal and transferable adversarial examples with low complexity, releasing the requirement for professional background and specialized equipment. PhoneyTalker decomposes an arbitrary voice into phone combinations and generates phone-level perturbations using a generative model, which are reusable for voices from different persons with various texts. Experiments on mainstream speaker recognition systems with large-scale corpus show that PhoneyTalker outperforms state-of-the-art methods with overall attack success rates of 99.9% and 84.0% under white-box and black-box settings respectively.

Mobile health (mHealth) applications, benefiting from mobile computing, have emerged rapidly in recent years, and generated a large volume of mHealth data. However, these valuable data are dispersed across isolated devices or organizations, which hinders discovering insights underlying the aggregated data. Considering the online characteristics of mHealth tasks, there is an urgent need for online data acquisition. In this paper, we present the first online data Valuation And Pricing mechanism, namely VAP, to incentive users to contribute mHealth data for machine learning (ML) tasks in mHealth systems. Under the framework of Bayesian ML, we propose a new metric based on the concept of entropy, to evaluate data valuation during model training in an online manner. In proportion to the data valuation, we then determine payments as compensations for users to contribute their data. We formulate this pricing problem as a contextual multi-armed bandit with the goal of profit maximization and propose a new algorithm based on the characteristics of pricing. We also extend VAP to general ML models. Finally, we have evaluated VAP on two real-world mHealth data sets. Evaluation results show that VAP outperforms the state-of-the-art valuation and pricing mechanisms in terms of computational complexity and extracted profit.

Long tail latency of short flows (or messages) greatly affects user-facing applications in datacenters. Prior solutions to the problem introduce significant implementation complexities, such as global state monitoring, complex network control, or non-trivial switch modifications. While promising superior performance, they are hard to implement in practice.This paper presents Cloudburst, a simple, effective yet readily deployable solution achieving similar or even better results without introducing the above complexities. At its core, Cloudburst explores forward error correction (FEC) over multipath — it proactively spreads FEC-coded packets generated from messages over multipath in parallel, and recovers them with the first few arriving ones. As a result, Cloudburst is able to obliviously exploit underutilized paths, thus achieving low tail latency. We have implemented Cloudburst as a user-space library, and deployed it on a testbed with commodity switches. Our testbed and simulation experiments show the superior performance of Cloudburst. For example, Cloudburst achieves 63.69% and 60.06% reduction in 99th percentile message/flow completion time (FCT) compared to DCTCP and PIAS, respectively.