INFOCOM 2019 论文列表

With more attention paid to user privacy and communication security, the volume of encrypted traffic rises sharply, which brings a huge challenge to traditional rule-based traffic classification methods. Combining machine learning algorithms and manual-design features has become the mainstream methods to solve this problem. However, these features depend on professional experience heavily, which needs lots of human effort. And these methods divide the encrypted traffic classification problem into piece-wise sub-problems, which could not guarantee the optimal solution. In this paper, we apply the recurrent neural network to the encrypted traffic classification problem and propose the Flow Sequence Network (FS-Net). The FS-Net is an end-to-end classification model that learns representative features from the raw flows, and then classifies them in a unified framework. Moreover, we adopt a multi-layer encoder-decoder structure which can mine the potential sequential characteristics of flows deeply, and import the reconstruction mechanism which can enhance the effectiveness of features. Our comprehensive experiments on the real-world dataset covering 18 applications indicate that FS-Net achieves an excellent performance (99.14% TPR, 0.05% FPR and 0.9906 FTF) and outperforms the state-of-the-art methods.

Content providers (CPs) are keen to cache their popular contents in small-cell base stations (SBSs) provided by mobile network operators (MNOs). In fact, they can serve the requests of their subscribers with low latency, thereby increasing user satisfaction. Employing advanced video encoding techniques, such as scalable video coding (SVC), improves the utilization of wireless resources and the network infrastructure. However, the cache trading policies for SVC videos in multi-provider networks have not been studied yet. In this article, we design a commercial trading system in which multiple CPs, each owning SVC videos, compete over renting the cache in multiple SBSs provided by an MNO. We model cache trading between the MNO and CPs as a social welfare maximization problem, whose objective is to maximize the trading profit while achieving the economic properties of rationality, balanced budget, and truthfulness. Since optimal allocation of random-size caches to multiple CPs is NP-hard, we devise an iterative trading mechanism based on double auction called DOCAT, wherein the cache of SBSs is segmented and traded in multiple rounds. In each round of the auction, the MNO and CPs price the cache segments based on their profit, then submit their asking and buying bids, respectively. Next, a many-to-one matching algorithm is run to efficiently find perfect matches between the cache segments and winning CPs. Numerical results based on a real video dataset show that DOCAT increases the social welfare of the system while satisfying the desired economic properties.

This paper presents a novel RF local positioning system, iLPS, specifically designed for challenging indoor non-lineof-sight (NLOS) scenarios and/or urban canyons where global positioning systems (GPS) fail to reliably operate. iLPS enables decimeter-level localization of numerous tags concurrently with wireless communication using frequency-shifting active reflector anchors and orthogonal frequency division multiple access (OFDMA) waveforms. OFDMA signals are devised with carefully assigned subcarriers so that each tag can estimate the time-difference-of-arrival (TDoA) by analyzing the channel impulse response (CIR) from the main and reflector anchors without interfering each other. The proposed active reflection scheme efficiently eliminates the stringent time synchronization requirement while providing the diversity gain for enhanced information decoding reliability at the tag. Significant challenges from NLOS multipaths and the usage of relatively narrow bandwidth of 80MHz in the ISM-band are successfully mitigated by machine learning assisted algorithms. Field trials with the prototype system on Universal Software Radio Peripheral (USRP) confirm that iLPS can achieve decimeter-level accuracy localization and concurrent wireless communication over up to 100m distances.

Mobile payment has drawn considerable attention due to its convenience of paying via personal mobile devices at anytime and anywhere, and passcodes (i.e., PINs or patterns) are the first choice of most consumers to authorize the payment. This paper demonstrates a serious security breach and aims to raise the awareness of the public that the passcodes for authorizing transactions in mobile payments can be leaked by exploiting the embedded sensors in wearable devices (e.g., smartwatches). We present a passcode inference system, WristSpy, which examines to what extent the user's PIN/pattern during the mobile payment could be revealed from a single wrist-worn wearable device under different passcode input scenarios involving either two hands or a single hand. In particular, WristSpy has the capability to accurately reconstruct fine-grained hand movement trajectories and infer PINs/patterns when mobile and wearable devices are on two hands through building a Euclidean distance-based model and developing a training-free parallel PIN/pattern inference algorithm. When both devices are on the same single hand, a highly challenging case, WristSpy extracts multi-dimensional features by capturing the dynamics of minute hand vibrations and performs machine-learning based classification to identify PIN entries. Extensive experiments with 15 volunteers and 1600 passcode inputs demonstrate that an adversary is able to recover a user's PIN/pattern with up to 92% success rate within 5 tries under various input scenarios.

We study service scheduling problems in a slotted system in which jobs arrive according to a Bernoulli process and have to leave within two slots after arrival, service costs are quadratic in service rates, and there is also a linear waiting cost. We illustrate how these systems can be used to model CPU speed scaling, EV charging at a charging center, load scheduling in smart grids etc. We frame the problems as average cost Markov decision processes. While the studied system is a linear system with quadratic costs, it has state dependent control and non-standard cost function structure, rendering the optimization problem complex. We obtain explicit optimal policies in the case when all the jobs are of same size. In particular, we show that the optimal policy is linear or piece-wise linear in the system state, depending on the system parameters. Further, when the job sizes can take two distinct values, we provide an algorithm that yields the optimal policy. We illustrate different forms of these policies via numerical examples.

Given the increasingly serious air pollution problem, air quality index (AQI) monitoring in urban areas has drawn considerable attention. This paper presents ImgSensingNet, a vision guided aerial-ground sensing system, for air quality monitoring and forecasting by the fusion of haze images taken by the unmanned-aerial-vehicle (UAV) and the AQI data collected by an on-ground wireless sensor network. Specifically, ImgSensingNet first leverages the computer vision technique to tell the AQI scale in different regions from the haze images, where haze-relevant features and a deep convolutional neural network (CNN) are designed for direct learning between haze images and corresponding AQI scale. Based on the learnt AQI scale, ImgSensingNet determines whether to wake up on-ground wireless sensors for small-scale AQI monitoring and inference, which can greatly reduce the energy consumption of the system. An entropy-based model is employed for accurate real-time AQI estimation at un-measured locations and future air quality distribution forecasting. We implement and evaluate ImgSensingNet on two university campuses since Feb. 2018, and has collected 17,630 photos and 2.6 millions of AQI data samples. Experimental results confirm that ImgSensingNet can achieve high estimation accuracy while greatly reduce the battery consumption, compared to other state-of-the-art AQI monitoring approaches.

In this paper a novel dynamic spectrum management scheme for 5G Non Orthogonal Multiple Access (NOMA) wireless networks is proposed, where users are offered the option to transmit via licensed and unlicensed bands. Users are enabled to determine the optimal allocation of their transmission power in each one of the bands, while the unlicensed band is treated as a Common Pool Resource (CPR) - being non-excludable and rivalrous - which may collapse due to over-exploitation. Towards providing a pragmatic modeling approach for decision making under a realistic setting of probabilistic uncertainty, while properly capturing user risk perceptions, we model the corresponding optimization problem under the principles of Prospect Theory, removing the common assumption that subjects are behaving as neutral utility maximizers, a concept that does not reflect user risk behavior peculiarities. The corresponding problem is formulated as a CPR game, while the existence and uniqueness of its Pure Nash Equilibrium point are proven, and a user centric distributed algorithm is devised that obtains the corresponding solution. Detailed evaluation results are presented, highlighting the operation and superiority of the proposed framework against conventional Expected Utility Theory based approaches, while providing useful insights about user optimal decisions under realistic behaviors.

Mobile crowd sensing (MCS) is a technique where sensing tasks are outsourced to a crowd of mobile users. Since most of sensing tasks are location-dependent, workers are required to embed their locations into sensing reports, which incurs location privacy vulnerabilities. Realizing that workers perceive their location privacy differently, in this work we construct an auction-based trading market, facilitating location privacy trading between workers and the platform. Each worker can decide how much location privacy to disclose to the platform based on its own location privacy leakage budget $\xi$. The higher $\xi$ is, the less secrecy its reported location preserves. As a result, it receives higher payment from the platform as a compensation to its privacy loss. Besides, our mechanism enables the platform to select a suitable set of winning workers to achieve desirable service accuracy. For this purpose, a heuristic algorithm is devised, with polynomial-time complexity and bounded optimality gap. As formally proved in this manuscript, our proposed mechanism guarantees a series of nice properties, including $\xi$-privacy, $(\alpha,\beta)$accuracy, and budget feasibility.

Many practical applications have observed knowledge evolution, i.e., continuous born of new knowledge, with its formation influenced by the structure of historical knowledge. This observation gives rise to evolving knowledge graphs whose structure temporally grows over time. However, both the modal characterization and the algorithmic implementation of evolving knowledge graphs remain unexplored. To this end, we propose EvolveKG, a framework that reveals cross-time knowledge interaction with desirable performance of storage and computation. The novelty of EvolveKG lies in Derivative Graph - a static weighted snapshot of evolution at a certain time. Particularly, each weight quantifies knowledge effectiveness with a temporarily decaying function of consistency and attenuation, two proposed factors depicting whether or not the effectiveness of a fact fades away with time. Thanks to the cross-time interaction, EvolveKG allows future knowledge prediction by virtue of the influence from the historical ones. Empirically tested under two real datasets, the superiority of EvolveKG is confirmed via its prediction accuracy.

Wireless Sensor-Actuator Network (WSAN) technology is gaining rapid adoption in process industries in recent years. A WSAN typically connects sensors, actuators, and controllers in industrial facilities, such as steel mills, oil refineries, chemical plants, and infrastructures implementing complex monitoring and control processes. IEEE 802.15.4 based WSANs operate at low-power and can be manufactured inexpensively, which make them ideal where battery lifetime and costs are important. Recent studies have shown that the selection of network parameters has a significant effect on the network performance. However, the current practice of parameter selection is largely based on experience and rules of thumb involving a coarse-grained analysis of expected network load and dynamics or measurements during a few field trials, resulting in non-optimal decisions in many cases. In this work, we develop the Parameter Selection and Adaptation FramEwork (P-SAFE) that optimally configures the network parameters based on the application Quality of Service (QoS) demand and adapts the configuration at runtime to consistently satisfy the dynamic requirements. We implement P-SAFE and evaluate it on three physical testbeds. Experimental results show our solution can significantly better meet the application QoS demand compared to the state of the art.

We study the problem of joint offloading decision and resource allocation for mobile cloud networks with a computing access point (CAP) and a remote cloud center. We consider the case where the task computing requirement is not fully known before their execution. We aim to jointly optimize the offloading decisions as well as the allocation of computation and communication resources, to minimize a weighted sum of the average cost and cost variation. The problem is formulated as a mixed-integer program. We propose an efficient algorithm, termed Task Offloading and Resource Allocation with Uncertain Computing (TORAUC), and show that it always converges to a Karush-Kuhn-Tucker (KKT) point of an alternate form of the original problem, which has its binary constraints removed but guarantees an offloading decision solution that is arbitrarily close to binary. We extend TORAUC to TORAUC-MP for the case of a multi-processor CAP. Through trace-based simulation, we study the performance of TORAUC and TORAUC-MP. We observe that TORAUC is nearly optimal, and both algorithms substantially outperform several alternatives.

Nowadays, the growing demand for the 3D human-computer interaction (HCI) has brought about a number of novel approaches, which achieve the HCI by tracking the motion of different devices, including the translation and the rotation. In this paper, we propose to use a spinning linearly polarized antenna to track the 3D motion of a specified object attached with the passive RFID tag array. Different from the fixed antenna-based solutions, which suffer from the unavoidable signal interferences at some specific positions/orientations, and only achieve the good performance in some feasible sensing conditions, our spinning antenna-based solution seeks to sufficiently suppress the ambient signal interferences and extracts the most distinctive features, by actively spinning the antenna to create the optimal sensing condition. Moreover, by leveraging the matching/mismatching property of the linearly polarized antenna, i.e., in comparison to the circularly polarized antenna, the phase variation around the matching direction is more stable, and the RSSI variation in the mismatching direction is more distinctive, we are able to find more distinctive features to estimate the position and the orientation. We build a model to investigate the RSSI and the phase variation of the RFID tag along with the spinning of the antenna, and further extend the model from a single RFID tag to an RFID tag array. Furthermore, we design corresponding solutions to extract the distinctive RSSI and phase values from the RF-signal variation. Our solution tracks the translation of the tag array based on the phase features, and the rotation of the tag array based on the RSSI variation. The experimental results show that our system can achieve an average error of 13. 6cm in the translation tracking, and an average error of 8.3° in the rotation tracking in the 3D space.

The last decade has witnessed a rising interest in Gossip protocols in distributed systems. In particular, as soon as there is a need to disseminate events, they become a key functional building block due to their scalability, robustness and fault tolerance under high churn. However, Gossip protocols are known to be bandwidth intensive. A huge amount of algorithms has been studied to limit the number of exchanged messages using different combinations of push/pull approaches. We are revisiting the state of the art by applying Random Linear Network Coding to further increase performance. In particular, the originality of our approach is to combine sparse-vector encoding to send our network-coding coefficients and Lamport timestamps to split messages in generations in order to provide an efficient gossiping. Our results demonstrate that we are able to drastically reduce bandwidth overhead and dissemination delay compared to the state of the art.

Sleep monitoring plays an important role in many medical applications, including SIDS prevention, care of patients with pressure ulcers, and assistance to patients with sleep apnea, where studies have shown that autonomous and continuous monitoring of sleep postures provides useful information for lowering health risk. Existing systems are designed based on electrocardiogram, cameras and pressure sensors, which are expensive to deploy, intrusive to privacy, or uncomfortable to use. This paper presents TagSheet, the first sleep monitoring system based on passive RFID tags, which provides a convenient, non-intrusive, and comfortable way of monitoring the sleeping postures. It does not require attaching any tag directly to a patient’s body. Tags are taped under a bed sheet. With a combination of hierarchical recognition, image processing and polynomial fitting, the proposed system identifies body postures based on the observed variation caused by the patient body to the backscattered signals from tags. The system does not require any personalized data training, making it plug-n-play in use. One additional advantage is that the system can also estimate the patient’s respiration rate. This is particularly helpful in assisting patients with sleep apnea. We have implemented a prototype system, and experiments show that the system performs posture identification with an accuracy up to 96.7% and in the meantime it measures the respiration rate with a small error of about 0.7 bpm (breath per minute).

Recent years have seen booming development and great success in interactive crowdsourced livecast (i.e., crowdcast). Different from traditional livecast services, crowdcast is featured with tremendous video contents at the broadcaster side, highly diverse viewer side content watching environments/preferences as well as viewers' personalized quality of experience (QoE) demands (e.g., individual preferences for streaming delays, channel switching latencies and bitrates). This imposes unprecedented key challenges on how to flexibly and cost-effectively accommodate the heterogeneous and personalized QoE demands for the mass of viewers. In this paper, we propose DeepCast, an edge-assisted crowdcast framework, which makes intelligent decisions at edges based on the massive amount of real-time information from the network and viewers to accommodate personalized QoE with minimized system cost. Given the excessive computation complexity in this context, we propose a data-driven deep reinforcement learning (DRL) based solution that can automatically learn the best suitable strategies for viewer scheduling and transcoding selection. To our best knowledge, DeepCast is the first edge-assisted framework that applies the advance of DRL to explicitly accommodate personalized QoE optimization for crowdcast services. We collect multiple real-world datasets and evaluate the performance of DeepCast using trace-driven experiments. The results demonstrate the superiority of our DeepCast framework and its DRL-based solution.

Many important functions in software defined networks can benefit from fine-grained traffic measurement at flow level. Because TCAM-based flow entries only provide aggregate traffic statistics, prior research has suggested to perform flow-level measurement in SRAM and balance the measurement load across the network through collaborative traffic measurement. The key problem of collaborative measurement is to provide a mechanism to distribute flows to switches such that each switch can identify its subset of flows to measure. We observe that the prior work has focused on optimizing flow distribution among switches, but overlooked their high space and per-packet processing overhead introduced to the data plane, which becomes a serious issue in large SDN systems. In this paper, we propose a new lightweight solution to the flow distribution problem. It follows the design principle of alleviating complexity of the data plane by minimizing the data-plane space and processing overhead. At the control plane, we formulate flow distribution as optimization problems under two scenarios that implement collaborative measurement by edge switches only and by edge/core switches together, respectively. Our extensive simulations demonstrate that, comparing with the best existing work, the proposed lightweight solution achieves a comparable performance in terms of load balancing, while drastically reducing both space overhead and per-packet processing overhead, making it more practical in real-world systems that are sensitive to the additional overhead introduced by flow distribution.

Distributed optimization has important applications in the practical implementation of machine learning and signal processing setup by providing means to allow interconnected network of processors to work towards the optimization of a global objective with intermittent communication. Existing works on distributed optimization predominantly assume all the processors storing related data to perform updates for the optimization task in each iteration. However, such optimization processes are typically executed at shared computing/data centers along with other concurrent tasks. Therefore, it is necessary to develop efficient distributed optimization methods that possess the flexibility to share the computing resources with other ongoing tasks. In this work, we propose a new first-order framework that allows for this flexibility through a probabilistic computing resource allocation strategy while guaranteeing the satisfactory performance of distributed optimization. Our results, both analytical and numerical, show that by controlling a flexibility parameter, our suite of algorithms (designed for various scenarios) can achieve the lower computation and communication costs of distributed optimization than their inflexible counterparts. This framework also enables the fair sharing of the common resources with other concurrent tasks being processed by the processing network.

Reverse auction-based incentive mechanisms have been commonly proposed to stimulate mobile users to participate in crowdsensing, where users submit bids to the platform to compete for tasks. Recent works pointed out that bid is a private information which can reveal sensitive information of users (e.g., location privacy), and proposed bid-preserving mechanisms with differential privacy against inference attack. However, all these mechanisms rely on a trusted platform, and would fail in bid protection completely when the platform is untrusted (e.g., honest-but-curious). In this paper, we focus on the bid protection problem in mobile crowdsensing with an untrusted platform, and propose a novel privacy-preserving incentive mechanism to protect users' true bids against the honest-but-curious platform while minimizing the social cost of winner selection. To this end, instead of uploading the true bid to the platform, a differentially private bid obfuscation function is designed with the exponential mechanism, which helps each user to obfuscate bids locally and submit obfuscated task-bid pairs to the platform. The winner selection problem with the obfuscated task-bid pairs is formulated as an integer linear programming problem and proved to be NP-hard. We consider the optimization problem at two different scenarios, and propose a solution based on Hungarian method for single measurement and a greedy solution for multiple measurements, respectively. The proposed incentive mechanism is proved to satisfy ε-differential privacy, individual rationality and γ-truthfulness. The extensive experiments on a real-world data set demonstrate the effectiveness of the proposed mechanism against the untrusted platform.

Recently, a new metric, called Age of Information (AoI), has become popular to quantify the freshness of information collected at network edge. AoI research is still in its infancy and most prior efforts assume overly simplified models in their investigation. In this paper, we consider a more general model for AoI research that is closer to what happens in the real world. Specifically, we consider general and heterogeneous sampling behaviors among source nodes, varying sample size, and multiple data transmission units in each time slot. Under this much general setting, we develop new theoretical results (in terms of properties and performance bounds) and a new near-optimal low-complexity scheduling algorithm. Our results make a major advance of AoI research in terms of more realistic models.