INFOCOM 2020 论文列表

Increasingly rich data sets and complicated models make distributed machine learning more and more important. However, the cost of extensive and frequent parameter synchronizations can easily diminish the benefits of distributed training across multiple machines. In this paper, we present Geryon, a network-level flow scheduling scheme to accelerate distributed Convolutional Neural Network (CNN) training. Geryon leverages multiple flows with different priorities to transfer parameters of different urgency levels, which can naturally coordinate multiple parameter servers and prioritize the urgent parameter transfers in the entire network fabric. Geryon requires no modification in CNN models and does not affect the training accuracy. Based on the experimental results of four representative CNN models on a testbed of 8 GPU servers, Geryon achieves up to 95.7% scaling efficiency even with 10GbE bandwidth. In contrast, for most models, the scaling efficiency of vanilla TensorFlow is no more than 37% and that of TensorFlow with parameter partition and slicing is around 80%. In terms of training throughput, Geryon enhanced with parameter partition and slicing achieves up to 4.37x speedup, where the flow scheduling algorithm itself achieves up to 1.2x speedup over parameter partition and slicing.

Passive RFID technology is widely used in user authentication and access control. We propose RF-Rhythm, a secure and usable two-factor RFID authentication system with strong resilience to lost/stolen/cloned RFID cards. In RF-Rhythm, each legitimate user performs a sequence of taps on his/her RFID card according to a self-chosen secret melody. Such rhythmic taps can induce phase changes in the backscattered signals, which the RFID reader can detect to recover the user’s tapping rhythm. In addition to verifying the RFID card’s identification information as usual, the backend server compares the extracted tapping rhythm with what it acquires in the user enrollment phase. The user passes authentication checks if and only if both verifications succeed. We also propose a novel phase-hopping protocol in which the RFID reader emits Continuous Wave (CW) with random phases for extracting the user’s secret tapping rhythm. Our protocol can prevent a capable adversary from extracting and then replaying a legitimate tapping rhythm from sniffed RFID signals. Comprehensive user experiments confirm the high security and usability of RF-Rhythm with false-positive and false-negative rates close to zero.

Since under-allocating computation resource (e.g., CPU cores) causes suboptimal JCTs of data-parallel jobs, users are inclined to request excessive computation resource to decrease JCTs. However, over-allocating computation resource for data-parallel jobs incurs considerable system overheads (e.g., network communication and disk I/O overhead), which prolong the job completion time. In this paper, we propose ReLoca towards the optimal allocation of computation resource with the objective of minimizing the job completion time. ReLoca employs a deep neural network to guide the allocation of computation resource, by learning the impact of the operations in data-parallel jobs on the system overhead and computation time. Since training samples are time-consuming to collect, we develop an adaptive sampling method to preferably collect high-quality samples and thus overcome the issue of data scarcity. We apply ReLoca to improve Spark and conduct real experiments with five typical applications in big data analytics. Results show that ReLoca significantly reduces the average job completion time. Compared with the state-of-the-art method, ReLoca has higher prediction accuracy, needs fewer training samples and decreases the sampling overhead. With the prediction by ReLoca, the JCT decreases by 29.85%.

To cope with the exploding mobile traffic in the fifth generation cellular network, the dense deployment of small cells and cognitive radios are two key technologies that significantly increase the network capacity and improve the spectrum utilization efficiency. Despite the desirable features, small cell cognitive radio networks (SCRNs) also face a higher risk of unauthorized spectrum access, which should not be overlooked. In this paper, we consider a passive monitoring system for SCRNs, which deploys sniffers for wireless traffic capture and network forensics, and study the optimal sniffer channel assignment (SCA) problem to maximize the monitoring performance. Unlike most existing SCA approaches that concentrate on user activity, we highlight the inherent error in wireless data capture (i.e. imperfect monitoring) due to the unreliable nature of wireless propagation, and propose an online-learning based algorithm called OSA (Online Sniffer-channel Assignment). OSA is a type of contextual combinatorial multi-armed bandit learning algorithm, which addresses key challenges in SCRN monitoring including the time- varying spectrum resource, imperfect monitoring, and uncertain network conditions. We theoretically prove that OSA has a sublinear learning regret bound and illustrate via simulations that OSA significantly outperforms benchmark solutions.

Recent years have seen a rapidly increasing traffic demand for HTTP-based high-quality live video streaming. The surging traffic demand, as well as the real-time property of live videos, make it challenging for content delivery networks (CDNs) to guarantee the Quality-of-Experiences (QoE) of viewers. The initial video segment (IVS) of live streaming plays an important role in the QoE of live viewers, particularly when users require fast join time and smooth view experience. State-of-the-art research on this regard estimates network throughput for each viewer and thus may incur a large overhead that offsets the benefit. To tackle the problem, we propose Rldish, a scheme deployed at the edge CDN server, to dynamically select a suitable IVS for new live viewers based on Reinforcement Learning (RL). Rldish is transparent to both the client and the streaming server. It collects the real-time QoE observations from the edge without any client-side assistance, then uses these QoE observations as real-time rewards in RL. We deploy Rldish as a virtualized network function (VNF) in a real HTTP cache server, and evaluate its performance using streaming servers distributed over the world. Our experiments show that Rldish improves the state- of-the-art IVS selection scheme w.r.t. the average QoE of live viewers by up to 22%.

The multi-path transmission techniques enable multiple paths to maximize resource usage and increase throughput in transmission, which have been installed over mobile devices in recent years. For video streaming applications, compared to the single-path transmission, the multi-path techniques can establish multiple subflows simultaneously to extend the available bandwidth for streaming high-quality videos in mobile devices. Existing adaptive video streaming systems have difficulty in harnessing multi-path scheduling and balancing the tradeoff between the quality of experience (QoE) and quality of service (QoS) concerns. In this paper, we propose an actor-critic network based on Periodical Experience Replay for Multi-path video streaming (PERM). Specifically, PERM employs two actor modules and a critic module: the two actor modules respectively assign the path usage of each subflow and select bitrates for the next chunk of the video, while the critic module predicts the overall objectives. We conduct trace-driven emulation and real-world testbed experiment to examine the performance of PERM, and results show that PERM outperforms state-of-the-art multi-path and single path streaming systems, with an improvement of 10%- 15% on the QoE and QoS metrics.

This paper focuses on similarity caching systems, in which a user request for an object o that is not in the cache can be (partially) satisfied by a similar stored object o', at the cost of a loss of user utility. Similarity caching systems can be effectively employed in several application areas, like multimedia retrieval, recommender systems, genome study, and machine learning training/serving. However, despite their relevance, the behavior of such systems is far from being well understood. In this paper, we provide a first comprehensive analysis of similarity caching in the offline, adversarial, and stochastic settings. We show that similarity caching raises significant new challenges, for which we propose the first dynamic policies with some optimality guarantees. We evaluate the performance of our schemes under both synthetic and real request traces.

Orthogonal blinding based schemes for wireless physical layer security aim to achieve secure communication by injecting noise into channels orthogonal to the main channel and corrupting the eavesdropper’s signal reception. These methods, albeit practical, have been proven vulnerable against multiantenna eavesdroppers who can filter the message from the noise. The vulnerability is rooted in the fact that the main channel state remains static in spite of the noise injection, which allows an eavesdropper to estimate it promptly via known symbols and filter out the noise. Our proposed scheme leverages a reconfigurable antenna for Alice to rapidly change the channel state during transmission and a compressive sensing based algorithm for her to predict and cancel the changing effects for Bob. As a result, the communication between Alice and Bob remains clear, whereas randomized channel state prevents Eve from launching the knownplaintext attack. We formally analyze the security of the scheme against both single and multi-antenna eavesdroppers and identify its unique anti-eavesdropping properties due to the artificially created fast-changing channel. We conduct extensive simulations and real-world experiments to evaluate its performance. Empirical results show that our scheme can suppress Eve’s attack success rate to the level of random guessing, even if she knows all the symbols transmitted through other antenna modes.

In this paper we study a team orienteering problem, which is to find service paths for multiple vehicles in a network such that the profit sum of serving the nodes in the paths is maximized, subject to the cost budget of each vehicle. This problem has many potential applications in IoT and smart cities, such as dispatching energy-constrained mobile chargers to charge as many energy-critical sensors as possible to prolong the network lifetime. In this paper, we first formulate the team orienteering problem, where different vehicles are different types, each node can be served by multiple vehicles, and the profit of serving the node is a submodular function of the number of vehicles serving it. We then propose a novel (1 - (1/e)1/2+ε)approximation algorithm for the problem, where c is a given constant with 0 ≤ ε ≤ 1 and ε is the base of the natural logarithm. In particular, the approximation ratio is no less than 0.32 when ε = 0.5. In addition, for a special team orienteering problem with the same type of vehicles and the profits of serving a node once and multiple times being the same, we devise an improved approximation algorithm. Finally, we evaluate the proposed algorithms with simulation experiments, and the results of which are very promising. Precisely, the profit sums delivered by the proposed algorithms are approximately 12.5% to 17.5% higher than those by existing algorithms.

With the popularity of drones and driverless cars, vehicular crowdsensing (VCS) becomes increasingly widely-used by taking advantage of their high-precision sensors and durability in harsh environments. Since abrupt sensing tasks usually cannot be prepared beforehand, we need a generic control logic fit-for-use all tasks which are similar in nature, but different in their own settings like Point-of-Interest (PoI) distributions. The objectives include to simultaneously maximize the data collection amount, geographic fairness, and minimize the energy consumption of all vehicles for all tasks, which usually cannot be explicitly expressed in a closed-form equation, thus not tractable as an optimization problem. In this paper, we propose a deep reinforcement learning (DRL)-based centralized control, distributed execution framework for multi-task-oriented VCS, called "DRL-MTVCS". It includes an asynchronous architecture with spatiotemporal state information modeling, multi-task-oriented value estimates by adaptive normalization, and auxiliary vehicle action exploration by pixel control. We compare with three baselines, and results show that DRL-MTVCS outperforms all others in terms of energy efficiency when varying different numbers of tasks, vehicles, charging stations and sensing range.

LoRa has been shown as a promising platform for connecting large scale of Internet of Things (IoT) devices, by providing low-power long-range communication with a low data rate. LoRa has different transmission parameters (e.g., transmission power and spreading factor) to tradeoff noise resilience, transmission range and energy consumption for different environments. Thus, adjusting those parameters is essential for LoRa performance. Existing approaches are mainly threshold based and fail to achieve optimal energy efficiency. We propose DyLoRa, a dynamic LoRa transmission control system to improve energy efficiency. The high level idea of DyLoRa is to adjust parameters to different environments. The main challenge is that LoRa has very limited data rate and sparse data, making it very time- and energy-consuming to obtain physical link properties. We show that symbol error rate is highly related to the Signal- Noise Ratio (SNR) and derive the model to characterize this. We further derive energy efficiency model based on the symbol error model. DyLoRa can adjust parameters for optimal energy efficiency from sparse LoRa packets. We implement DyLoRa based on LoRaWAN 1.0.2 with SX1276 LoRa node and SX1301 LoRa gateway and evaluate its performance in real networks. The evaluation results show that DyLoRa improves the energy efficiency by 41.2% on average compared with the state-of-the- art LoRaWAN ADR.

Network monitoring is vital in modern clouds and data center networks that need diverse traffic statistics ranging from flow size distributions to heavy hitters. To cope with increasing network rates and massive traffic volumes, sketch based approximate measurement has been extensively studied to trade the accuracy for memory and computation cost, which unfortunately, is sensitive to hash collisions.This paper presents a clustering-preserving sketch method to be resilient to hash collisions. We provide an equivalence analysis of the sketch in terms of the K-means clustering. Based on the analysis result, we cluster similar network flows to the same bucket array to reduce the estimation variance and use the average to obtain unbiased estimation. Testbed shows that the framework adapts to line rates and provides accurate query results. Real-world trace-driven simulations show that LSS remains stable performance under wide ranges of parameters and dramatically outperforms state-of-the-art sketching structures, with over 103to 105times reduction in relative errors for per-flow queries as the ratio of the number of buckets to the number of network flows reduces from 10% to 0.1%.

RFID applications for taking inventory and processing transactions in point-of-sale (POS) systems improve operational efficiency but are not designed to provide insights about customers' interactions with products. We bridge this gap by solving the proximity grouping problem to identify groups of RFID tags that stay in close proximity to each other over time. We design DeepTrack, a framework that uses deep learning to automatically track the group of items carried by a customer during her shopping journey. This unearths hidden purchase behaviors helping retailers make better business decisions and paves the way for innovative shopping experiences such as seamless checkout (`a la Amazon Go). DeepTrack employs a recurrent neural network (RNN) with the attention mechanism, to solve the proximity grouping problem in noisy settings without explicitly localizing tags. We tailor DeepTrack's design to track not only mobile groups (products carried by customers) but also flexibly identify stationary tag groups (products on shelves). The key attribute of DeepTrack is that it only uses readily available tag data from commercial off-the-shelf RFID equipment. Our experiments demonstrate that, with only two hours training data, DeepTrack achieves a grouping accuracy of 98.18% (99.79%) when tracking eight mobile (stationary) groups.

Human activity recognition (HAR) has become increasingly essential due to its potential to support a broad array of applications, e.g., elder care, and VR games. Recently, some pioneer WiFi-based HAR systems have been proposed due to its privacy-friendly and device-free characteristics. However, their crucial limitation lies in ignoring the inevitable impact of co-channel interference (CCI), which degrades the performance of these HAR systems significantly. To address this challenge, we propose PhaseAnti, a novel HAR system to exploit the CCI- independent phase component, NLPEV (Nonlinear Phase Error Variation), of Channel State Information (CSI) to cope with the impact of CCI. We provide a rigorous analysis of NLPEV data with respect to its stability and otherness. Validated by our experiments, this phase component across subcarriers is invariant to various CCI scenarios, while different for distinct motions. Based on the analysis, we use NLPEV data to perform HAR in CCI scenarios. Extensive experiments demonstrate that PhaseAnti can reliably recognize activity in various CCI scenarios. Specifically, PhaseAnti achieves a 95% recognition accuracy rate (RAR) on average, which improves up to 16% RAR in the presence of CCI. Moreover, the recognition speed is 9× faster than the state-of-the-art solution.

Protocol reverse engineering based on traffic traces infers the behavior of unknown network protocols by analyzing observable network messages. To perform correct deduction of message semantics or behavior analysis, accurate message type identification is an essential first step. However, identifying message types is particularly difficult for binary protocols, whose structural features are hidden in their densely packed data representation. We leverage the intrinsic structural features of binary protocols and propose an accurate method for discriminating message types.Our approach uses a similarity measure with continuous value range by comparing feature vectors where vector elements correspond to the fields in a message, rather than discrete byte values. This enables a better recognition of structural patterns, which remain hidden when only exact value matches are considered. We combine Hirschberg alignment with DBSCAN as cluster algorithm to yield a novel inference mechanism. By applying novel autoconfiguration schemes, we do not require manually configured parameters for the analysis of an unknown protocol, as required by earlier approaches.Results of our evaluations show that our approach has considerable advantages in message type identification result quality and also execution performance over previous approaches.

Given high-speed mobile Internet access today, audiences are expecting much higher video quality than before. Video service providers have deployed dynamic video bitrate adaptation services to fulfill such user demands. However, legacy video bitrate adaptation techniques are highly dependent on the estimation of dynamic bandwidth, and fail to integrate the video quality enhancement techniques, or consider the heterogeneous computing capabilities of client devices, leading to low quality of experience (QoE) for users. In this paper, we present a super-resolution based adaptive video streaming (SRAVS) framework, which applies a Reinforcement Learning (RL) model for integrating the video super-resolution (VSR) technique with the video streaming strategy. The VSR technique allows clients to download low bitrate video segments, reconstruct and enhance them to high-quality video segments while making the system less dependent on estimating dynamic bandwidth. The RL model investigates both the playback statistics and the distinguishing features related to the client-side computing capabilities. Trace-driven emulations over real-world videos and bandwidth traces verify that SRAVS can significantly improve the QoE for users compared to the state-of-the-art video streaming strategies with or without involving VSR techniques.

With the emergence of the information age, mobile data has become more random, heterogeneous and massive. Thanks to its many advantages, deep learning is increasingly applied in communication fields such as modulation recognition. However, recent studies show that the deep neural networks (DNN) is vulnerable to adversarial examples, where subtle perturbations deliberately designed by an attacker can fool a classifier model into making mistakes. From the perspective of an attacker, this study adds elaborate adversarial examples to the modulation signal, and explores the threats and impacts of adversarial attacks on the DNN-based modulation recognition in different environments. The results show that, regardless of a white-box or a black-box model, the adversarial attack can reduce the accuracy of the target model. Among them, the performance of the iterative attack is superior to the one-step attack in most scenarios. In order to ensure the invisibility of the attack (the waveform being consistent before and after the perturbations), an appropriate perturbation level is found without losing the attack effect. Finally, it is attested that the signal confidence level is inversely proportional to the attack success rate, and several groups of signals with high robustness are obtained.

The Bulk Synchronous Parallel (BSP) paradigm is gaining tremendous importance recently because of the pop-ularity of computations such as distributed machine learning and graph computation. In a typical BSP job, multiple workers concurrently conduct iterative computations, where frequent synchronization is required. Therefore, the workers should be scheduled simultaneously and their placement on different computing devices could significantly affect the performance. Simply retrofitting a traditional scheduling discipline will likely not yield the desired performance due to the unique characteristics of BSP jobs. In this work, we derive SPIN, a novel scheduling designed for BSP jobs with placement-sensitive execution to minimize the makespan of all jobs. We first prove the problem approximation hardness and then present how SPIN solves it with a rounding-based randomized approximation approach. Our analysis indicates SPIN achieves a good performance guarantee efficiently. Moreover, SPIN is robust against misestimation of job execution time by theoretically bounding its negative impact. We implement SPIN on a production-trace driven testbed with 40 GPUs. Our extensive experiments show that SPIN can reduce the job makespan and the average job completion time by up to 3× and 4.68×, respectively. Our approach also demonstrates better robustness to execution time misestimation compared with heuristic baselines.

Data-parallel training is widely used for scaling DNN training over large datasets, using the parameter server or all-reduce architecture. Communication scheduling has been promising to accelerate distributed DNN training, which aims to overlap communication with computation by scheduling the order of communication operations. We identify two limitations of previous communication scheduling work. First, layer-wise computation graph has been a common assumption, while modern machine learning frameworks (e.g., TensorFlow) use a sophisticated directed acyclic graph (DAG) representation as the execution model. Second, the default sizes of tensors are often less than optimal for transmission scheduling and bandwidth utilization. We propose PACE, a communication scheduler that preemptively schedules (potentially fused) all-reduce tensors based on the DAG of DNN training, guaranteeing maximal overlapping of communication with computation and high bandwidth utilization. The scheduler contains two integrated modules: given a DAG, we identify the best tensor-preemptive communication schedule that minimizes the training time; exploiting the optimal communication scheduling as an oracle, a dynamic programming approach is developed for generating a good DAG, which merges small communication tensors for efficient bandwidth utilization. Experiments in a GPU testbed show that PACE accelerates training with representative system configurations, achieving up to 36% speed-up compared with state-of-the-art solutions.