INFOCOM 2022 论文列表

Nowadays, with the emergence of software-defined networking, sketch-based network measurements have been widely used to balance the tradeoff between efficiency and reliability. The simplicity and generality of a sketch-based system allow it to track divergent performance metrics and deal with heterogeneous traffic characteristics. However, most of the existing proposals mainly consider priority-agnostic measurements, which introduce equal error probability to different classes of traffic. While network measurements are usually task-oriented, e.g., traffic engineering or intrusion detection, a system operator may be interested only in tracking specific types of traffic and expect various levels of tracking resolutions for different traffic classes. To achieve this goal, we propose MC-Sketch (Multi-Class Sketch), a priority-aware system that provides various classes of traffic with differential accuracy subject to the limited resources of a programmable switch. It privileges higher priority traffic in accessing the sketch over background traffic and naturally provides heterogeneous tracking resolutions. The experimental results and large-scale analysis show that MC-Sketch reduces the measurement errors of high priority flows by 56.92% without harming the overall accuracy much.

To bypass network censorship, Shadowsocks is often deployed on long-distance transnational networks; however, such proxy networks are usually plagued by high latency, high packet loss rate, and unstable bandwidth. Most existing tuning solutions rely on hand-tuned heuristics, which cannot work well in the volatile Shadowsocks networks due to the labor intensive and time-consuming properties. In this paper, we propose Auter, which automatically tunes multi-layer buffer parameters with reinforcement learning (RL) to improve the performance of Shadowsocks in long-distance networks. The key insight behind Auter is that different network environments require different sizes of buffers to achieve sufficiently good performance. Hence, Auter continuously learns a tuning policy from volatile network states and dynamically alter sizes of multi-buffers for high network performance. We prototype Auter and evaluate its effectiveness under various real networks. Our experimental results show that Auter can effectively improve network performance, up to 40.5% throughput increase in real networks. Besides, we demonstrate that Auter outperforms all the existing tuning schemes.

Physical-layer secret key generation has emerged as a promising solution for establishing cryptographic keys by leveraging reciprocal and time-varying wireless channels. However, existing approaches suffer from low key generation rates and vulnerabilities under various attacks in slowly varying environments. We propose a new physical-layer secret key generation approach with channel obfuscation, which improves the dynamic property of channel parameters based on random filtering and random antenna scheduling. Our approach makes one party obfuscate the channel to allow the legitimate party to obtain similar dynamic channel parameters, yet prevents a third party from inferring the obfuscation information. Our approach allows more random bits to be extracted from the obfuscated channel parameters by a joint design of the K-L transform and adaptive quantization. Results from a testbed implementation show that our approach, compared to the existing ones that we evaluate, performs the best in generating high entropy bits at a fast rate and is able to resist various attacks in slowly varying environments. Specifically, our approach can achieve a significantly faster secret bit generation rate at roughly 67 bit/pkt, and the key sequences can pass the randomness tests of the NIST test suite.

Edge computing capabilities in 5G wireless networks promise to benefit mobile users: computing tasks can be offloaded from user devices to nearby edge servers, reducing users’ experienced latencies. Few works have addressed how this offloading should handle long-term user mobility: as devices move, they will need to offload to different edge servers, which may require migrating data or state information from one edge server to another. In this paper, we introduce MoDEMS, a system model and architecture that provides a rigorous theoretical framework and studies the challenges of such migrations to minimize the service provider cost and user latency. We show that this cost minimization problem can be expressed as an integer linear programming problem, which is hard to solve due to resource constraints at the servers and unknown user mobility patterns. We show that finding the optimal migration plan is in general NP-hard, and we propose alternative heuristic solution algorithms that perform well in both theory and practice. We finally validate our results with real user mobility traces, ns-3 simulations, and an LTE testbed experiment. Migrations reduce the latency experienced by users of edge applications by 33% compared to previously proposed migration approaches.

We present FlexPatch, a novel mobile system to enable accurate and real-time object detection over high-resolution video streams. A widely-used approach for real-time video analysis is detection-based tracking (DBT), i.e., running the heavy-but-accurate detector every few frames and applying a lightweight tracker for in-between frames. However, the approach is limited for real-time processing of high-resolution videos in that i) a lightweight tracker fails to handle occlusion, object appearance changes, and occurrences of new objects, and ii) the detection results do not effectively offset tracking errors due to the high detection latency. We propose tracking-aware patching technique to address such limitations of the DBT frameworks. It effectively identifies a set of subareas where the tracker likely fails and tightly packs them into a small-sized rectangular area where the detection can be efficiently performed at low latency. This prevents the accumulation of tracking errors and offsets the tracking errors with frequent fresh detection results. Our extensive evaluation shows that FlexPatch not only enables real-time and power-efficient analysis of high-resolution frames on mobile devices but also improves the overall accuracy by 146% compared to baseline DBT frameworks.

With the popularity of Mobility-on-Demand (MOD) vehicles, a new market called MOD-Vehicular-Crowdsensing (MOVE-CS) was introduced for drivers to earn more by collecting road data. Unfortunately, MOVE-CS failed after two years of operation. To identify the root cause, we survey 581 drivers and reveal its simple operation model based on blindly competitive rewards. This model brings most drivers few yields, resulting in their withdrawals. In contrast, a similar market termed MOD-Human-Crowdsensing (MOMAN-CS) remains successful thanks to a complex model based on exclusively customized rewards. Hence, we wonder whether MOVE-CS can be resurrected by learning from MOMAN-CS. Despite considerable similarity, we can hardly apply the operation model of MOMAN-CS to MOVE-CS, since drivers are also concerned with passenger missions that dominate their earnings. To this end, we analyze a large-scale dataset of 12,493 MOD vehicles, finding that drivers have explicit preference for short-term, immediate gains as well as implicit rationality in pursuit of long-term, stable profits. Therefore, we design a novel operation model for MOVE-CS, at the heart of which lies a spatial-temporal differentiation-aware task recommendation scheme empowered by submodular optimization. Applied to the dataset, our design would essentially benefit both the drivers and platform, thus possessing the potential to resurrect MOVE-CS.

Deep Neural Network (DNN) is becoming adopted for video analytics on mobile devices. To reduce the delay of running DNNs, many mobile devices are equipped with Neural Processing Units (NPU). However, due to the resource limitations of NPU, these DNNs have to be compressed to increase the processing speed at the cost of accuracy. To address the low accuracy problem, we propose a Confidence Based Offloading (CBO) framework for deep learning video analytics. The major challenge is to determine when to return the NPU classification result based on the confidence level of running the DNN, and when to offload the video frames to the server for further processing to increase the accuracy. We first identify the problem of using existing confidence scores to make offloading decisions, and propose confidence score calibration techniques to improve the performance. Then, we formulate the CBO problem where the goal is to maximize accuracy under some time constraint, and propose an adaptive solution that determines which frames to offload at what resolution based on the confidence score and the network condition. Through real implementations and extensive evaluations, we demonstrate that the proposed solution can significantly outperform other approaches.

Over the last decade, Internet of Things (IoT) has permeated our daily life with a broad range of applications. However, a lack of sufficient security features in IoT devices renders IoT ecosystems vulnerable to various network intrusion attacks, potentially causing severe damage. Previous works have explored using machine learning to build anomaly detection models for defending against such attacks. In this paper, we propose FeCo, a federated-contrastive-learning framework that coordinates in-network IoT devices to jointly learn intrusion detection models. FeCo utilizes federated learning to alleviate users’ privacy concerns as participating devices only submit their model parameters rather than local data. Compared to previous works, we develop a novel representation learning method based on contrastive learning that is able to learn a more accurate model for the benign class. FeCo significantly improves the intrusion detection accuracy compared to previous works. Besides, we implement a two-step feature selection scheme to avoid overfitting and reduce computation time. Through extensive experiments on the NSL-KDD dataset, we demonstrate that FeCo achieves as high as 8% accuracy improvement compared to the state-of-the-art and is robust to non-IID data. Evaluations on convergence, computation overhead, and scalability further confirm the suitability of FeCo for IoT intrusion detection.

Interactive panoramic scene delivery not only consumes 4∼6× more bandwidth than traditional video streaming of the same resolution but also requires timely displaying the delivered content to ensure smooth interaction. Since users can only see roughly 20% of the entire scene at a time (called the viewport), it is sufficient to deliver the relevant portion of the panoramic scene if we can accurately predict the user’s motion. It is customary to deliver a portion larger than the viewport to tolerate inaccurate predictions. Intuitively, the larger the delivered portion, the higher the prediction accuracy and lower the wireless transmission success probability. The goal is to select an appropriate delivery portion to maximize system throughput. We formulate this problem as a multi-armed bandit problem and use the classical Kullback-Leibler Upper Confidence Bound (KL-UCB) algorithm for the portion selection. We further develop a novel variant of the KL-UCB algorithm that effectively leverages two-level feedback (i.e., both prediction and transmission outcomes) after each decision on the selected portion and show its asymptotical optimality, which may be of independent interest by itself. We demonstrate the superior performance of our proposed algorithms over existing heuristic methods using both synthetic simulations and real experimental evaluations.

Recovery of missing network monitoring data is of great significance for network operation and maintenance tasks such as anomaly detection and traffic prediction. To exploit historical data for more accurate missing data recovery, some recent studies combine the data together as a tensor to learn more features. However, the need of performing high cost data decomposition compromises their speed and accuracy, which makes them difficult to track dynamic features from streaming monitoring data. To ensure fast and accurate recovery of network monitoring data, this paper proposes NMMF-Stream, a stream-processing scheme with a context extraction module and a generation module. To achieve fast feature extraction and missing data filling with a low sampling rate, we propose several novel techniques, including the context extraction based on both positive and negative monitoring data, context validation via measuring the Pointwise Mutual Information, GRU-based temporal feature learning and memorization, and a new composite loss function to guide the fast and accurate data filling. We have done extensive experiments using two real network traffic monitoring data sets and one network latency data set. The experimental results demonstrate that, compared with three baselines, NMMF-Stream can fill the newly arrived monitoring data very quickly with much higher accuracy.

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

Controlling antenna tilts in cellular networks is imperative to reach an efficient trade-off between network coverage and capacity. In this paper, we devise algorithms learning optimal tilt control policies from existing data (in the so-called passive learning setting) or from data actively generated by the algorithms (the active learning setting). We formalize the design of such algorithms as a Best Policy Identification (BPI) problem in Contextual Linear Multi-Arm Bandits (CL-MAB). An arm represents an antenna tilt update; the context captures current network conditions; the reward corresponds to an improvement of performance, mixing coverage and capacity; and the objective is to identify, with a given level of confidence, an approximately optimal policy (a function mapping the context to an arm with maximal reward). For CL-MAB in both active and passive learning settings, we derive information-theoretical lower bounds on the number of samples required by any algorithm returning an approximately optimal policy with a given level of certainty, and devise algorithms achieving these fundamental limits. We apply our algorithms to the Remote Electrical Tilt (RET) optimization problem in cellular networks, and show that they can produce optimal tilt update policy using much fewer data samples than naive or existing rule-based learning algorithms.

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

The emergence of unmanned aerial vehicles (UAVs) extends the mobile edge computing (MEC) services in broader coverage to offer new flexible and low-latency computing services for user equipment (UE) in the era of 5G and beyond. One of the fundamental requirements in UAV-assisted mobile wireless systems is the low latency, which can be jointly optimized with service caching and task offloading. However, this is challenged by the communication overhead involved with service caching and constrained by limited energy capacity. In this work, we present a comprehensive optimization framework with the objective of minimizing the service latency while incorporating the unique features of UAVs. Specifically, to reduce the caching overhead, we make caching placement decision every T slots (specified by service providers), and adjust UAV trajectory, user equipment or UE-UAV association, and task offloading decisions at each time slot under the constraints of UAV’s energy and resource capacity. By leveraging Lyapunov optimization approach and dependent rounding technique, we design an alternating optimization-based algorithm, named TJSO, which iteratively optimizes caching and offloading decisions. Theoretical analysis proves that TJSO converges to the near-optimal solution in polynomial time. Extensive simulations further verify that our proposed solution can significantly reduce the service delay for UEs while maintaining low energy consumption when compared to the three state-of-the-art baselines.

With the ever-increasing malware threats, malware detection plays an indispensable role in protecting information systems. Although tremendous research efforts have been made, there are still two key challenges hindering them from being applied to accurately and robustly detect malwares. Firstly, most of them represent executables with shallow features, but ignore their semantic and structural information. Secondly, they are primarily based on representations that can be easily modified by attackers and thus cannot provide robustness against adversarial attacks. To tackle the challenges, we present MalGraph, which first represents executables with hierarchical graphs and then uses an end-to-end learning framework based on graph neural networks for malware detection. In particular, a hierarchical graph consists of a function call graph that captures the interaction semantics among different functions at the inter-function level and corresponding control-flow graphs for learning the structural semantics of each function at the intra-function level. We argue the abstraction and hierarchy nature of hierarchical graphs makes them not only easy to capture rich structural information of executables, but also be immune to adversarial attacks. Evaluations show that MalGraph not only outperforms state-of-the-art malware detection, but also exhibits stronger robustness against adversarial attacks by a large margin.

Incorporating domain adaptation is a promising solution to mitigate the domain shift problem of WiFi-based human activity recognition (HAR). The state-of-the-art solutions, however, do not fully exploit all the data, only focusing either on unlabeled samples or labeled samples in the target WiFi environment. Moreover, they largely fail to carefully consider the discrepancy between the source and target WiFi environments, making the adaptation of models to the target environment with few samples become much less effective. To cope with those issues, we propose a Target-Oriented Semi-Supervised (TOSS) domain adaptation method for WiFi-based HAR that can effectively leverage both labeled and unlabeled target samples. We further design a dynamic pseudo label strategy and an uncertainty-based selection method to learn the knowledge from both source and target environments. We implement TOSS with a typical meta learning model and conduct extensive evaluations. The results show that TOSS greatly outperforms state-of-the-art methods under comprehensive 1 on 1 and multi-source one-shot domain adaptation experiments across multiple real-world scenarios.

Learning to optimize (L2O) has recently emerged as a promising approach to solving optimization problems by exploiting the strong prediction power of neural networks and offering lower runtime complexity than conventional solvers. While L2O has been applied to various problems, a crucial yet challenging class of problems — robust combinatorial optimization in the form of minimax optimization — have largely remained under-explored. In addition to the exponentially large decision space, a key challenge for robust combinatorial optimization lies in the inner optimization problem, which is typically non-convex and entangled with outer optimization. In this paper, we study robust combinatorial optimization and propose a novel learning-based optimizer, called LRCO (Learning for Robust Combinatorial Optimization), which quickly outputs a robust solution in the presence of uncertain context. LRCO leverages a pair of learning-based optimizers — one for the minimizer and the other for the maximizer — that use their respective objective functions as losses and can be trained without the need of labels for training problem instances. To evaluate the performance of LRCO, we perform simulations for the task offloading problem in vehicular edge computing. Our results highlight that LRCO can greatly reduce the worst-case cost and improve robustness, while having a very low runtime complexity.

We consider federated learning in a wireless edge network, where multiple power-limited mobile devices collaboratively train a global model, using their local data with the assistance of an edge server. Exploiting over-the-air computation, the edge server updates the global model via analog aggregation of the local models over noisy wireless fading channels. Unlike existing works that separately optimize computation and communication at each step of the learning algorithm, in this work, we jointly optimize the training of the global model and the analog aggregation of local models over time. Our objective is to minimize the accumulated training loss at the edge server, subject to individual long-term transmit power constraints at the mobile devices. We propose an efficient algorithm, termed Online Model Updating with Analog Aggregation (OMUAA), to adaptively update the local and global models based on the time-varying communication environment. The trained model of OMUAA is channel- and power-aware, and it is in closed form with low computational complexity. We study the mutual impact between model training and analog aggregation over time, to derive performance bounds on the computation and communication performance metrics. Simulation results based on real-world image classification datasets and typical Long-Term Evolution network settings demonstrate substantial performance gain of OMUAA over the known best alternatives.

Vehicle-to-vehicle (V2V) communication allows vehicles to directly exchange messages, increasing their situational awareness and offering the potential to prevent hundreds of thousands vehicular crashes annually. Cellular Vehicle-to-Everything (C-V2X), with its LTE-V2X and New Radio (NR)-V2X variants in 4G/LTE- and 5G-based C-V2X, is emerging as the main V2V technology. However, despite security protocols and standards for C-V2X, we expose in this paper that its physical (PHY) and MAC layers are not resilient against intelligent, protocol-aware attacks due to the very predictable PHY-layer structure and vulnerable scheduling algorithm used in both LTE-V2X and NR-V2X. We devise two stealthy denial-of-service (DoS) exploits that dramatically degrade C-V2X availability, thereby increasing the chances of fatal vehicle collisions. We experimentally evaluate our attacks on an integrated, hybrid testbed with USRPs and state-of-the-art LTE-V2X devices as well as through extensive simulations, showing that within seconds, our attacks can reduce a target’s packet delivery ratio by 90% or degrade C-V2X channel throughput by 50%. We propose, analyze, and evaluate detection approaches as well as mitigation techniques to address the vulnerabilities we expose in the C-V2X PHY/MAC layers, providing direction towards better-secured, resilient 5G C-V2X.