INFOCOM 2021 Papers

Real-time on-device object detection for video analytics fails to meet the accuracy requirement due to limited resources of mobile devices while offloading object detection inference to edges is time-consuming due to the transference of video data over edge networks. Based on the system with both on-device object tracking and edge-assisted analysis, we formulate a non-linear time-coupled program over time, maximizing the overall accuracy of object detection by deciding the frequency of edge-assisted inference, under the consideration of both dynamic edge networks and the constrained detection latency. We then design a learning-based online algorithm to adjust the threshold for triggering edge-assisted inference on the fly in terms of the object tracking results, which essentially controls the deviation of on-device tracking between two consecutive frames in the video, by only taking previously observable inputs. We rigorously prove that our approach only incurs sub-linear dynamic regret for the optimality objective. At last, we implement our proposed online schema, and extensive testbed results with real-world traces confirm the empirical superiority over alternative algorithms, in terms of up to 36% improvement on detection accuracy with ensured detection latency.

Multi-device interaction has attracted a growing interest in both mobile communication industry and mobile computing research community as mobile devices enabled social media and social networking continue to blossom. However, due to the stringent low latency requirements and the complexity and intensity of computation, implementing efficient multi-device interaction for real-time video streaming analysis and sharing is still in its infancy. Unlike previous approaches that rely on high network bandwidth and high availability of cloud center with GPUs to support intensive computations for multi-device interaction and for improving the service experience, we propose MIRSA, a novel edge centric multi-device interaction framework with a lightweight end-to-end DNN for on-device visual odometry (VO) streaming analysis by leveraging edge computing optimizations with three main contributions. First, we design MIRSA to migrate computations from the cloud to the device side, reducing the high overhead for large transmission of video streaming while alleviating the server load of the cloud. Second, we design a lightweight VO network by utilizing temporal shift module to support on-device pose estimation. Third, we provide on-device resource-aware scheduling algorithm to optimize the task allocation. Extensive experiments show MIRSA provides real-time high quality pose estimation as an interactive service and outperforms baseline methods.

The two-factor authentication (2FA) has drawn increasingly attention as the mobile devices become more prevalent. For example, the user's possession of the enrolled phone could be used by the 2FA system as the second proof to protect his/her online accounts. Existing 2FA solutions mainly require some form of user-device interaction, which may severely affect user experience and creates extra burdens to users. In this work, we propose Proximity-Echo, a secure 2FA system utilizing the proximity of a user's enrolled phone and the login device as the second proof without requiring the user's interactions or pre-constructed device fingerprints. The basic idea of Proximity-Echo is to derive location signatures based on acoustic beep signals emitted alternately by both devices and sensing the echoes with microphones, and compare the extracted signatures for proximity detection. Given the received beep signal, our system designs a period selection scheme to identify two sound segments accurately: the chirp period is the sound segment propagating directly from the speaker to the microphone whereas the echo period is the sound segment reflected back by surrounding objects. To achieve an accurate proximity detection, we develop a new energy loss compensation extraction scheme by utilizing the extracted chirp periods to estimate the intrinsic differences of energy loss between microphones of the enrolled phone and the login device. Our proximity detection component then conducts the similarity comparison between the identified two echo periods after the energy loss compensation to effectively determine whether the enrolled phone and the login device are in proximity for 2FA. Our experimental results show that our Proximity-Echo is accurate in providing 2FA and robust to both man-in-the-middle (MiM) and co-located attacks across different scenarios and device models.

We investigate the minimum-delay multicast problem for millimeter wave (mmWave) networks. Salient characteristics of mmWave links, directionality and reflections, are considered under sectored antenna model. We first consider directionality only, and identify the property such that the optimal policy can be recursively partitioned into smaller sizes. Using such optimal substructure, we propose an iterative method based on graphs which finds the optimal schedule in polynomial time. Next, we extend our model to incorporate reflections. We introduce the concept of path diversity which states that the availability of reflected paths enables opportunistic reduction of multicast delay. We prove NP-hardness of the problem, and propose approximations with performance bounds and heuristics of reduced complexity. By simulation we show the outperformance of our method over conventional ones, and numerically characterize the gain of path diversity in terms of network size.

The new and important service class of massive Ultra-Reliable Low-Latency Communications (mURLLC) is defined in the 6G era to guarantee very stringent quality-of-service (QoS) requirements, such as ultra-high data rate, super-high reliability, tightly-bounded end-to-end latency, etc. Various 6G promising techniques, such as finite blocklength coding (FBC) and Terahertz (THz), have been proposed to significantly improve QoS performances of mURLLC. Furthermore, with the rapid developments in nano techniques, THz wireless nano-networks have drawn great research attention due to its ability to support ultra-high data-rate while addressing the spectrum scarcity and capacity limitations problems. However, how to efficiently integrate THz-band nano communications with FBC in supporting statistical delay/error-rate bounded QoS provisioning for mURLLC still remains as an open challenge over 6G THz wireless nano-networks. To overcome these problems, in this paper we propose the THz-band statistical delay/error-rate bounded QoS provisioning schemes in supporting mURLLC standards by optimizing both the transmit power and blocklength over 6G THz wireless nano-networks in the finite blocklength regime. Specifically, first, we develop the FBC-driven THz-band wireless channel models in nano-scale. Second, we build up the THz-band interference model and derive the channel capacity and channel dispersion functions using FBC. Third, we maximize the ϵ-effective capacity by developing the joint optimal resource allocation policies under statistical delay/error-rate bounded QoS constraints. Finally, we conduct the extensive simulations to validate and evaluate our proposed schemes at the THz band in the finite blocklength regime.

This paper investigates bandwidth minimization under AoI constraints - a fundamental problem that has not been studied in AoI research. The problem is of critical importance in bandwidth-limited IoT environment when AoI is used as a constraint. We present a novel fast algorithm called Aion that can construct a scheduler to satisfy AoI constraints with strong theoretical guarantee in terms of minimizing required bandwidth. Specifically, we prove that the bandwidth required by Aion is minimum if the AoI constraint vector meets a special mathematical structure called Fractional Consecutively Divisible (FCD). In the general case when the given AoI constraint vector is not FCD, we prove that the bandwidth required by Aion is tightly upper bounded by a factor of the minimum. The results from this paper lay the foundation for future research on bandwidth minimization with AoI guarantee.

Spectrum sharing will be a key technology to tackle spectrum scarcity in the sub-6 GHz bands. To fairly access the shared bandwidth, wireless users will necessarily need to quickly sense large portions of spectrum and opportunistically access unutilized bands. The key unaddressed challenges of spectrum sensing are that (i) it has to be performed with extremely low latency over large bandwidths to detect tiny spectrum holes and to guarantee strict real-time digital signal processing (DSP) constraints; (ii) its underlying algorithms need to be extremely accurate, and flexible enough to work with different wireless bands and protocols to find application in real-world settings. To the best of our knowledge, the literature lacks spectrum sensing techniques able to accomplish both requirements. In this paper, we propose DeepSense, a software/hardware framework for real-time wideband spectrum sensing that relies on real-time deep learning tightly integrated into the transceiver's baseband processing logic to detect and exploit unutilized spectrum bands. DeepSense uses a convolutional neural network (CNN) implemented in the wireless platform's hardware fabric to analyze a small portion of the unprocessed baseband waveform to automatically extract the maximum amount of information with the least amount of I/Q samples. We extensively validate the accuracy, latency and generality performance of DeepSense with (i) a 400 GB dataset containing hundreds of thousands of WiFi transmissions collected "in the wild" with different Signal-to-Noise-Ratio (SNR) conditions and over different days; (ii) a dataset of transmissions collected using our own software-defined radio testbed; and (iii) a synthetic dataset of LTE transmissions under controlled SNR conditions. We also measure the real-time latency of the CNNs trained on the three datasets with an FPGA implementation, and compare our approach with a fixed energy threshold mechanism. Results show that our learning-based approach can deliver a precision and recall of 98% and 97% respectively and a latency as low as 0.61ms. For reproducibility and benchmarking purposes, we pledge to share the code and the datasets used in this paper to the community.

Distributed machine learning with multiple concurrent workers has been widely adopted to train large deep neural networks (DNNs). Parameter synchronization is a key component in each iteration of distributed training, where workers exchange locally computed gradients through an AllReduce operation or parameter servers, for global parameter updates. Parameter synchronization often constitutes a significant portion of the training time; minimizing the communication time contributes substantially to DNN training speed-up. Standard ring-based AllReduce or PS architecture work efficiently mostly with homogeneous inter-worker connectivity. However, available bandwidth among workers in real-world clusters is often heterogeneous, due to different hardware configurations, switching topologies, and contention with concurrent jobs. This work investigates the best parameter synchronization topology and schedule among workers for most expedited communication in distributed DNN training. We show that the optimal parameter synchronization topology should be comprised of trees with different workers as roots, each for aggregating or broadcasting a partition of gradients/parameters. We identify near-optimal forest packing to maximally utilize available bandwidth and overlap aggregation and broadcast stages to minimize communication time. We provide theoretical analysis of the performance bound, and show that our scheme outperforms state-of-the-art parameter synchronization schemes by up to 18.3 times with extensive evaluation under various settings.

In this paper, we address the problem of building adaptive network coding coefficients under dynamic network conditions (e.g., varying link quality and changing number of relays). In existing linear network coding solutions including deterministic network coding and random linear network coding, coding coefficients are set by a heuristic or randomly chosen from a Galois field with equal probability, which can not adapt to dynamic network conditions with good decoding performance. We propose INCdeep, an adaptive Intelligent Network Coding with Deep Reinforcement Learning. Specifically, we formulate a coding coefficients selection problem where network variations can be automatically and continuously expressed as the state transitions of a Markov decision process (MDP). The key advantage is that INCdeep is able to learn and dynamically adjust the coding coefficients for the source node and each relay node according to ongoing network conditions, instead of randomly. The results show that INCdeep has generalization ability that adapts well in dynamic scenarios where link quality is changing fast, and it converges fast in the training process. Compared with the benchmark coding algorithms, INCdeep shows superior performance, including higher decoding probability and lower coding overhead through simulations and experiments.

Unmanned aerial vehicles (UAVs) have brought numerous potentials to establish flexible and reliable emergency networks in disaster areas when terrestrial communication infrastructures go down. Nevertheless, potential security threats may occur on UAVs during data transmissions due to the untrustful environment and open-access UAV networking. Moreover, UAVs typically have limited battery and computation capacity, making them unaffordable to execute heavy security provisioning operations when carrying out complicated rescue tasks. In this paper, we develop RescueChain, a secure and efficient information sharing scheme for UAV-aided disaster rescue. Specifically, we first implement a lightweight blockchain-based framework to safeguard data sharing under disasters and immutably trace misbehaving entities. A reputation-based consensus protocol is devised to adapt the weakly connected environment with improved consensus efficiency and promoted UAVs' honest behaviors. Furthermore, we introduce a novel vehicular fog computing based off-chain mechanism by leveraging ground vehicles as moving fog nodes to offload UAVs' heavy data processing and storage tasks. To optimally stimulate vehicles to share their idle computing resources, we also design a two-layer reinforcement learning based incentive algorithm for UAVs and ground vehicles in the highly dynamic networks. Simulation results show that RescueChain can effectively accelerate consensus process, enhance user payoffs, and reduce delivery latency, compared with representative existing approaches.

With the rapid advancement in machine learning (ML), ML-based Intrusion Detection Systems (IDSs) are widely deployed to protect networks from various attacks. Yet one of the biggest challenges is that ML-based IDSs suffer from adversarial example (AE) attacks. By applying small perturbations (e.g. slightly increasing packet inter-arrival time) to the intrusion traffic, an AE attack can flip the prediction of a well-trained IDS. We address this challenge by proposing MANDA, a MANifold and Decision boundary-based AE detection system. Through analyzing AE attacks, we notice that 1) an AE tends to be close to its original manifold (i.e., the cluster of samples in its original class) regardless which class it is misclassified into; and 2) AEs tend to be close to the decision boundary so as to minimize the perturbation scale. Based on the two observations, we design MANDA for accurate AE detection by exploiting inconsistency between manifold evaluation and IDS model inference and evaluating model uncertainty on small perturbations. We evaluate MANDA on NSL-KDD under three state-of-the-art AE attacks. Our experimental results show that MANDA achieves as high as 98.41% true-positive rate with 5% false-positive rate and can be applied to other problem spaces such as image recognition.

Continuous domestic respiration monitoring provides vital information for diagnosing assorted diseases. In this paper, we introduce RESPTRACKER, the first continuous, multiple-person respiration tracking system in domestic settings using acoustic-based COTS devices. RESPTRACKER uses a two-stage algorithm to separate and recombine respiration signals from multiple paths in a short period so that it can track the respiration rate of multiple moving subjects. Our experimental results show that our two-stage algorithm can distinguish the respiration of at least four subjects at a distance of three meters.

We consider the problem of network unreachability in a global-scale cloud-hosted service that caters to hundreds of millions of users. Even when the service itself is up, the "last mile" between where users are, and the cloud is often the weak link that could render the service unreachable. We present NetDetector, a tool for detecting network-unreachability based on measurements from a client-based HTTP-ping service. NetDetector employs two models. The first, GA (Gaussian Alerts) models temporally averaged raw success rate of the HTTP-pings as a Gaussian distribution and flags significant dips below the mean as unreachability episodes. The second, more sophisticated approach (BB, or Beta-Binomial) models the health of network connectivity as the probability of an access request succeeding, estimates health from noisy samples, and alerts based on dips in health below a client-network-specific SLO (service-level objective) derived from data. These algorithms are enhanced by a drill-down technique that identifies a more precise scope of the unreachability event. We present promising results from GA, which has been in deployment, and the experimental BB detector over a 4-month period. For instance, GA flags 49 country-level unreachability incidents, of which 42 were labelled true positives based on investigation by on-call engineers (OCEs).

Unmanned Aerial Vehicles (UAVs) or drones are increasingly used for urban applications like traffic monitoring and construction surveys. Autonomous navigation allows drones to visit waypoints and accomplish activities as part of their mission. A common activity is to hover and observe a location using on-board cameras. Advances in Deep Neural Networks (DNNs) allow such videos to be analyzed for automated decision making. UAVs also host edge computing capability for on-board inferencing by such DNNs. To this end, for a fleet of drones, we propose a novel Mission Scheduling Problem (MSP) that co-schedules the flight routes to visit and record video at waypoints, and their subsequent on-board edge analytics. The proposed schedule maximizes the utility from the activities while meeting activity deadlines as well as energy and computing constraints. We first prove that MSP is NP-hard and then optimally solve it by formulating a mixed integer linear programming (MILP) problem. Next, we design two efficient heuristic algorithms, jsc and vrc, that provide fast sub-optimal solutions. Evaluation of these three schedulers using real drone traces demonstrate utility-runtime trade-offs under diverse workloads.

UHF RFID technology becomes increasingly popular in RFID-enabled stores (e.g., UNIQLO), since UHF RFID readers can quickly read a large number of RFID tags from afar. The deployed RFID infrastructure, however, does not directly benefit smartphone users in the stores, mainly because smartphones cannot read UHF RFID tags or fetch relevant information (e.g., updated price, real-time promotion). This paper aims to bridge the gap and allow users to `read' UHF RFID tags using their smartphones, without any hardware modification to either deployed RFID systems or smartphone hardware. To `read' an interested tag, a user makes a pre-defined smartphone gesture in front of an interested tag. The smartphone gesture causes changes in 1) RFID measurement data (e.g., phase) captured by RFID infrastructure, and 2) motion sensor data (e.g., accelerometer) captured by the user's smartphone. By matching the two data, our system (named ShakeReader) can pair the interested tag with the corresponding smartphone, thereby enabling the smartphone to indirectly `read' the interested UHF tag. We build a novel reflector polarization model to analyze the impact of smartphone gesture to RFID backscattered signals. Experimental results show that ShakeReader can accurately pair interested tags with their corresponding smartphones with an accuracy of >94.6%.

Unmanned aerial vehicle (UAV) communications and networks are promising technologies in the forthcoming fifth-generation wireless communications. However, they have the challenges for realizing secure communications. In this paper, we consider to construct a virtual antenna array consists UAV elements and use collaborative beamforming (CB) to achieve the UAV secure communications with different base stations (BSs), subject to the known and unknown eavesdroppers on the ground. To achieve a better secure performance, the UAV elements can fly to optimal positions with optimal excitation current weights for performing CB transmissions. However, this leads to extra motion energy consumptions. We formulate a secure communication multi-objective optimization problem (MOP) of UAV networks to simultaneously improve the total secrecy rates, total maximum sidelobe levels (SLLs) and total motion energy consumptions of UAVs by jointly optimizing the positions and excitation current weights of UAVs, and the order of communicating with different BSs. Due to the complexity and NP-hardness of the formulated MOP, we propose an improved multi-objective dragonfly algorithm with chaotic solution initialization and hybrid solution update operators (IMODACH) to solve the problem. Simulation results verify that the proposed IMODACH can effectively solve the formulated MOP and it has better performance than some other benchmark approaches.

Payment channel networks (PCNs) are proposed to improve the cryptocurrency scalability by settling off-chain transactions. However, PCN introduces an undesirable assumption that a channel participant must stay online and be synchronized with the blockchain to defend against frauds. To alleviate this issue, watchtowers have been introduced, such that a hiring party can employ a watchtower to monitor the channel for fraud. However, a watchtower might profit from colluding with a cheating counterparty and fail to perform this job. Existing solutions either focus on heavy cryptographic techniques or require a large collateral. In this work, we leverage smart contracts through economic approaches to counter collusions for watchtowers in PCNs. This brings distrust between the watchtower and the counterparty, so that rational parties do not collude or cheat. We provide detailed analyses on the contracts and rigorously prove that the contracts are effective to counter collusions with minimal on-chain operations. In particular, a watchtower only needs to lock a small collateral, which incentivizes participation of watchtowers and users. We also provide an implementation of the contracts in Solidity and execute them on Ethereum to demonstrate the scalability and efficiency of the contracts.

In this work, we perform a comparative study of centralized and decentralized update strategies for the basic remote tracking problem of many distributed users/devices with randomly evolving states. Our goal is to reveal the impact of the fundamentally different tradeoffs that exist between information accuracy and communication cost under these two update paradigms. In one extreme, decentralized updates are triggered by distributed users/transmitters based on exact local state-information, but also at a higher cost due to the need for uncoordinated multi-user communication. In the other extreme, centralized updates are triggered by the common tracker/receiver based on estimated global state-information, but also at a lower cost due to the capability of coordinated multi-user communication. We use a generic superlinear function to model the communication cost with respect to the number of simultaneous updates for multiple sources. We characterize the conditions under which transmitter-driven decentralized update policies outperform their receiver-driven centralized counterparts for symmetric sources, and vice versa. Further, we extend the results to a scenario where system parameters are unknown and develop learning-based update policies that asymptotically achieve the minimum cost levels attained by the optimal policies.

We consider online convex optimization (OCO) with multi-slot feedback delay, where an agent makes a sequence of online decisions to minimize the accumulation of time-varying convex loss functions, subject to short-term and long-term constraints that are possibly time-varying. The current convex loss function and the long-term constraint function are revealed to the agent only after the decision is made, and they may be delayed for multiple time slots. Existing work on OCO under this general setting has focused on the static regret, which measures the gap of losses between the online decision sequence and an offline benchmark that is fixed over time. In this work, we consider both the static regret and the more practically meaningful dynamic regret, where the benchmark is a time-varying sequence of per-slot optimizers. We propose an efficient algorithm, termed Delay-Tolerant Constrained-OCO (DTC-OCO), which uses a novel constraint penalty with double regularization to tackle the asynchrony between information feedback and decision updates. We derive upper bounds on its dynamic regret, static regret, and constraint violation, proving them to be sublinear under mild conditions. We further apply DTC-OCO to a general network resource allocation problem, which arises in many systems such as data networks and cloud computing. Simulation results demonstrate substantial performance gain of DTC-OCO over the known best alternative.