IEEE INFOCOM 2022
Privacy
Otus: A Gaze Model-based Privacy Control Framework for Eye Tracking Applications
Miao Hu and Zhenxiao Luo (Sun Yat-Sen University, China); Yipeng Zhou (Macquarie University, Australia); Xuezheng Liu and Di Wu (Sun Yat-Sen University, China)
Privacy-Preserving Online Task Assignment in Spatial Crowdsourcing: A Graph-based Approach
Hengzhi Wang, En Wang and Yongjian Yang (Jilin University, China); Jie Wu (Temple University, USA); Falko Dressler (TU Berlin, Germany)
Protect Privacy from Gradient Leakage Attack in Federated Learning
Junxiao Wang, Song Guo and Xin Xie (Hong Kong Polytechnic University, Hong Kong); Heng Qi (Dalian University of Technology, China)
When Deep Learning Meets Steganography: Protecting Inference Privacy in the Dark
Qin Liu (Hunan University & Temple University, China); Jiamin Yang and Hongbo Jiang (Hunan University, China); Jie Wu (Temple University, USA); Tao Peng (Guangzhou University, China); Tian Wang (Beijing Normal University & UIC, China); Guojun Wang (Guangzhou University, China)
Session Chair
Yupeng Li (Hong Kong Baptist University)
Cloud
Cutting Tail Latency in Commodity Datacenters with Cloudburst
Gaoxiong Zeng (Hong Kong University of Science and Technology, China); Li Chen (Huawei, China); Bairen Yi (Bytedance, China); Kai Chen (Hong Kong University of Science and Technology, China)
This paper presents Cloudburst, a simple, effective yet readily deployable solution achieving similar or even better results without introducing the above complexities. At its core, Cloudburst explores forward error correction (FEC) over multipath - it proactively spreads FEC-coded packets generated from messages over multipath in parallel, and recovers them with the first few arriving ones. As a result, Cloudburst is able to obliviously exploit underutilized paths, thus achieving low tail latency. We have implemented Cloudburst as a user-space library, and deployed it on a testbed with commodity switches. Our testbed and simulation experiments show the superior performance of Cloudburst. For example, Cloudburst achieves 63.69% and 60.06% reduction in 99th percentile message/flow completion time (FCT) compared to DCTCP and PIAS, respectively.
EdgeMatrix: A Resources Redefined Edge-Cloud System for Prioritized Services
Yuanming Ren, Shihao Shen, Yanli Ju and Xiaofei Wang (Tianjin University, China); Wenyu Wang (Shanghai Zhuichu Networking Technologies Co., Ltd., China); Victor C.M. Leung (Shenzhen University, China & The University of British Columbia, Canada)
TRUST: Real-Time Request Updating with Elastic Resource Provisioning in Clouds
Jingzhou Wang, Gongming Zhao, Hongli Xu and Yangming Zhao (University of Science and Technology of China, China); Xuwei Yang (Huawei Technologies, China); He Huang (Soochow University, China)
VITA: Virtual Network Topology-aware Southbound Message Delivery in Clouds
Luyao Luo, Gongming Zhao and Hongli Xu (University of Science and Technology of China, China); Liguang Xie and Ying Xiong (Futurewei Technologies, USA)
Session Chair
Hong Xu (The Chinese University of Hong Kong)
Learning and Prediction
Boosting Internet Card Cellular Business via User Portraits: A Case of Churn Prediction
Fan Wu and Ju Ren (Tsinghua University, China); Feng Lyu (Central South University, China); Peng Yang (Huazhong University of Science and Technology, China); Yongmin Zhang and Deyu Zhang (Central South University, China); Yaoxue Zhang (Tsinghua University, China)
Particularly, we first conduct a systematical analysis on usage data by investigating the difference of two types of users, examining the impact of user properties, and characterizing the spatio-temporal networking patterns. After that, we shed light on one specific business case of churn prediction by devising an IC user Churn Prediction model, named ICCP, which consists of a feature extraction component and a learning architecture design. In ICCP, both the static portrait features and temporal sequential features are extracted, and one principal component analysis block and the embedding/transformer layers are devised to learn the respective information of two types of features, which are collectively fed into the classification multilayer perceptron layer for prediction. Extensive experiments corroborate the efficacy of ICCP.
Lumos: towards Better Video Streaming QoE through Accurate Throughput Prediction
Gerui Lv, Qinghua Wu, Weiran Wang and Zhenyu Li (Institute of Computing Technology, Chinese Academy of Sciences, China); Gaogang Xie (CNIC Chinese Academy of Sciences & University of Chinese Academy of Sciences, China)
Poisoning Attacks on Deep Learning based Wireless Traffic Prediction
Tianhang Zheng and Baochun Li (University of Toronto, Canada)
PreGAN: Preemptive Migration Prediction Network for Proactive Fault-Tolerant Edge Computing
Shreshth Tuli and Giuliano Casale (Imperial College London, United Kingdom (Great Britain)); Nicholas Jennings (Imperial College, United Kingdom (Great Britain))
Session Chair
Ruozhou Yu (North Carolina State University)
RFID Applications
Encoding based Range Detection in Commodity RFID Systems
Xi Yu and Jia Liu (Nanjing University, China); Shigeng Zhang (Central South University, China); Xingyu Chen, Xu Zhang and Lijun Chen (Nanjing University, China)
RC6D: An RFID and CV Fusion System for Real-time 6D Object Pose Estimation
Bojun Zhang (TianJin University, China); Mengning Li (Shanghai Jiao Tong University); Xin Xie (Hong Kong Polytechnic University, Hong Kong); Luoyi Fu (Shanghai Jiao Tong University, China); Xinyu Tong and Xiulong Liu (Tianjin University, China)
RCID: Fingerprinting Passive RFID Tags via Wideband Backscatter
Jiawei Li, Ang Li, Dianqi Han and Yan Zhang (Arizona State University, USA); Tao Li (Indiana University-Purdue University Indianapolis, USA); Yanchao Zhang (Arizona State University, USA)
Revisiting RFID Missing Tag Identification
Kanghuai Liu (SYSU, China); Lin Chen (Sun Yat-sen University, China); Junyi Huang and Shiyuan Liu (SYSU, China); Jihong Yu (Beijing Institute of Technology/ Simon Fraser University, China)
by leveraging a tree-based structure with the expected execution time of .\Omega \left(\frac{\log\log N}{\log N}N+\frac{(1-\alpha)^2(1-\delta)^2}{ \epsilon^2}\right)., reducing the time overhead by a factor of up to .\log N. over the best algorithm in the literature. The key technicality in our design is a novel data structure termed as collision-partition tree (CPT), built upon a subset of bits in tag pseudo-IDs leading to more balanced tree structure and hence reducing the time complexity in parsing the entire tree.
Session Chair
Song Min Kim (KAIST)
Policy and Rules (New)
CoToRu: Automatic Generation of Network Intrusion Detection Rules from Code
Heng Chuan Tan (Advanced Digital Sciences Center, Singapore); Carmen Cheh and Binbin Chen (Singapore University of Technology and Design, Singapore)
Learning Buffer Management Policies for Shared Memory Switches
Mowei Wang, Sijiang Huang and Yong Cui (Tsinghua University, China); Wendong Wang (Beijing University of Posts and Telecommunications, China); Zhenhua Liu (Huawei Technologies, China)
Current buffer management practices usually rely on simple, generalized heuristics and have unrealistic assumptions of traffic patterns, since developing and tuning a buffer management policy that is suited for every pattern is infeasible. We show that modern machine learning techniques can be of essential help to learn efficient policies automatically.
In this paper, we propose Neural Dynamic Threshold (NDT) that uses reinforcement learning and neural networks to learn buffer management policies without any human instructions except for a high-level objective, e.g. minimizing average flow completion time (FCT). However, the high complexity and scale of the buffer management problem present enormous challenges to off-the-shelf RL solutions. To make NDT feasible, we develop three techniques: 1) a scalable neural network model leveraging the permutation symmetry of the switch ports, 2) an action encoding scheme with domain knowledge, and 3) a cumulative-event trigger mechanism to achieve efficient training and inference. Our simulation and DPDK-based switch prototype demonstrate that NDT generalizes well and outperforms hand-tuned heuristic policies even on workloads for which it was not explicitly trained.
Learning Optimal Antenna Tilt Control Policies: A Contextual Linear Bandit Approach
Filippo Vannella (KTH Royal Institute of Technology & Ericsson Research, Sweden); Alexandre Proutiere (KTH, Sweden); Yassir Jedra (KTH Royal Institute of Technology, Sweden); Jaeseong Jeong (Ericsson Research, Sweden)
Policy-Induced Unsupervised Feature Selection: A Networking Case Study
Jalil Taghia, Farnaz Moradi, Hannes Larsson and Xiaoyu Lan (Ericsson Research, Sweden); Masoumeh Ebrahimi (KTH Royal Institute of Techology & University of Turku, Sweden); Andreas Johnsson (Ericsson Research, Sweden)
Session Chair
Kate Ching-Ju Lin (National Chiao Tung University)
Scheduling 1
AutoByte: Automatic Configuration for Optimal Communication Scheduling in DNN Training
Yiqing Ma (HKUST, China); Hao Wang (HKUST, Hong Kong); Yiming Zhang (NUDT & NiceX Lab, China); Kai Chen (Hong Kong University of Science and Technology, China)
To address this problem, in this paper we present a realtime configuration method (called AutoByte) that automatically and timely searches the optimal hyper-parameters as the training systems dynamically change. AutoByte extends the ByteScheduler framework with a meta-network, which takes the systems' runtime statistics as its input and outputs predictions for speedups under specific configurations. Evaluation results on various DNN models show that AutoByte can dynamically tune the hyper-parameters with low resource usage, and deliver up to 33.2% higher performance than the best static configuration method on the ByteScheduler framework.
Joint Near-Optimal Age-based Data Transmission and Energy Replenishment Scheduling at Wireless-Powered Network Edge
Quan Chen (Guangdong University of Technology, China); Zhipeng Cai (Georgia State University, USA); Cheng Liang lun and Feng Wang (Guangdong University of Technology, China); Hong Gao (University of Harbin Institute Technology, China)
Most existing works try to optimize the system AoI from the point of data transmission. Unfortunately, at wireless-powered network edge, the charging schedule of the source nodes also needs to be decided besides data transmission. Thus, in this paper, we investigate the joint scheduling problem of data transmission and energy replenishment to optimize the peak AoI at network edge with directional chargers. To the best of our knowledge, this is the first work that considers such two problems simultaneously.
Firstly, the theoretical bounds of the peak AoI with respect to the charging latency are derived. Secondly, for the minimum peak AoI scheduling problem with a single charger, an optimal scheduling algorithm is proposed to minimize the charging latency, and then a data transmission scheduling strategy is also given to optimize the peak AoI. The proposed algorithm is proved to have a constant approximation ratio of up to 1.5. When there exist multiple chargers, an approximate algorithm is also proposed to minimize the charging latency and peak AoI. Finally, the simulation results verify the high performance of proposed algorithms in terms of AoI.
Kalmia: A Heterogeneous QoS-aware Scheduling Framework for DNN Tasks on Edge Servers
Ziyan Fu and Ju Ren (Tsinghua University, China); Deyu Zhang (Central South University, China); Yuezhi Zhou and Yaoxue Zhang (Tsinghua University, China)
Subset Selection for Hybrid Task Scheduling with General Cost Constraints
Yu Sun, Chi Lin, Jiankang Ren, Pengfei Wang, Lei Wang, Guowei WU and Qiang Zhang (Dalian University of Technology, China)
Session Chair
Yusheng Ji (National Institute of Informatics)
5G and mmW Networks
A Comparative Measurement Study of Commercial 5G mmWave Deployments
Arvind Narayanan (University of Minnesota, USA); Muhammad Iqbal Rochman (University of Chicago, USA); Ahmad Hassan (University of Minnesota, USA); Bariq S. Firmansyah (Institut Teknologi Bandung, Indonesia); Vanlin Sathya (University of Chicago, USA); Monisha Ghosh (University Of Chicago, USA); Feng Qian (University of Minnesota, Twin Cities, USA); Zhi-Li Zhang (University of Minnesota, USA)
of beams used, number of channels aggregated, and density of deployments, which reflect on the throughput performance. Our measurement-driven propagation analysis demonstrates that narrower beams experience a lower path-loss exponent than wider beams, which combined with up to eight frequency channels
aggregated on up to eight beams can deliver a peak throughput of 1.2 Gbps at distances greater than 100 m.
AI in 5G: The Case of Online Distributed Transfer Learning over Edge Networks
Yulan Yuan (Beijing University of Posts and Telecommunications, China); Lei Jiao (University of Oregon, USA); Konglin Zhu (Beijing University of Posts and Telecommunications, China); Xiaojun Lin (Purdue University, USA); Lin Zhang (Beijing University of Posts and Telecommunications, China)
mmPhone: Acoustic Eavesdropping on Loudspeakers via mmWave-characterized Piezoelectric Effect
Chao Wang, Feng Lin, Tiantian Liu, Ziwei Liu, Yijie Shen, Zhongjie Ba and Li Lu (Zhejiang University, China); Wenyao Xu (SUNY Buffalo & Wireless Health Institute, USA); Kui Ren (Zhejiang University, China)
Optimizing Coverage with Intelligent Surfaces for Indoor mmWave Networks
Jingyuan Zhang and Douglas Blough (Georgia Institute of Technology, USA)
Session Chair
Xiaojun Lin (Purdue University)
TII Virtual Booth
Pricing
DiFi: A Go-as-You-Pay Wi-Fi Access System
Lianjie Shi, Runxin Tian, Xin Wang and Richard T. B. Ma (National University of Singapore, Singapore)
Online Data Valuation and Pricing for Machine Learning Tasks in Mobile Health
Anran Xu, Zhenzhe Zheng, Fan Wu and Guihai Chen (Shanghai Jiao Tong University, China)
Online Pricing with Limited Supply and Time-Sensitive Valuations
Shaoang Li, Lan Zhang and Xiang-Yang Li (University of Science and Technology of China, China)
Extensive simulation studies show that our algorithm outperforms previous mechanisms in various settings.
Optimal Pricing Under Vertical and Horizontal Interaction Structures for IoT Networks
Ningning Ding (The Chinese University of Hong Kong, Hong Kong); Lin Gao (Harbin Institute of Technology (Shenzhen), China); Jianwei Huang (The Chinese University of Hong Kong, Shenzhen, China); Xin Li (Huawei Technologies, China); Xin Chen (Shanghai Research Center, Huawei Technologies, China)
Session Chair
Xiaowen Gong (Auburn University)
Scheduling 2
EdgeTuner: Fast Scheduling Algorithm Tuning for Dynamic Edge-Cloud Workloads and Resources
Rui Han, Shilin Wen, Chi Harold Liu, Ye Yuan and Guoren Wang (Beijing Institute of Technology, China); Lydia Y. Chen (IBM Zurich Research Laboratory, Switzerland)
Optimizing Task Placement and Online Scheduling for Distributed GNN Training Acceleration
Ziyue Luo, Yixin Bao and Chuan Wu (The University of Hong Kong, Hong Kong)
Payment Channel Networks: Single-Hop Scheduling for Throughput Maximization
Nikolaos Papadis and Leandros Tassiulas (Yale University, USA)
Shield: Safety Ensured High-efficient Scheduling for Magnetic MIMO Wireless Power Transfer System
Wangqiu Zhou, Hao Zhou, Xiaoyu Wang, Kaiwen Guo, Haisheng Tan and Xiang-Yang Li (University of Science and Technology of China, China)
Session Chair
Peshal Nayak (Samsung Research America)
Algorithms 1
Copa+: Analysis and Improvement of thedelay-based congestion control algorithm Copa
Wanchun Jiang, Haoyang Li, Zheyuan Liu, Jia Wu and Jiawei Huang (Central South University, China); Danfeng Shan (Xi'an Jiaotong University, China); Jianxin Wang (Central South University, China)
Learning for Robust Combinatorial Optimization: Algorithm and Application
Zhihui Shao (UC Riverside, USA); Jianyi Yang (University of California, Riverside, USA); Cong Shen (University of Virginia, USA); Shaolei Ren (University of California, Riverside, USA)
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, with low runtime complexity.
Polynomial-Time Algorithm for the Regional SRLG-disjoint Paths Problem
Balázs Vass (Budapest University of Technology and Economics, Hungary); Erika R. Bérczi-Kovács and Ábel Barabás (Eötvös University, Budapest, Hungary); Zsombor László Hajdú and János Tapolcai (Budapest University of Technology and Economics, Hungary)
Provably Efficient Algorithms for Traffic-sensitive SFC Placement and Flow Routing
Yingling Mao, Xiaojun Shang and Yuanyuan Yang (Stony Brook University, USA)
Session Chair
En Wang (Jilin University)
Panel
Mid-Scale Research Infrastructures for Networking Research
Panelists: Navid Nikaein (Eurecom), Dipankar Raychaudhuri (Rutgers University), Ashutosh Sabharwal (Rice University), Kuang-Ching Wang (Clemson University), Murat Torlak (NSF); Moderator: Xinyu Zhang (UC San Diego)
Virtual Lunch Break
A Reflection with INFOCOM Achievement Award Winner
A Reflection with INFOCOM Achievement Award Winner
Guoliang Xue (Arizona State University, USA)
Mobile Applications 1
DeepEar: Sound Localization with Binaural Microphones
Qiang Yang and Yuanqing Zheng (The Hong Kong Polytechnic University, Hong Kong)
Different from hand-crafted features used in prior works, DeepEar can automatically extract useful features for localization. More importantly, the trained neural networks can be extended and adapt to new environments with a minimum amount of extra training data. Experiment results show that DeepEar can substantially outperform a state-of-the-art deep learning approach, with a sound detection accuracy of 93.3% and an azimuth estimation error of 7.4 degrees in multi-source scenarios.
Impact of Later-Stages COVID-19 Response Measures on Spatiotemporal Mobile Service Usage
André Felipe Zanella, Orlando E. Martínez-Durive and Sachit Mishra (IMDEA Networks Institute, Spain); Zbigniew Smoreda (Orange Labs & France Telecom Group, France); Marco Fiore (IMDEA Networks Institute, Spain)
SAH: Fine-grained RFID Localization with Antenna Calibration
Xu Zhang, Jia Liu, Xingyu Chen, Wenjie Li and Lijun Chen (Nanjing University, China)
Separating Voices from Multiple Sound Sources using 2D Microphone Array
Xinran Lu, Lei Xie and Fang Wang (Nanjing University, China); Tao Gu (Macquarie University, Australia); Chuyu Wang, Wei Wang and Sanglu Lu (Nanjing University, China)
Session Chair
Zhichao Cao (Michigan State University)
AoI
A Theory of Second-Order Wireless Network Optimization and Its Application on AoI
Daojing Guo, Khaled Nakhleh and I-Hong Hou (Texas A&M University, USA); Sastry Kompella and Clement Kam (Naval Research Laboratory, USA)
Age-Based Scheduling for Monitoring and Control Applications in Mobile Edge Computing Systems
Xingqiu He, Sheng Wang, Xiong Wang, Shizhong Xu and Jing Ren (University of Electronic Science and Technology of China, China)
AoI-centric Task Scheduling for Autonomous Driving Systems
Chengyuan Xu, Qian Xu and Jianping Wang (City University of Hong Kong, Hong Kong); Kui Wu (University of Victoria, Canada); Kejie Lu (University of Puerto Rico at Mayaguez, Puerto Rico); Chunming Qiao (University at Buffalo, USA)
AoI-minimal UAV Crowdsensing by Model-based Graph Convolutional Reinforcement Learning
Zipeng Dai, Chi Harold Liu, Yuxiao Ye, Rui Han, Ye Yuan and Guoren Wang (Beijing Institute of Technology, China); Jian Tang (Syracuse University, USA)
Session Chair
Jaya Prakash V Champati (IMDEA Networks Institute)
Caching
Caching-based Multicast Message Authentication in Time-critical Industrial Control Systems
Utku Tefek (Advanced Digital Sciences Center, Singapore & University of Illinois Urbana-Champaign, USA); Ertem Esiner (Advanced Digital Sciences Center, Singapore); Daisuke Mashima (Advanced Digital Sciences Center & National University of Singapore, Singapore); Binbin Chen (Singapore University of Technology and Design, Singapore); Yih-Chun Hu (University of Illinois at Urbana-Champaign, USA)
Distributed Cooperative Caching in Unreliable Edge Environments
Yu Liu, Yingling Mao, Xiaojun Shang, Zhenhua Liu and Yuanyuan Yang (Stony Brook University, USA)
Online File Caching in Latency-Sensitive Systems with Delayed Hits and Bypassing
Chi Zhang, Haisheng Tan and Guopeng Li (University of Science and Technology of China, China); Zhenhua Han (Microsoft Research Asia, China); Shaofeng H.-C. Jiang (Peking University, China); Xiang-Yang Li (University of Science and Technology of China, China)
Motivated by the practical scenarios, we study the online general file caching problem with delayed hits and bypassing, i.e., a request may be bypassed and processed directly at the remote data center. The objective is to minimize the total request latency. We show a general reduction that turns a traditional file caching algorithm to one that can handle delayed hits. We give an ..O(Z^{3/2} \log K)..-competitive algorithm called CaLa with this reduction, where ..Z.. is the maximum fetching latency of any file and ..K.. is the cache size, and we show a nearly-tight lower bound ..\Omega(Z \log k).. for our ratio. Extensive simulations based on the production data trace from Google and the Yahoo benchmark illustrate that CaLa can reduce the latency by up to ..9.42\%.. compared with the state-of-the-art scheme dealing with delayed hits without bypassing, and this improvement increases to ..32.01\%.. if bypassing is allowed.
Retention-aware Container Caching for Serverless Edge Computing
Li Pan (Huazhong University of Science and Technology, China); Lin Wang (VU Amsterdam & TU Darmstadt, The Netherlands); Shutong Chen and Fangming Liu (Huazhong University of Science and Technology, China)
Session Chair
Jian Li (Binghamton University)
Algorithms 2
A Unified Model for Bi-objective Online Stochastic Bipartite Matching with Two-sided Limited Patience
Gaofei Xiao and Jiaqi Zheng (Nanjing University, China); Haipeng Dai (Nanjing University & State Key Laboratory for Novel Software Technology, China)
Lazy Self-Adjusting Bounded-Degree Networks for the Matching Model
Evgeniy Feder (ITMO University, Russia); Ichha Rathod and Punit Shyamsukha (Indian Institute of Technology Delhi, India); Robert Sama (University of Vienna, Austria); Vitaly Aksenov (ITMO University, Russia); Iosif Salem and Stefan Schmid (University of Vienna, Austria)
We initiate the study of online algorithms for SANs in a more realistic cost model, the Matching Model (MM), in which the network topology is given by the union of a constant number of bipartite matchings (realized by optical switches), and in which changing an entire matching incurs a fixed cost \alpha The cost of routing is given by the number of hops packets need to traverse.
Our main result is a lazy topology adjustment method for designing efficient online SAN algorithms in the MM. We design and analyze online SAN algorithms for line, tree, and bounded degree networks in the MM, with cost O(\sqrt{\alpha}) times the cost of reference algorithms in the uniform cost model (SM). We report on empirical results considering publicly available datacenter network traces, that verify the theoretical bounds.
Maximizing h-hop Independently Submodular Functions Under Connectivity Constraint
Wenzheng Xu and Dezhong Peng (Sichuan University, China); Weifa Liang and Xiaohua Jia (City University of Hong Kong, Hong Kong); Zichuan Xu (Dalian University of Technology, China); Pan Zhou (School of CSE, Huazhong University of Science and Technology, China); Weigang Wu and Xiang Chen (Sun Yat-sen University, China)
Optimal Shielding to Guarantee Region-Based Connectivity under Geographical Failures
Binglin Tao, Mingyu Xiao, Bakhadyr Khoussainov and Junqiang Peng (University of Electronic Science and Technology of China, China)
Session Chair
Song Fang (University of Oklahoma)
Virtual Coffee Break
Mobile Security
Big Brother is Listening: An Evaluation Framework on Ultrasonic Microphone Jammers
Yike Chen, Ming Gao, Yimin Li, Lingfeng Zhang, Li Lu and Feng Lin (Zhejiang University, China); Jinsong Han (Zhejiang University & School of Cyber Science and Technology, China); Kui Ren (Zhejiang University, China)
InertiEAR: Automatic and Device-independent IMU-based Eavesdropping on Smartphones
Ming Gao, Yajie Liu, Yike Chen, Yimin Li, Zhongjie Ba and Xian Xu (Zhejiang University, China); Jinsong Han (Zhejiang University & School of Cyber Science and Technology, China)
In the InertiEAR design, we exploit coherence between responses of the built-in accelerometer and gyroscope and their hardware diversity using a mathematical model. The coherence allows precise segmentation without manual assistance. We also mitigate the impact of hardware diversity and achieve better device-independent performance than existing approaches that have to massively increase training data from different smartphones for a scalable network model. These two advantages re-enable zero-permission attacks but also extend the attacking surface and endangering degree to off-the-shelf smartphones. InertiEAR achieves a recognition accuracy of 78.8% with a cross-device accuracy of up to 49.8% among 12 smartphones.
JADE: Data-Driven Automated Jammer Detection Framework for Operational Mobile Networks
Caner Kilinc (University of Edinburgh, Sweden); Mahesh K Marina (The University of Edinburgh, United Kingdom (Great Britain)); Muhammad Usama (Information Technology University (ITU), Punjab, Lahore, Pakistan); Salih Ergüt (Oredata, Turkey & Rumeli University, Turkey); Jon Crowcroft (University of Cambridge, United Kingdom (Great Britain)); Tugrul Gundogdu and Ilhan Akinci (Turkcell, Turkey)
MDoC: Compromising WRSNs through Denial of Charge by Mobile Charger
Chi Lin, Pengfei Wang, Qiang Zhang, Hao Wang, Lei Wang and Guowei WU (Dalian University of Technology, China)
Session Chair
Chi Lin (Dalian University of Technology)
Edge Computing
MoDEMS: Optimizing Edge Computing Migrations For User Mobility
Taejin Kim (Carnegie Mellon University, USA); Sandesh Dhawaskar sathyanarayana (Energy Sciences Network, Lawrence Berkeley National Laboratory & University of Colorado Boulder, USA); Siqi Chen (University of Colorado Boulder, USA); Youngbin Im (Ulsan National Institute of Science and Technology, Korea (South)); Xiaoxi Zhang (Sun Yat-sen University, China); Sangtae Ha (University of Colorado Boulder, USA); Carlee Joe-Wong (Carnegie Mellon University, USA)
Optimal Admission Control Mechanism Design for Time-Sensitive Services in Edge Computing
Shutong Chen (Huazhong University of Science and Technology, China); Lin Wang (VU Amsterdam & TU Darmstadt, The Netherlands); Fangming Liu (Huazhong University of Science and Technology, China)
To address this issue, we propose an admission control mechanism for time-sensitive edge services. Specifically, we allow the service provider to offer admission advice to arriving requests regarding whether to join for service or balk to seek alternatives. Our goal is twofold: maximizing revenue of the service provider and ensuring QoS if the provided admission advice is followed. To this end, we propose a threshold structure that estimates the highest length of the request queue. Leveraging such a threshold structure, we propose a mechanism to balance the trade-off between increasing revenue from accepting more requests and guaranteeing QoS by advising requests to balk. Rigorous analysis shows that our mechanism achieves the goal and that the provided admission advice is optimal for end-users to follow. We further validate our mechanism through trace-driven simulations with both synthetic and real-world service request traces.
Towards Online Privacy-preserving Computation Offloading in Mobile Edge Computing
Xiaoyi Pang (Wuhan University, China); Zhibo Wang (Zhejiang University, China); Jingxin Li and Ruiting Zhou (Wuhan University, China); Ju Ren (Tsinghua University, China); Zhetao Li (Xiangtan University, China)
Two Time-Scale Joint Service Caching and Task Offloading for UAV-assisted Mobile Edge Computing
Ruiting Zhou and Xiaoyi Wu (Wuhan University, China); Haisheng Tan (University of Science and Technology of China, China); Renli Zhang (Wuhan University, China)
Session Chair
Jianli Pan (University of Missouri, St. Louis)
Learning at the Edge
Decentralized Task Offloading in Edge Computing: A Multi-User Multi-Armed Bandit Approach
Xiong Wang (Huazhong University of Science and Technology, China); Jiancheng Ye (Huawei, Hong Kong); John C.S. Lui (The Chinese University of Hong Kong, Hong Kong)
Deep Learning on Mobile Devices Through Neural Processing Units and Edge Computing
Tianxiang Tan and Guohong Cao (The Pennsylvania State University, USA)
Learning-based Multi-Drone Network Edge Orchestration for Video Analytics
Chengyi Qu, Rounak Singh, Alicia Esquivel Morel and Prasad Calyam (University of Missouri-Columbia, USA)
Inefficient configurations in drone video analytics applications due to edge network misconfigurations can result in degraded video quality and inefficient resource utilization. In this paper, we present a novel scheme for offline/online learning-based network edge orchestration to achieve pertinent selection of both network protocols and video properties in multi-drone based video analytics. Our approach features both supervised and unsupervised machine learning algorithms to enable decision making for selection of both network protocols and video properties in the drones' pre-takeoff stage i.e., offline stage. In addition, our approach facilitates drone trajectory optimization during drone flights through an online reinforcement learning-based multi-agent deep Q-network algorithm. Evaluation results show how our offline orchestration can suitably choose network protocols (i.e., amongst TCP/HTTP, UDP/RTP, QUIC). We also demonstrate how our unsupervised learning approach outperforms existing learning approaches, and achieves efficient offloading while also improving the network performance (i.e., throughput and round-trip time) by least 25% with satisfactory video quality. Lastly, we show via trace-based simulations, how our online orchestration achieves 91% of oracle baseline network throughput performance with comparable video quality.
Online Model Updating with Analog Aggregation in Wireless Edge Learning
Juncheng Wang (University of Toronto, Canada); Min Dong (Ontario Tech University, Canada); Ben Liang (University of Toronto, Canada); Gary Boudreau (Ericsson, Canada); Hatem Abou-Zeid (University of Calgary, Canada)
Session Chair
Stephen Lee (University of Pittsburgh)
Mobile Applications 2
An RFID and Computer Vision Fusion System for Book Inventory using Mobile Robot
Jiuwu Zhang and Xiulong Liu (Tianjin University, China); Tao Gu (Macquarie University, Australia); Bojun Zhang (TianJin University, China); Dongdong Liu, Zijuan Liu and Keqiu Li (Tianjin University, China)
GASLA: Enhancing the Applicability of Sign Language Translation
Jiao Li, Yang Liu, Weitao Xu and Zhenjiang Li (City University of Hong Kong, Hong Kong)
Tackling Multipath and Biased Training Data for IMU-Assisted BLE Proximity Detection
Tianlang He and Jiajie Tan (The Hong Kong University of Science and Technology, China); Steve Zhuo (HKUST, Hong Kong); Maximilian Printz and S.-H. Gary Chan (The Hong Kong University of Science and Technology, China)
We propose PRID, an IMU-assisted BLE proximity detection approach robust against RSSI fluctuation and IMU data bias. PRID histogramizes RSSI to extract multipath features and uses carriage state regularization to mitigate overfitting upon IMU data bias. We further propose PRID-lite based on binarized neural network to cut memory requirement for resource-constrained devices. We have conducted extensive experiments under different multipath environments and data bias levels, and a crowdsourced dataset. Our results show that PRID reduces over 50% false detection cases compared with the existing arts. PRID-lite reduces over 90% PRID model size and extends 60% battery life, with minor compromise on accuracy (7%).
VR Viewport Pose Model for Quantifying and Exploiting Frame Correlations
Ying Chen and Hojung Kwon (Duke University, USA); Hazer Inaltekin (Macquarie University, Australia); Maria Gorlatova (Duke University, USA)
Session Chair
Chuyu Wang (Nanjing University)
QoE (New)
Adaptive Bitrate with User-level QoE Preference for Video Streaming
Xutong Zuo (Tsinghua University, China); Jiayu Yang (Beijing University of Posts and Telecommunications, China); Mowei Wang and Yong Cui (Tsinghua University, China)
Enabling QoE Support for Interactive Applications over Mobile Edge with High User Mobility
Xiaojun Shang (Stony Brook University, USA); Yaodong Huang (Shenzhen University, China); Yingling Mao, Zhenhua Liu and Yuanyuan Yang (Stony Brook University, USA)
On Uploading Behavior and Optimizations of a Mobile Live Streaming Service
Jinyang Li, Zhenyu Li and Qinghua Wu (Institute of Computing Technology, Chinese Academy of Sciences, China); Gareth Tyson (Queen Mary, University of London, United Kingdom (Great Britain))
VSiM: Improving QoE Fairness for Video Streaming in Mobile Environments
Yali Yuan (University of Goettingen, Germany); Weijun Wang (Nanjing University & University of Goettingen, China); Yuhan Wang (Göttingen University, Germany); Sripriya Adhatarao (Uni Goettingen, Germany); Bangbang Ren (National University of Defense Technology, China); Kai Zheng (Huawei Technologies, China); Xiaoming Fu (University of Goettingen, Germany)
Session Chair
Eirini Eleni Tsiropoulou (University of New Mexico)
Low Latency
Dino: A Block Transmission Protocol with Low Bandwidth Consumption and Propagation Latency
Zhenxing Hu and Zhen Xiao (Peking University, China)
Enabling Low-latency-capable Satellite-Ground Topology for Emerging LEO Satellite Networks
Yaoying Zhang, Qian Wu, Zeqi Lai and Hewu Li (Tsinghua University, China)
In this paper, we conduct a quantitative study on the impact of various satellite-ground designs on the network performance of ISTN. We identify that the high-density and high-dynamicity characteristics of emerging mega-constellations have imposed big challenges, and caused significant routing instability, low network reachability, high latency and jitter over the ISTN path. To alleviate the above challenges, we formulate the Low-latency Satellite-Ground Interconnecting (LSGI) problem, targeting at integrating the space and ground segment in the ISTN, while minimizing the maximum transmission latency and keeping routing stable. We further design algorithms to solve the LSGI problem through wisely coordinating the establishment of ground-to-satellite links among distributed ground stations. Comprehensive experiment results demonstrate that our solution can outperform related schemes with about 19% reduction of the latency and 70% reduction of the jitter on average, while sustaining the highest network reachability among them.
SPACERTC: Unleashing the Low-latency Potential of Mega-constellations for Real-Time Communications
Zeqi Lai, Weisen Liu, Qian Wu and Hewu Li (Tsinghua University, China); Jingxi Xu (Tencent, China); Jianping Wu (Tsinghua University, China)
Torp: Full-Coverage and Low-Overhead Profiling of Host-Side Latency
Xiang Chen (Zhejiang University, Peking University, and Fuzhou University, China); Hongyan Liu (Zhejiang University, China); Junyi Guo (Peking University, China); Xinyue Jiang (Zhejiang University, China); Qun Huang (Peking University, China); Dong Zhang (Fuzhou University, China); Chunming Wu and Haifeng Zhou (Zhejiang University, China)
Session Chair
Stenio Fernandes (Service Now)
Algorithms 3
Ao\(^2\)I: Minimizing Age of Outdated Information to Improve Freshness in Data Collection
Qingyu Liu, Chengzhang Li, Thomas Hou, Wenjing Lou and Jeffrey Reed (Virginia Tech, USA); Sastry Kompella (Naval Research Laboratory, USA)
CausalRD: A Causal View of Rumor Detection via Eliminating Popularity and Conformity Biases
Weifeng Zhang, Ting Zhong and Ce Li (University of Electronic Science and Technology of China, China); Kunpeng Zhang (University of Maryland, USA); Fan Zhou (University of Electronic Science and Technology of China, China)
To overcome such an issue and alleviate the bias from these two factors, we propose a rumor detection framework to learn debiased user preference and effective event representation in a causal view. We first build a graph to capture causal relationships among users, events, and their interactions. Then we apply the causal intervention to eliminate popularity and conformity biases and obtain debiased user preference representation. Finally, we leverage the power of graph neural networks to aggregate learned user representation and event features for the final event type classification. Empirical experiments conducted on two real-world datasets demonstrate the effectiveness of our proposed approach compared to several cutting-edge baselines.
Learning from Delayed Semi-Bandit Feedback under Strong Fairness Guarantees
Juaren Steiger (Queen's University, Canada); Bin Li (The Pennsylvania State University, USA); Ning Lu (Queen's University, Canada)
Optimizing Sampling for Data Freshness: Unreliable Transmissions with Random Two-way Delay
Jiayu Pan and Ahmed M Bedewy (The Ohio State University, USA); Yin Sun (Auburn University, USA); Ness B. Shroff (The Ohio State University, USA)
Session Chair
Zhangyu Guan (University at Buffalo)
Virtual Dinner Break
Poster: Machine Learning for Networking
Noise-Resilient Federated Learning: Suppressing Noisy Labels in the Local Datasets of Participants
Rahul Mishra (IIT (BHU) Varanasi, India); Hari Prabhat Gupta (Indian Institute of Technology (BHU) Varanasi, INDIA, India); Tanima Dutta (IIT (BHU) Varanasi, India)
Differentiating Losses in Wireless Networks: A Learning Approach
Yuhao Chen, Jinyao Yan and Yuan Zhang (Communication University of China, China); Karin Anna Hummel (Johannes Kepler University Linz, Austria)
Battery-less Massive Access for Simultaneous Information Transmission and Federated Learning in WPT Networks
Wanli Ni (Beijng University of Posts and Telecommunications, China); Xufeng Liu (Beijing University of Posts and Telecommunications, China); Hui Tian (Beijng University of posts and telecommunications, China)
Collaborative Learning for Large-Scale Discrete Optimal Transport under Incomplete Populational Information
Navpreet Kaur and Juntao Chen (Fordham University, USA)
Leveraging Spanning Tree to Detect Colluding Attackers in Federated Learning
Priyesh Ranjan, Federico Coro, Ashish Gupta and Sajal K. Das (Missouri University of Science and Technology, USA)
Spectrum Sharing in UAV-Assisted HetNet Based on CMB-AM Multi-Agent Deep Reinforcement Learning
Guan Wei, Bo Gao, Ke Xiong and Yang Lu (Beijing Jiaotong University, China)
Inverse Reinforcement Learning Meets Power Allocation in Multi-user Cellular Networks
Ruichen Zhang, Ke Xiong, Xingcong Tian and Yang Lu (Beijing Jiaotong University, China); Pingyi Fan (Tsinghua University, China); Khaled B. Letaief (The Hong Kong University of Science and Technology, Hong Kong)
Cyber Attacks Detection using Machine Learning in Smart Grid Systems
Sohan Gyawali (University of Texas Permian Basin, USA); Omar A Beg (The University of Texas Permian Basin, USA)
Age-Energy Efficiency in WPCNs: A Deep Reinforcement Learning Approach
Haina Zheng and Ke Xiong (Beijing Jiaotong University, China); Mengying Sun (Beijing University of Posts and Telecommunications, China); Zhangdui Zhong (Beijing Jiaotong University, China); Khaled B. Letaief (The Hong Kong University of Science and Technology, Hong Kong)
Session Chair
Xingyu Zhou (Wayne State University, USA)
Poster: Wireless Systems and IoT
Simultaneous Intra-Group Communication: Understanding the Problem Space
Jagnyashini Debadarshini and Sudipta Saha (Indian Institute of Technology Bhubaneswar, India)
Efficient Coordination among Electrical Vehicles: An IoT-Assisted Approach
Jagnyashini Debadarshini and Sudipta Saha (Indian Institute of Technology Bhubaneswar, India)
Statoeuver: State-aware Load Balancing for Network Function Virtualization
Wendi Feng and Ranzheng Cao (Beijing Information Science and Technology University, China); Zhi-Li Zhang (University of Minnesota, USA)
LoRaCoin: Towards a blockchain-based platform for managing LoRa devices
Eloi Cruz Harillo (Technical University of Catalunya, Spain); Felix Freitag (Technical University of Catalonia, Spain)
An ns3-based Energy Module for 5G mmWave Base Stations
Argha Sen (Indian Institute of Technology Kharagpur, India); Sashank Bonda (IIT Kharagpur, India); Jay Jayatheerthan (Intel Technology Pvt. Ltd., India); Sandip Chakraborty (Indian Institute of Technology Kharagpur, India)