D. Zhang, Yue Ma, Chao Zheng, Yang Zhang, X. Hu, Dong Wang
{"title":"Cooperative-Competitive Task Allocation in Edge Computing for Delay-Sensitive Social Sensing","authors":"D. Zhang, Yue Ma, Chao Zheng, Yang Zhang, X. Hu, Dong Wang","doi":"10.1109/SEC.2018.00025","DOIUrl":"https://doi.org/10.1109/SEC.2018.00025","url":null,"abstract":"With the ever-increasing data processing capabilities of edge computing devices and the growing acceptance of running social sensing applications on such cloud-edge systems, effectively allocating processing tasks between the server and the edge devices has emerged as a critical undertaking for maximizing the performance of such systems. Task allocation in such an environment faces several unique challenges: (i) the objectives of applications and edge devices may be inconsistent or even conflicting with each other, and (ii) edge devices may only be partially collaborative in finishing the computation tasks due to the \"rational actor\" nature and trust constraints of these devices, and (iii) an edge device's availability to participate in computation can change over time and the application is often unaware of such availability dynamics. Many social sensing applications are also delay-sensitive, which further exacerbates the problem. To overcome these challenges, this paper introduces a novel game-theoretic task allocation framework. The framework includes a dynamic feedback incentive mechanism, a decentralized fictitious play with a new negotiation scheme, and a judiciously-designed private payoff function. The proposed framework was implemented on a testbed that consists of heterogeneous edge devices (Jetson TX1, TK1, Raspberry Pi3) and Amazon elastic cloud. Evaluations based on two real-world social sensing applications show that the new framework can well satisfy real-time Quality-of-Service requirements of the applications and provide much higher payoffs to edge devices compared to the state-of-the-arts.","PeriodicalId":376439,"journal":{"name":"2018 IEEE/ACM Symposium on Edge Computing (SEC)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132143078","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Learning from Differentially Private Neural Activations with Edge Computing","authors":"Yunlong Mao, Shanhe Yi, Qun A. Li, Jinghao Feng, Fengyuan Xu, Sheng Zhong","doi":"10.1109/SEC.2018.00014","DOIUrl":"https://doi.org/10.1109/SEC.2018.00014","url":null,"abstract":"Deep convolutional neural networks (DNNs) have brought significant performance improvements to face recognition. However the training can hardly be carried out on mobile devices because the training of these models requires much computational power. An individual user with the demand of deriving DNN models from her own datasets usually has to outsource the training procedure onto an edge server. However this outsourcing method violates privacy because it exposes the users' data to curious service providers. In this paper, we utilize the differentially private mechanism to enable the privacy-preserving edge based training of DNN face recognition models. During the training, DNN is split between the user device and the edge server in a way that both private data and model parameters are protected, with only a small cost of local computations. We rigorously prove that our approach is privacy preserving. We finally show that our mechanism is capable of training models in different scenarios, e.g., from scratch, or through fine-tuning over existed models.","PeriodicalId":376439,"journal":{"name":"2018 IEEE/ACM Symposium on Edge Computing (SEC)","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126776704","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Defending Internet of Things Against Malicious Domain Names using D-FENS","authors":"Jeffrey Spaulding, Aziz Mohaisen","doi":"10.1109/SEC.2018.00051","DOIUrl":"https://doi.org/10.1109/SEC.2018.00051","url":null,"abstract":"Malicious domain names have long been pervasive in the global DNS (Domain Name System) infrastructure and lend themselves to undesirable activities such as phishing or even DNS-based attacks like distributed denial-of-service (DDoS) and DNS rebinding. With the rise and explosive growth of the Internet of Things (IoT), adversaries are exploiting these devices which typically lack security measures to launch DNS-based attacks through malicious domain names. Typical countermeasures against such malicious domain names employ blacklists and whitelists to determine which domain names should be resolved. While these domain lists offer fast lookup times, they require carefully curated and up-to-date information which tends to fall short of detecting newly-registered malicious domain names. In this work, we present a system called D-FENS (DNS Filtering & Extraction Network System) which works in tandem with blacklists and features a live DNS server and binary classifier to accurately predict unreported malicious domain names. The D-FENS classifier model operates at the character-level and leverages the use of deep learning architectures such as Convolutional Neural Networks (CNN) and Long Short-Term Memory networks (LSTM) for real-time classification which forgoes the need for feature-engineering typically associated with traditional machine learning approaches. Sourcing from free and open datasets, we evaluate our system and achieve a 0.95 area under the receiver operating characteristic curve for binary classification. By accurately predicting unreported malicious domain names in real-time, D-FENS prevents Internet-connected systems from unknowingly connecting to potentially malicious domain names.","PeriodicalId":376439,"journal":{"name":"2018 IEEE/ACM Symposium on Edge Computing (SEC)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116783246","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Chien-Chun Hung, G. Ananthanarayanan, P. Bodík, L. Golubchik, Minlan Yu, P. Bahl, Matthai Philipose
{"title":"VideoEdge: Processing Camera Streams using Hierarchical Clusters","authors":"Chien-Chun Hung, G. Ananthanarayanan, P. Bodík, L. Golubchik, Minlan Yu, P. Bahl, Matthai Philipose","doi":"10.1109/SEC.2018.00016","DOIUrl":"https://doi.org/10.1109/SEC.2018.00016","url":null,"abstract":"Organizations deploy a hierarchy of clusters - cameras, private clusters, public clouds - for analyzing live video feeds from their cameras. Video analytics queries have many implementation options which impact their resource demands and accuracy of outputs. Our objective is to select the \"query plan\" - implementations (and their knobs) - and place it across the hierarchy of clusters, and merge common components across queries to maximize the average query accuracy. This is a challenging task, because we have to consider multi-resource (network and compute) demands and constraints in the hierarchical cluster and search in an exponentially large search space for plans, placements, and merging. We propose VideoEdge, a system that introduces dominant demand to identify the best tradeoff between multiple resources and accuracy, and narrows the search space by identifying a \"Pareto band\" of promising configurations. VideoEdge also balances the resource benefits and accuracy penalty of merging queries. Deployment results show that VideoEdge improves accuracy by 25:4 and 5:4 compared to fair allocation of resources and a recent solution for video query planning (VideoStorm), respectively, and is within 6% of optimum.","PeriodicalId":376439,"journal":{"name":"2018 IEEE/ACM Symposium on Edge Computing (SEC)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126988468","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号
