Pub Date : 2020-07-01DOI: 10.1109/INFOCOMWKSHPS50562.2020.9162911
Ngombo Armando, J. Fernandes, A. Rodrigues, J. Silva, F. Boavida
As the Internet of Things (IoT) get bigger and more complex, efficient and effective management solutions must be developed and put into operation. IoT management is even more crucial if we want to have a unified management that can cope with electronic, virtual (software) and human-based sensors, which provide contextualised data via Online Social Networks (OSN). In this paper we present and explore approaches to this unified management, resorting to open and widely adopted standards for both data and device management, namely OMA - Lightweight Machine to Machine (LwM2M) and FIWARE. We present a proof-of-concept (PoC) implementation that shows that the management of the referred three types of sensing is feasible from both functional and performance points of view.
{"title":"Exploring Approaches to the Management of Physical, Virtual, and Social Sensors","authors":"Ngombo Armando, J. Fernandes, A. Rodrigues, J. Silva, F. Boavida","doi":"10.1109/INFOCOMWKSHPS50562.2020.9162911","DOIUrl":"https://doi.org/10.1109/INFOCOMWKSHPS50562.2020.9162911","url":null,"abstract":"As the Internet of Things (IoT) get bigger and more complex, efficient and effective management solutions must be developed and put into operation. IoT management is even more crucial if we want to have a unified management that can cope with electronic, virtual (software) and human-based sensors, which provide contextualised data via Online Social Networks (OSN). In this paper we present and explore approaches to this unified management, resorting to open and widely adopted standards for both data and device management, namely OMA - Lightweight Machine to Machine (LwM2M) and FIWARE. We present a proof-of-concept (PoC) implementation that shows that the management of the referred three types of sensing is feasible from both functional and performance points of view.","PeriodicalId":104136,"journal":{"name":"IEEE INFOCOM 2020 - IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131134500","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}
Pub Date : 2020-07-01DOI: 10.1109/INFOCOMWKSHPS50562.2020.9162990
Ke Lin, Siyao Cheng, Jianzhong Li
As the rapid development of smart home applications, they bring us much more convenience to operate smart lights, room heaters etc., directly. However, it is still hard for the elderly or someone with leg problems to operate the above things because the movement of them is dependent on a pair of crutches so that their hands are not always available while using crutches. Therefore, if the elderly or someone with leg problems can control the devices directly with crutches, it will become more comfortable and convenient for them to live in the smart houses. Due to such motivation, we propose iCrutch in this paper. By bidding the user's obsolescent smartphone on the currently-used crutch, iCrutch can recognize the user's actions and send controlling commands to the smart home actuators for further response. Unlike remote controllers, our iCrutch permits the user to operate without leaving his/her hands from the crutches. Meanwhile, iCrutch almost does not introduce extra cost since the obsolescent smartphone and the current crutch are made full use of. The expense of our system is noticeably reduced compared with embedding a smart system into the crutch.
{"title":"Demo Abstract: iCrutch: A Smartphone-based Intelligent Crutch for Smart Home Applications","authors":"Ke Lin, Siyao Cheng, Jianzhong Li","doi":"10.1109/INFOCOMWKSHPS50562.2020.9162990","DOIUrl":"https://doi.org/10.1109/INFOCOMWKSHPS50562.2020.9162990","url":null,"abstract":"As the rapid development of smart home applications, they bring us much more convenience to operate smart lights, room heaters etc., directly. However, it is still hard for the elderly or someone with leg problems to operate the above things because the movement of them is dependent on a pair of crutches so that their hands are not always available while using crutches. Therefore, if the elderly or someone with leg problems can control the devices directly with crutches, it will become more comfortable and convenient for them to live in the smart houses. Due to such motivation, we propose iCrutch in this paper. By bidding the user's obsolescent smartphone on the currently-used crutch, iCrutch can recognize the user's actions and send controlling commands to the smart home actuators for further response. Unlike remote controllers, our iCrutch permits the user to operate without leaving his/her hands from the crutches. Meanwhile, iCrutch almost does not introduce extra cost since the obsolescent smartphone and the current crutch are made full use of. The expense of our system is noticeably reduced compared with embedding a smart system into the crutch.","PeriodicalId":104136,"journal":{"name":"IEEE INFOCOM 2020 - IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS)","volume":"79 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134082886","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}
Pub Date : 2020-07-01DOI: 10.1109/INFOCOMWKSHPS50562.2020.9162668
S. S, V. R., M. Alazab, Soman Kp
Governments around the globe are promoting smart city applications to enhance the quality of daily-life activities in urban areas. Smart cities include internet-enabled devices that are used by applications like health care, power grid, water treatment, traffic control, etc to enhance its effectiveness. The expansion in the quantity of Internet-of-things (IoT) based botnet attacks is due to the growing trend of Internet-enabled devices. To provide advanced cyber security solutions to IoT devices and smart city applications, this paper proposes a deep learning (DL) based botnet detection system that works on network traffic flows. The botnet detection framework collects the network traffic flows, converts them into connection records and uses a DL model to detect attacks emanating from the compromised IoT devices. To determine an optimal DL model, many experiments are conducted on well-known and recently released benchmark data sets. Further, the datasets are visualized to understand its characteristics. The proposed DL model outperformed the conventional machine learning (ML) models.
{"title":"Network Flow based IoT Botnet Attack Detection using Deep Learning","authors":"S. S, V. R., M. Alazab, Soman Kp","doi":"10.1109/INFOCOMWKSHPS50562.2020.9162668","DOIUrl":"https://doi.org/10.1109/INFOCOMWKSHPS50562.2020.9162668","url":null,"abstract":"Governments around the globe are promoting smart city applications to enhance the quality of daily-life activities in urban areas. Smart cities include internet-enabled devices that are used by applications like health care, power grid, water treatment, traffic control, etc to enhance its effectiveness. The expansion in the quantity of Internet-of-things (IoT) based botnet attacks is due to the growing trend of Internet-enabled devices. To provide advanced cyber security solutions to IoT devices and smart city applications, this paper proposes a deep learning (DL) based botnet detection system that works on network traffic flows. The botnet detection framework collects the network traffic flows, converts them into connection records and uses a DL model to detect attacks emanating from the compromised IoT devices. To determine an optimal DL model, many experiments are conducted on well-known and recently released benchmark data sets. Further, the datasets are visualized to understand its characteristics. The proposed DL model outperformed the conventional machine learning (ML) models.","PeriodicalId":104136,"journal":{"name":"IEEE INFOCOM 2020 - IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133291658","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}
Pub Date : 2020-07-01DOI: 10.1109/INFOCOMWKSHPS50562.2020.9162675
Xiaoyu Zhang, Yongzhi Wang, Yu Zou
Trusted Execution Environment introduces a promising avenue for protecting MapReduce jobs on untrusted cloud environment. However existing works pointed out that simply protecting MapReduce workers with trusted execution environment and protecting cross-worker communications with encryption still leak information via cross-worker traffic volumes. Although several countermeasures were proposed to defeat such a side-channel attack, in this paper, we showed that previous countermeasures not only fail in completely eliminating such a side-channel, but also have limitations from other aspects. To address all the discovered limitations, we further discussed possible strategies.
{"title":"Reconsidering Leakage Prevention in MapReduce","authors":"Xiaoyu Zhang, Yongzhi Wang, Yu Zou","doi":"10.1109/INFOCOMWKSHPS50562.2020.9162675","DOIUrl":"https://doi.org/10.1109/INFOCOMWKSHPS50562.2020.9162675","url":null,"abstract":"Trusted Execution Environment introduces a promising avenue for protecting MapReduce jobs on untrusted cloud environment. However existing works pointed out that simply protecting MapReduce workers with trusted execution environment and protecting cross-worker communications with encryption still leak information via cross-worker traffic volumes. Although several countermeasures were proposed to defeat such a side-channel attack, in this paper, we showed that previous countermeasures not only fail in completely eliminating such a side-channel, but also have limitations from other aspects. To address all the discovered limitations, we further discussed possible strategies.","PeriodicalId":104136,"journal":{"name":"IEEE INFOCOM 2020 - IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS)","volume":"124 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131980660","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}
Pub Date : 2020-07-01DOI: 10.1109/infocomwkshps50562.2020.9162888
G. Raja, P. Dhanasekaran, S. Anbalagan, Aishwarya Ganapathisubramaniyan, A. Bashir
Intelligent Transportation System (ITS) are helping to enhance road safety and traffic management applications. Internet of Vehicles (IoV) plays a promising role in this field, which turns each vehicle into a smart object with its own compute, storage, and networking capabilities. Nowadays, accidents have been increased mainly due to un-notified alerts about other accidents, work-in-progress, and excessive motorized vehicles at peak times. This non-line of sight information can be efficiently delivered using vehicular communication. IoV network, however has its own challenges like high mobility and dynamic network topology. The above mentioned challenges are addressed with the assistance of a centralized Software Defined Network (SDN), which isolates the control plane from the data plane. In IoV, SDN provides logically centralized traffic management and improves the vehicular communication. In this paper, the Software Defined-Internet of Vehicles (SD-IoV) system is designed to manage heavy traffic and avoids broadcast storm problem with high packet delivery ratio. The proposed broadcast routing mechanism uses selective forwarding and neighbor awareness of the vehicle to efficiently broadcast emergency alert messages, thereby avoiding traffic jams and reducing travel time. On-Board Unit (OBU) in vehicles detects the accident and initializes the broadcast algorithm in SD-IoV system. The accident detection by OBU in vehicles is simulated using machine learning technique with an accuracy of 90%. Simulation performed in SUMO and OMNeT++ shows that with the help of the SDN controller, the IoV network achieves a high packet delivery ratio with minimal delay.
{"title":"SDN-enabled Traffic Alert System for IoV in Smart Cities","authors":"G. Raja, P. Dhanasekaran, S. Anbalagan, Aishwarya Ganapathisubramaniyan, A. Bashir","doi":"10.1109/infocomwkshps50562.2020.9162888","DOIUrl":"https://doi.org/10.1109/infocomwkshps50562.2020.9162888","url":null,"abstract":"Intelligent Transportation System (ITS) are helping to enhance road safety and traffic management applications. Internet of Vehicles (IoV) plays a promising role in this field, which turns each vehicle into a smart object with its own compute, storage, and networking capabilities. Nowadays, accidents have been increased mainly due to un-notified alerts about other accidents, work-in-progress, and excessive motorized vehicles at peak times. This non-line of sight information can be efficiently delivered using vehicular communication. IoV network, however has its own challenges like high mobility and dynamic network topology. The above mentioned challenges are addressed with the assistance of a centralized Software Defined Network (SDN), which isolates the control plane from the data plane. In IoV, SDN provides logically centralized traffic management and improves the vehicular communication. In this paper, the Software Defined-Internet of Vehicles (SD-IoV) system is designed to manage heavy traffic and avoids broadcast storm problem with high packet delivery ratio. The proposed broadcast routing mechanism uses selective forwarding and neighbor awareness of the vehicle to efficiently broadcast emergency alert messages, thereby avoiding traffic jams and reducing travel time. On-Board Unit (OBU) in vehicles detects the accident and initializes the broadcast algorithm in SD-IoV system. The accident detection by OBU in vehicles is simulated using machine learning technique with an accuracy of 90%. Simulation performed in SUMO and OMNeT++ shows that with the help of the SDN controller, the IoV network achieves a high packet delivery ratio with minimal delay.","PeriodicalId":104136,"journal":{"name":"IEEE INFOCOM 2020 - IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS)","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132500513","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}
Pub Date : 2020-07-01DOI: 10.1109/INFOCOMWKSHPS50562.2020.9162721
Gauravdeep Shami, M. Lyonnais, Rodney G. Wilson
High bandwidth, low latency modern-day applications are extremely sensitive to variations in network parameters. In-band Network Telemetry (INT) can help in extracting forwarding plane dynamics of the network element and characterize the service path to make preemptive service modifications. In this demonstration, we showcase a programmable telemetry framework via FPGA based NICs installed in e-science Data Transfer Nodes (DTN) operating over Ciena's Research Network Innovation Platform (CENI). We demonstrate the benefits of this framework in accelerating fault localization mechanisms and implementing corrective actions, in a closed loop with Software Defined Network (SDN) Orchestrators.
{"title":"Real Time Adaptive Networking using Programmable 100Gbps NIC on Data Transfer Nodes","authors":"Gauravdeep Shami, M. Lyonnais, Rodney G. Wilson","doi":"10.1109/INFOCOMWKSHPS50562.2020.9162721","DOIUrl":"https://doi.org/10.1109/INFOCOMWKSHPS50562.2020.9162721","url":null,"abstract":"High bandwidth, low latency modern-day applications are extremely sensitive to variations in network parameters. In-band Network Telemetry (INT) can help in extracting forwarding plane dynamics of the network element and characterize the service path to make preemptive service modifications. In this demonstration, we showcase a programmable telemetry framework via FPGA based NICs installed in e-science Data Transfer Nodes (DTN) operating over Ciena's Research Network Innovation Platform (CENI). We demonstrate the benefits of this framework in accelerating fault localization mechanisms and implementing corrective actions, in a closed loop with Software Defined Network (SDN) Orchestrators.","PeriodicalId":104136,"journal":{"name":"IEEE INFOCOM 2020 - IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114213212","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}
Pub Date : 2020-07-01DOI: 10.1109/INFOCOMWKSHPS50562.2020.9162863
Weifeng Sun, Guanghao Zhang, Yuankui Zhang, Chi Lin
Radio access technology (RAT) is used to choose the best target network during the network access or network handover. It could be used for the rescuing scenario in the wireless multi-hop networks. Most researches about RAT selection focus on heterogeneous cell networks, which are single-hop networks. The radio access selection method for cell networks is no longer suitable for heterogeneous wireless multi-hop network (HWMN), because the communicating quality of the expected access point (EAP) could not reflect the whole network capability due to the multi-hop characteristics. This paper presents a novel metric, named n-hop prediction (NHP), for radio access selection in HWMN. NHP takes network capability and load within n-hop range of the expected access point into account, and also it takes users' QoS requirement into account. Simulation results reveal that the proposed approach can achieve better performance than that without considering these factors.
{"title":"RAT-NHP: Radio Access Technology Selection Based on N-hop Prediction","authors":"Weifeng Sun, Guanghao Zhang, Yuankui Zhang, Chi Lin","doi":"10.1109/INFOCOMWKSHPS50562.2020.9162863","DOIUrl":"https://doi.org/10.1109/INFOCOMWKSHPS50562.2020.9162863","url":null,"abstract":"Radio access technology (RAT) is used to choose the best target network during the network access or network handover. It could be used for the rescuing scenario in the wireless multi-hop networks. Most researches about RAT selection focus on heterogeneous cell networks, which are single-hop networks. The radio access selection method for cell networks is no longer suitable for heterogeneous wireless multi-hop network (HWMN), because the communicating quality of the expected access point (EAP) could not reflect the whole network capability due to the multi-hop characteristics. This paper presents a novel metric, named n-hop prediction (NHP), for radio access selection in HWMN. NHP takes network capability and load within n-hop range of the expected access point into account, and also it takes users' QoS requirement into account. Simulation results reveal that the proposed approach can achieve better performance than that without considering these factors.","PeriodicalId":104136,"journal":{"name":"IEEE INFOCOM 2020 - IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133584185","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}
Pub Date : 2020-07-01DOI: 10.1109/infocomwkshps50562.2020.9162939
Yan Sun, Lihua Yin, Zhe Sun, Zhihong Tian, Xiaojiang Du
The massive data collection, transmission, storage and processing in IoT are challenging to the cloud computing environment. Aiming at the problem of data sharing and privacy protection of IoT, this paper designed an IoT data sharing model that is based on the edge computing service. The model establishes the virtual data management service by the data abstraction in the edge service layer to provide data service for IoT devices, and further proposed a privacy preserving scheme for data sharing based on attribute encryption. The scheme realized anonymous data sharing and access control and finally is proved to be secure and has a good performance.
{"title":"An IoT data sharing privacy preserving scheme","authors":"Yan Sun, Lihua Yin, Zhe Sun, Zhihong Tian, Xiaojiang Du","doi":"10.1109/infocomwkshps50562.2020.9162939","DOIUrl":"https://doi.org/10.1109/infocomwkshps50562.2020.9162939","url":null,"abstract":"The massive data collection, transmission, storage and processing in IoT are challenging to the cloud computing environment. Aiming at the problem of data sharing and privacy protection of IoT, this paper designed an IoT data sharing model that is based on the edge computing service. The model establishes the virtual data management service by the data abstraction in the edge service layer to provide data service for IoT devices, and further proposed a privacy preserving scheme for data sharing based on attribute encryption. The scheme realized anonymous data sharing and access control and finally is proved to be secure and has a good performance.","PeriodicalId":104136,"journal":{"name":"IEEE INFOCOM 2020 - IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133932833","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}
Pub Date : 2020-07-01DOI: 10.1109/infocomwkshps50562.2020.9163058
Sheng Wang, Linning Peng, Hua Fu, A. Hu, Xinyu Zhou
Global system for mobile communications (GSM) is one of the most widely used communication standards in the world today, which still has a large number of users, so it is of great security significance to identify devices operating in a GSM network. This paper proposes a novel radio frequency fingerprinting (RFF) based device identifications method for mobile phones. A differential constellation trace figure (DCTF) physical layer RFF extraction and convolutional neural network (CNN) based classification scheme is designed to identify accessing mobile phones. Theoretical analysis shows that differential process of GSM signal can effectively reflect the characteristics of RFF from different phones. Compared with the existing RFF identification methods, CNN based classification can identify the DCTF of different devices with low complexity and high accuracy. Furthermore, the proposed DCTF-CNN method is robust to different device locations and GSM parameters. Experimental results show that the accuracy of the proposed DCTF-CNN method can reach 92.97% and 99.77% with SNR at 25 dB and 50 dB for 6 mobile phones.
GSM (Global system for mobile communications，全球移动通信系统)是当今世界上使用最广泛的通信标准之一，它仍然拥有大量的用户，因此识别在GSM网络中运行的设备具有重要的安全意义。提出了一种基于射频指纹技术的手机设备识别方法。设计了一种基于差分星座轨迹图(DCTF)物理层RFF提取和卷积神经网络(CNN)的手机识别方法。理论分析表明，GSM信号的差分处理可以有效地反映不同手机的RFF特征。与现有的RFF识别方法相比，基于CNN的分类可以识别不同设备的DCTF，且复杂度低，准确率高。此外，所提出的DCTF-CNN方法对不同的设备位置和GSM参数具有鲁棒性。实验结果表明，本文提出的DCTF-CNN方法在25 dB和50 dB信噪比下的准确率分别达到92.97%和99.77%，适用于6部手机。
{"title":"A Convolutional Neural Network-Based RF Fingerprinting Identification Scheme for Mobile Phones","authors":"Sheng Wang, Linning Peng, Hua Fu, A. Hu, Xinyu Zhou","doi":"10.1109/infocomwkshps50562.2020.9163058","DOIUrl":"https://doi.org/10.1109/infocomwkshps50562.2020.9163058","url":null,"abstract":"Global system for mobile communications (GSM) is one of the most widely used communication standards in the world today, which still has a large number of users, so it is of great security significance to identify devices operating in a GSM network. This paper proposes a novel radio frequency fingerprinting (RFF) based device identifications method for mobile phones. A differential constellation trace figure (DCTF) physical layer RFF extraction and convolutional neural network (CNN) based classification scheme is designed to identify accessing mobile phones. Theoretical analysis shows that differential process of GSM signal can effectively reflect the characteristics of RFF from different phones. Compared with the existing RFF identification methods, CNN based classification can identify the DCTF of different devices with low complexity and high accuracy. Furthermore, the proposed DCTF-CNN method is robust to different device locations and GSM parameters. Experimental results show that the accuracy of the proposed DCTF-CNN method can reach 92.97% and 99.77% with SNR at 25 dB and 50 dB for 6 mobile phones.","PeriodicalId":104136,"journal":{"name":"IEEE INFOCOM 2020 - IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129370354","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}
Pub Date : 2020-07-01DOI: 10.1109/INFOCOMWKSHPS50562.2020.9162704
Cedric Beliard, A. Finamore, Dario Rossi
Fostered by the tremendous success in the image recognition field, recently there has been a strong push for the adoption of Convolutional Neural Networks (CNN) in networks, especially at the edge, assisted by low-power hardware equipment (known as “tensor processing units”) for the acceleration of CNN-related computations. The availability of such hardware has reignited the interest for traffic classification approaches that are based on Deep Learning. However, unlike tree-based approaches that are easy to interpret, CNNs are in essence represented by a large number of weights, whose interpretation is particularly obscure for the human operators. Since human operators will need to deal, troubleshoot, and maintain these automatically learned models, that will replace the more easily human-readable heuristic rules of DPI classification engine, there is a clear need to open the “deep pandora box”, and make it easily accessible for network domain experts. In this demonstration, we shed light in the inference process of a commercial-grade classification engine dealing with hundreds of classes, enriching the classification workflow with tools to enable better understanding of the inner mechanics of both the traffic and the models.
{"title":"Opening the Deep Pandora Box: Explainable Traffic Classification","authors":"Cedric Beliard, A. Finamore, Dario Rossi","doi":"10.1109/INFOCOMWKSHPS50562.2020.9162704","DOIUrl":"https://doi.org/10.1109/INFOCOMWKSHPS50562.2020.9162704","url":null,"abstract":"Fostered by the tremendous success in the image recognition field, recently there has been a strong push for the adoption of Convolutional Neural Networks (CNN) in networks, especially at the edge, assisted by low-power hardware equipment (known as “tensor processing units”) for the acceleration of CNN-related computations. The availability of such hardware has reignited the interest for traffic classification approaches that are based on Deep Learning. However, unlike tree-based approaches that are easy to interpret, CNNs are in essence represented by a large number of weights, whose interpretation is particularly obscure for the human operators. Since human operators will need to deal, troubleshoot, and maintain these automatically learned models, that will replace the more easily human-readable heuristic rules of DPI classification engine, there is a clear need to open the “deep pandora box”, and make it easily accessible for network domain experts. In this demonstration, we shed light in the inference process of a commercial-grade classification engine dealing with hundreds of classes, enriching the classification workflow with tools to enable better understanding of the inner mechanics of both the traffic and the models.","PeriodicalId":104136,"journal":{"name":"IEEE INFOCOM 2020 - IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116082257","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：