Mingyuan Zang, Changgang Zheng, Radostin Stoyanov, L. Dittmann, Noa Zilberman
IoT gateways are vital to the scalability and security of IoT networks. As more devices connect to the network, traditional hard-coded gateways fail to flexibly process diverse IoT traffic from highly dynamic devices. This calls for a more advanced analysis solution. In this work, we present P4Pir, an in-network traffic analysis solution for IoT gateways. It utilizes programmable data planes for in-band traffic learning with self-driven machine learning model updates. Preliminary results show that P4Pir can accurately detect emerging attacks based on retraining and updating the machine learning model.
{"title":"P4Pir: in-network analysis for smart IoT gateways","authors":"Mingyuan Zang, Changgang Zheng, Radostin Stoyanov, L. Dittmann, Noa Zilberman","doi":"10.1145/3546037.3546060","DOIUrl":"https://doi.org/10.1145/3546037.3546060","url":null,"abstract":"IoT gateways are vital to the scalability and security of IoT networks. As more devices connect to the network, traditional hard-coded gateways fail to flexibly process diverse IoT traffic from highly dynamic devices. This calls for a more advanced analysis solution. In this work, we present P4Pir, an in-network traffic analysis solution for IoT gateways. It utilizes programmable data planes for in-band traffic learning with self-driven machine learning model updates. Preliminary results show that P4Pir can accurately detect emerging attacks based on retraining and updating the machine learning model.","PeriodicalId":351682,"journal":{"name":"Proceedings of the SIGCOMM '22 Poster and Demo Sessions","volume":"60 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125473113","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}
Zhongzheng Lai, Dong Yuan, Wei Bao, Yu Zhang, B. Zhou
Deep learning (DL) has been used for wireless signal analysis in many applications, e.g., indoor localization. By collecting measurement data of wireless signals from the environment, DL models can be trained to accurately predict the change of signal characteristics. However, constructing high-quality DL training data from a real experiment environment is often labor-intensive and time-consuming, which is the biggest obstacle to applying the newest DL model to wireless network research. To address such issues, we present DeepWiSim, a ray-tracing-based wireless signal simulator that automates the DL process from data generation to model training and evaluation. The demonstration shows that DeepWiSim can efficiently generate high-quality simulated wireless signal measurement data and simultaneously train and evaluate the DL model.
{"title":"DeepWiSim","authors":"Zhongzheng Lai, Dong Yuan, Wei Bao, Yu Zhang, B. Zhou","doi":"10.1145/3546037.3546049","DOIUrl":"https://doi.org/10.1145/3546037.3546049","url":null,"abstract":"Deep learning (DL) has been used for wireless signal analysis in many applications, e.g., indoor localization. By collecting measurement data of wireless signals from the environment, DL models can be trained to accurately predict the change of signal characteristics. However, constructing high-quality DL training data from a real experiment environment is often labor-intensive and time-consuming, which is the biggest obstacle to applying the newest DL model to wireless network research. To address such issues, we present DeepWiSim, a ray-tracing-based wireless signal simulator that automates the DL process from data generation to model training and evaluation. The demonstration shows that DeepWiSim can efficiently generate high-quality simulated wireless signal measurement data and simultaneously train and evaluate the DL model.","PeriodicalId":351682,"journal":{"name":"Proceedings of the SIGCOMM '22 Poster and Demo Sessions","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122068956","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}
Zhipeng Zhao, Nirav Atre, Hugo Sadok, Siddharth Sahay, Shashank Obla, J. Hoe, Justine Sherry
Intrusion Detection and Prevention Systems (IDS/IPSes) are critical components of the service chain for many network deployments. Ever-increasing network line rates and security threats have imposed substantial performance and correctness requirements on these systems: 100Gbps+ throughput with 100K+ concurrent connections, while scanning for 10K+ attack signatures in every packet.
{"title":"Pigasus 2.0: making the pigasus IDS robust to attacks and different workloads","authors":"Zhipeng Zhao, Nirav Atre, Hugo Sadok, Siddharth Sahay, Shashank Obla, J. Hoe, Justine Sherry","doi":"10.1145/3546037.3546065","DOIUrl":"https://doi.org/10.1145/3546037.3546065","url":null,"abstract":"Intrusion Detection and Prevention Systems (IDS/IPSes) are critical components of the service chain for many network deployments. Ever-increasing network line rates and security threats have imposed substantial performance and correctness requirements on these systems: 100Gbps+ throughput with 100K+ concurrent connections, while scanning for 10K+ attack signatures in every packet.","PeriodicalId":351682,"journal":{"name":"Proceedings of the SIGCOMM '22 Poster and Demo Sessions","volume":"258 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116817736","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}
Run Huang, Mengying Zhou, Tiancheng Guo, Yang Chen
Determining the physical locations of CDN Points of Presence (PoPs) is fundamental to understanding and diagnosing CDN services. Yet, the popular deployment of IP Anycast in CDNs has rendered existing geolocation tools unreliable. To fill this gap, we present an HTTP-based solution that leverages subtle geographic hints in HTTP responses to locate CDN PoPs at the city-level granularity. The evaluation shows that our technique achieves over 90% accuracy with an average error distance of less than 40 km.
{"title":"Locating CDN edge servers with HTTP responses","authors":"Run Huang, Mengying Zhou, Tiancheng Guo, Yang Chen","doi":"10.1145/3546037.3546051","DOIUrl":"https://doi.org/10.1145/3546037.3546051","url":null,"abstract":"Determining the physical locations of CDN Points of Presence (PoPs) is fundamental to understanding and diagnosing CDN services. Yet, the popular deployment of IP Anycast in CDNs has rendered existing geolocation tools unreliable. To fill this gap, we present an HTTP-based solution that leverages subtle geographic hints in HTTP responses to locate CDN PoPs at the city-level granularity. The evaluation shows that our technique achieves over 90% accuracy with an average error distance of less than 40 km.","PeriodicalId":351682,"journal":{"name":"Proceedings of the SIGCOMM '22 Poster and Demo Sessions","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124241363","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}
We present a new Kubernetes architecture that leverages in-network caching to accelerate one of Kubernetes' core components, its key-value store. We also identify performance limitations of previous in-network caching platforms and propose a new platform that demonstrates better throughput and scalability by utilising a different replication method.
{"title":"Accelerating kubernetes with in-network caching","authors":"Stefanos G. Sagkriotis, D. Pezaros","doi":"10.1145/3546037.3546058","DOIUrl":"https://doi.org/10.1145/3546037.3546058","url":null,"abstract":"We present a new Kubernetes architecture that leverages in-network caching to accelerate one of Kubernetes' core components, its key-value store. We also identify performance limitations of previous in-network caching platforms and propose a new platform that demonstrates better throughput and scalability by utilising a different replication method.","PeriodicalId":351682,"journal":{"name":"Proceedings of the SIGCOMM '22 Poster and Demo Sessions","volume":"121 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115567687","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}
MAC addresses can be collected by passive observers to track Wi-Fi users. While address randomization neutralizes this threat for devices not yet associated, the problem remains for devices being associated with a WLAN. In this paper, we introduce RoMA, which is an anti-tracking scheme making use of concurrent virtual network interfaces (VIFs). We provide a proof-of-concept implementation of RoMA and show that it has a limited impact on the performance of the devices.
{"title":"RoMA: rotating MAC address for privacy protection","authors":"Johann Hugon, M. Cunche, Thomas Begin","doi":"10.1145/3546037.3546055","DOIUrl":"https://doi.org/10.1145/3546037.3546055","url":null,"abstract":"MAC addresses can be collected by passive observers to track Wi-Fi users. While address randomization neutralizes this threat for devices not yet associated, the problem remains for devices being associated with a WLAN. In this paper, we introduce RoMA, which is an anti-tracking scheme making use of concurrent virtual network interfaces (VIFs). We provide a proof-of-concept implementation of RoMA and show that it has a limited impact on the performance of the devices.","PeriodicalId":351682,"journal":{"name":"Proceedings of the SIGCOMM '22 Poster and Demo Sessions","volume":"129 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114470921","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}
The small cell size, wide bandwidth, and MIMO antenna arrays in 5G mmWave networks provide great opportunities for IoT localization. However, low-power and low-cost IoT devices are incapable of leveraging these benefits. We present mm-ISLA: a system that enables IoT nodes to localize themselves using ambient 5G mmWave signals without any coordination with the base stations. mm-ISLA leverages MEMS Spike-Train filters to access the wideband 5G signals and estimates the Angle of Departure from the base station MIMO antenna arrays to accurately localize the IoT nodes.
{"title":"Enabling IoT self-localization using ambient 5G mmWave signals","authors":"Junfeng Guan, Suraj Jog, Sohrab Madani, Ruochen Lu, S. Gong, Deepak Vasisht, Haitham Hassanieh","doi":"10.1145/3546037.3546061","DOIUrl":"https://doi.org/10.1145/3546037.3546061","url":null,"abstract":"The small cell size, wide bandwidth, and MIMO antenna arrays in 5G mmWave networks provide great opportunities for IoT localization. However, low-power and low-cost IoT devices are incapable of leveraging these benefits. We present mm-ISLA: a system that enables IoT nodes to localize themselves using ambient 5G mmWave signals without any coordination with the base stations. mm-ISLA leverages MEMS Spike-Train filters to access the wideband 5G signals and estimates the Angle of Departure from the base station MIMO antenna arrays to accurately localize the IoT nodes.","PeriodicalId":351682,"journal":{"name":"Proceedings of the SIGCOMM '22 Poster and Demo Sessions","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114354435","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":"FoReCo","authors":"M. Groshev, Javier Sacido, J. Martín-Pérez","doi":"10.1145/3546037.3546047","DOIUrl":"https://doi.org/10.1145/3546037.3546047","url":null,"abstract":"","PeriodicalId":351682,"journal":{"name":"Proceedings of the SIGCOMM '22 Poster and Demo Sessions","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133149487","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}
Core-stateless resource sharing solutions implemented in P4 hardware data planes have been proposed in the past few years. They share the idea of tagging packets with special values at the network edge that are then solely used for deciding how to handle packets in the network in case of congestion. Though the scheduler of our Core-Stateless Active Queue management (CSAQM) was implemented in P4 and was evaluated on Intel Tofino ASIC, the packet marker have only had a DPDK-based software implementation so far. In this demo, we present the full data plane implementation of CSAQM. Both packet marking and packet scheduling are executed by an Intel Tofino ASIC. We demonstrate the scalability of our implementation by showing policy enforcement among up to 35000 subscribers at a 100 Gbps bottleneck using only a single queue. In addition, we also present the resource sharing and isolation properties of CSAQM between flows with different rate control strategies, resulting in flow-specific congestion signals (drop probabilities) by design.
{"title":"Resource sharing beyond FQ: 35K users at 100Gbps","authors":"Dávid Kis, G. Gombos, S. Laki, S. Nádas","doi":"10.1145/3546037.3546045","DOIUrl":"https://doi.org/10.1145/3546037.3546045","url":null,"abstract":"Core-stateless resource sharing solutions implemented in P4 hardware data planes have been proposed in the past few years. They share the idea of tagging packets with special values at the network edge that are then solely used for deciding how to handle packets in the network in case of congestion. Though the scheduler of our Core-Stateless Active Queue management (CSAQM) was implemented in P4 and was evaluated on Intel Tofino ASIC, the packet marker have only had a DPDK-based software implementation so far. In this demo, we present the full data plane implementation of CSAQM. Both packet marking and packet scheduling are executed by an Intel Tofino ASIC. We demonstrate the scalability of our implementation by showing policy enforcement among up to 35000 subscribers at a 100 Gbps bottleneck using only a single queue. In addition, we also present the resource sharing and isolation properties of CSAQM between flows with different rate control strategies, resulting in flow-specific congestion signals (drop probabilities) by design.","PeriodicalId":351682,"journal":{"name":"Proceedings of the SIGCOMM '22 Poster and Demo Sessions","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128778897","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}
G. Bartolomeo, Simon Bäurle, Nitinder Mohan, Jörg Ott
Edge computing enables developers to deploy their services on compute resources deployed closer to the users. The abstraction requires powerful orchestration capabilities and the resolution of complex optimization problems. While edge computing is a consistently growing trend, the community (research and industry) still largely embraces adaptations and extensions of existing cloud technologies that have been proven ineffective on edge (e.g. Kubernetes). In this work, we present Oakestra, a novel hierarchical orchestration framework specifically designed for supporting service operation over heterogeneous edge infrastructures. In this demonstration, we showcase the various features and operations of Oakestra using our latency-critical augmented reality (AR) application.
{"title":"Oakestra","authors":"G. Bartolomeo, Simon Bäurle, Nitinder Mohan, Jörg Ott","doi":"10.1145/3546037.3546056","DOIUrl":"https://doi.org/10.1145/3546037.3546056","url":null,"abstract":"Edge computing enables developers to deploy their services on compute resources deployed closer to the users. The abstraction requires powerful orchestration capabilities and the resolution of complex optimization problems. While edge computing is a consistently growing trend, the community (research and industry) still largely embraces adaptations and extensions of existing cloud technologies that have been proven ineffective on edge (e.g. Kubernetes). In this work, we present Oakestra, a novel hierarchical orchestration framework specifically designed for supporting service operation over heterogeneous edge infrastructures. In this demonstration, we showcase the various features and operations of Oakestra using our latency-critical augmented reality (AR) application.","PeriodicalId":351682,"journal":{"name":"Proceedings of the SIGCOMM '22 Poster and Demo Sessions","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114081221","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：