Pub Date : 2020-11-16DOI: 10.1109/LCN48667.2020.9314840
Summera Nosheen, J. Khan
IEEE802.11 standard is continuously evolving to satisfy the increasing throughput and QoS (Quality of Service) requirements of diverse user applications. One of the advanced key features of the IEEE802.11 standard is the introduction of the DL-MU-MIMO (Downlink Multi-user Multiple Input and Multiple Output) techniques which enables a multi-antenna access point to serve multiple download users concurrently. The MAC layer of the 802.11ac protocol utilises the TXOP sharing technique to support the DL-MU-MIMO operating mode. In this paper, we propose a new TXOP sharing algorithm for the 802.11ac MAC protocol to offer high throughput and QoS for multimedia traffic. The proposed algorithm is referred to as FRA−TXOPE (Flow Rate Adaptive Transmission Opportunity Extension), enhancing our previously published FRA−TXOP algorithm. The FRA−TXOP E algorithm adaptively shares the TXOP resources with primary and secondary traffic sources by continuously monitoring different traffic source flow rates and QoS requirements. Simulation results show that the proposed algorithms significantly enhance the QoS performance of all traffic sources by improving the network throughput and channel utilisation in IEEE802.11ac WLANs.
{"title":"An Adaptive TXOP Sharing Algorithm for Multimedia Traffic in IEEE802.11ac Networks","authors":"Summera Nosheen, J. Khan","doi":"10.1109/LCN48667.2020.9314840","DOIUrl":"https://doi.org/10.1109/LCN48667.2020.9314840","url":null,"abstract":"IEEE802.11 standard is continuously evolving to satisfy the increasing throughput and QoS (Quality of Service) requirements of diverse user applications. One of the advanced key features of the IEEE802.11 standard is the introduction of the DL-MU-MIMO (Downlink Multi-user Multiple Input and Multiple Output) techniques which enables a multi-antenna access point to serve multiple download users concurrently. The MAC layer of the 802.11ac protocol utilises the TXOP sharing technique to support the DL-MU-MIMO operating mode. In this paper, we propose a new TXOP sharing algorithm for the 802.11ac MAC protocol to offer high throughput and QoS for multimedia traffic. The proposed algorithm is referred to as FRA−TXOPE (Flow Rate Adaptive Transmission Opportunity Extension), enhancing our previously published FRA−TXOP algorithm. The FRA−TXOP E algorithm adaptively shares the TXOP resources with primary and secondary traffic sources by continuously monitoring different traffic source flow rates and QoS requirements. Simulation results show that the proposed algorithms significantly enhance the QoS performance of all traffic sources by improving the network throughput and channel utilisation in IEEE802.11ac WLANs.","PeriodicalId":245782,"journal":{"name":"2020 IEEE 45th Conference on Local Computer Networks (LCN)","volume":"608 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123045832","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 : 2020-11-16DOI: 10.1109/LCN48667.2020.9314849
B. Brik, A. Ksentini
To achieve the vision of Zero Touch Management (ZSM) of network slices in 5G, it is important to monitor and predict the performances of the running network slices, or their Key Performance Indicator (KPI). KPIs are usually monitored, but also with the advance of Machine Learning (ML) techniques are predicted, aiming at proactively reacting to any service degradation of running network slices. While network- and computation-oriented KPIs can be easily monitored and predicted, service-oriented KPIs are difficult to obtain due to the privacy issue, as they disclose critical information on the performance of services. To tackle this issue, in this paper, we propose to use a new ML technique, known as Federated Learning (FL), which consists of keeping raw data where it is generated, while sending only users’ local trained models to the centralized entity for aggregation. Hence, making FL as an adequate candidate to be used for predicting slices’ service-oriented KPIs.
{"title":"On Predicting Service-oriented Network Slices Performances in 5G: A Federated Learning Approach","authors":"B. Brik, A. Ksentini","doi":"10.1109/LCN48667.2020.9314849","DOIUrl":"https://doi.org/10.1109/LCN48667.2020.9314849","url":null,"abstract":"To achieve the vision of Zero Touch Management (ZSM) of network slices in 5G, it is important to monitor and predict the performances of the running network slices, or their Key Performance Indicator (KPI). KPIs are usually monitored, but also with the advance of Machine Learning (ML) techniques are predicted, aiming at proactively reacting to any service degradation of running network slices. While network- and computation-oriented KPIs can be easily monitored and predicted, service-oriented KPIs are difficult to obtain due to the privacy issue, as they disclose critical information on the performance of services. To tackle this issue, in this paper, we propose to use a new ML technique, known as Federated Learning (FL), which consists of keeping raw data where it is generated, while sending only users’ local trained models to the centralized entity for aggregation. Hence, making FL as an adequate candidate to be used for predicting slices’ service-oriented KPIs.","PeriodicalId":245782,"journal":{"name":"2020 IEEE 45th Conference on Local Computer Networks (LCN)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116067938","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 : 2020-11-16DOI: 10.1109/LCN48667.2020.9314825
Renato Caminha Juaçaba-Neto, P. Mérindol, Fabrice Théoleyre
The Internet of Things (IoT) is expected to integrate a large number of sensors, and actuators to the Internet. Multiple concurrent applications may cohabit on top of the same IoT infrastructure, and may re-use the same data for various purpose. However, privacy represents a major concern for many IoT applications, such as in smart building and healthcare. We propose here a multi-domain IoT framework where each domain aggregates distinct data-streams to respect their privacy concerns. We argue that removing sensitive meta-data and aggregating values reported by each data-stream is sufficient to hide individual private measurements. Moreover, relying on the Named Data Networking (NDN) paradigm, we can exploit caching strategies and perform in-network processing to ensure both scalability and privacy. In this paper, we discuss the necessary mechanisms to design a scalable inter-domain, privacy aware NDN scheme.
{"title":"A Multi-Domain Framework to Enable Privacy for Aggregated IoT Streams","authors":"Renato Caminha Juaçaba-Neto, P. Mérindol, Fabrice Théoleyre","doi":"10.1109/LCN48667.2020.9314825","DOIUrl":"https://doi.org/10.1109/LCN48667.2020.9314825","url":null,"abstract":"The Internet of Things (IoT) is expected to integrate a large number of sensors, and actuators to the Internet. Multiple concurrent applications may cohabit on top of the same IoT infrastructure, and may re-use the same data for various purpose. However, privacy represents a major concern for many IoT applications, such as in smart building and healthcare. We propose here a multi-domain IoT framework where each domain aggregates distinct data-streams to respect their privacy concerns. We argue that removing sensitive meta-data and aggregating values reported by each data-stream is sufficient to hide individual private measurements. Moreover, relying on the Named Data Networking (NDN) paradigm, we can exploit caching strategies and perform in-network processing to ensure both scalability and privacy. In this paper, we discuss the necessary mechanisms to design a scalable inter-domain, privacy aware NDN scheme.","PeriodicalId":245782,"journal":{"name":"2020 IEEE 45th Conference on Local Computer Networks (LCN)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133003974","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 : 2020-11-16DOI: 10.1109/LCN48667.2020.9314846
Yu Liu, Craig A. Shue
To support remote employees, organizations often use virtual private networks (VPNs) to provide confidential and authenticated tunnels between the organization’s networks and the employees’ systems. With widespread end-to-end application-layer encryption and authentication, the cryptographic features of VPNs are often redundant. However, many organizations still rely upon VPNs. We examine the motivations and limitations associated with VPNs and find that VPNs are often used to simplify access control and filtering for enterprise services.To avoid limitations associated with VPNs, we propose an approach that allows straightforward filtering. Our approach provides evidence a remote user belongs in a network, despite the address sharing present in tools like Carrier-Grade Network Address Translation. We preserve simple access control and eliminate the need for VPN servers, redundant cryptography, and VPN packet headers overheads. The approach is incrementally deployable and provides a second factor for authenticating users and systems while minimizing performance overheads.
{"title":"Beyond the VPN: Practical Client Identity in an Internet with Widespread IP Address Sharing","authors":"Yu Liu, Craig A. Shue","doi":"10.1109/LCN48667.2020.9314846","DOIUrl":"https://doi.org/10.1109/LCN48667.2020.9314846","url":null,"abstract":"To support remote employees, organizations often use virtual private networks (VPNs) to provide confidential and authenticated tunnels between the organization’s networks and the employees’ systems. With widespread end-to-end application-layer encryption and authentication, the cryptographic features of VPNs are often redundant. However, many organizations still rely upon VPNs. We examine the motivations and limitations associated with VPNs and find that VPNs are often used to simplify access control and filtering for enterprise services.To avoid limitations associated with VPNs, we propose an approach that allows straightforward filtering. Our approach provides evidence a remote user belongs in a network, despite the address sharing present in tools like Carrier-Grade Network Address Translation. We preserve simple access control and eliminate the need for VPN servers, redundant cryptography, and VPN packet headers overheads. The approach is incrementally deployable and provides a second factor for authenticating users and systems while minimizing performance overheads.","PeriodicalId":245782,"journal":{"name":"2020 IEEE 45th Conference on Local Computer Networks (LCN)","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133461743","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 : 2020-11-16DOI: 10.1109/LCN48667.2020.9314798
Aljoscha Dietrich, Dominik Leibenger, Christoph Sorge
After over a decade of research into the privacy of smart meters, the sensitivity of an individual household’s fine-grained energy readings is undisputed. A plethora of research contributions aim at protecting the privacy of end users while at the same time providing the energy supplier (and others) with sufficient data for safe operation, billing, and also forecasting purposes. The transmission of fine-grained readings is generally considered acceptable as long as they cannot be linked to the households they originate from (i.e., anonymized readings).Martinez et al. just recently pointed out that the typical provision of aggregated readings at the end of a billing period could compromise this anonymity, as the individual readings must sum up to the respective aggregate. In this short paper, we complement their research by examining the privacy implications of published aggregates of previously anonymized energy readings:We simulate attacks on a real world data set (Smart*), particularly investigating the implications of different parameter combinations such as aggregation group sizes, considered time spans, and reading precision to gain insights into theoretic risks, e.g., from an incautious choice of parameters.
{"title":"On the Lack of Anonymity of Anonymized Smart Meter Data: An Empiric Study","authors":"Aljoscha Dietrich, Dominik Leibenger, Christoph Sorge","doi":"10.1109/LCN48667.2020.9314798","DOIUrl":"https://doi.org/10.1109/LCN48667.2020.9314798","url":null,"abstract":"After over a decade of research into the privacy of smart meters, the sensitivity of an individual household’s fine-grained energy readings is undisputed. A plethora of research contributions aim at protecting the privacy of end users while at the same time providing the energy supplier (and others) with sufficient data for safe operation, billing, and also forecasting purposes. The transmission of fine-grained readings is generally considered acceptable as long as they cannot be linked to the households they originate from (i.e., anonymized readings).Martinez et al. just recently pointed out that the typical provision of aggregated readings at the end of a billing period could compromise this anonymity, as the individual readings must sum up to the respective aggregate. In this short paper, we complement their research by examining the privacy implications of published aggregates of previously anonymized energy readings:We simulate attacks on a real world data set (Smart*), particularly investigating the implications of different parameter combinations such as aggregation group sizes, considered time spans, and reading precision to gain insights into theoretic risks, e.g., from an incautious choice of parameters.","PeriodicalId":245782,"journal":{"name":"2020 IEEE 45th Conference on Local Computer Networks (LCN)","volume":"71 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131962266","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 : 2020-11-16DOI: 10.1109/LCN48667.2020.9314769
G. Mahindre, Rasika Karkare, R. Paffenroth, A. Jayasumana
Analysis of large-scale networks is hampered by limited data as complete network measurements are expensive or impossible to collect. We present an autoencoder based technique paired with pretraining, to predict missing topology information in ultra-sparsely sampled social networks. Randomly generated variations of Barabási-Albert and power law cluster graphs are used to pretrain a Hadamard Autoencoder. Pretrained neural network is then used to infer distances in social networks where only a very small fraction of intra-node distances are available. Model is evaluated on variations of Barabási-Albert and Powerlaw cluster graphs as well as on a real-world Facebook network. Results are compared with a deterministic Low-rank Matrix Completion (LMC) method as well as an autoencoder trained on partially observed data from the test-network. Results show that pretrained autoencoder far outperforms LMC when the number of distance samples available is less than 1%, while being competitive for higher fraction of samples.
{"title":"Inference in Social Networks from Ultra-Sparse Distance Measurements via Pretrained Hadamard Autoencoders","authors":"G. Mahindre, Rasika Karkare, R. Paffenroth, A. Jayasumana","doi":"10.1109/LCN48667.2020.9314769","DOIUrl":"https://doi.org/10.1109/LCN48667.2020.9314769","url":null,"abstract":"Analysis of large-scale networks is hampered by limited data as complete network measurements are expensive or impossible to collect. We present an autoencoder based technique paired with pretraining, to predict missing topology information in ultra-sparsely sampled social networks. Randomly generated variations of Barabási-Albert and power law cluster graphs are used to pretrain a Hadamard Autoencoder. Pretrained neural network is then used to infer distances in social networks where only a very small fraction of intra-node distances are available. Model is evaluated on variations of Barabási-Albert and Powerlaw cluster graphs as well as on a real-world Facebook network. Results are compared with a deterministic Low-rank Matrix Completion (LMC) method as well as an autoencoder trained on partially observed data from the test-network. Results show that pretrained autoencoder far outperforms LMC when the number of distance samples available is less than 1%, while being competitive for higher fraction of samples.","PeriodicalId":245782,"journal":{"name":"2020 IEEE 45th Conference on Local Computer Networks (LCN)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125444429","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 : 2020-11-16DOI: 10.1109/LCN48667.2020.9314781
Amirahmad Chapnevis, Ismail Güvenç, E. Bulut
Aggregated Internet of Things (IoT) communication aims to use core network resources efficiently by providing cellular access to a group of IoT devices over the same subscriber identity. Leveraging the low data rates and long data sending intervals of IoT devices, several of the IoT devices in the same serving area of the core network are grouped together and take turns to send their data to their servers without causing overlaps in their communication. In this paper, we take this approach further and benefiting from the flexibility in data sending schedules, we aim to increase savings in cellular resources by shifting (delaying or performing earlier) the regular traffic patterns of IoT devices slightly. To this end, we consider two different traffic shifting models, namely, consistent and inconsistent shifting. We first solve the optimal aggregation of IoT devices under each model by using Integer Linear Programming (ILP). In order to avoid the high complexity of ILP solution, we then develop a heuristic based solution that runs in polynomial time. Through simulations, we show that heuristic based solution provides close to optimal results in various scenarios and shifting based aggregated communication offers more resource optimization (i.e., smaller number of bearers needed to connect all IoT devices) than the aggregated communication with no shifting.
{"title":"Traffic Shifting based Resource Optimization in Aggregated IoT Communication","authors":"Amirahmad Chapnevis, Ismail Güvenç, E. Bulut","doi":"10.1109/LCN48667.2020.9314781","DOIUrl":"https://doi.org/10.1109/LCN48667.2020.9314781","url":null,"abstract":"Aggregated Internet of Things (IoT) communication aims to use core network resources efficiently by providing cellular access to a group of IoT devices over the same subscriber identity. Leveraging the low data rates and long data sending intervals of IoT devices, several of the IoT devices in the same serving area of the core network are grouped together and take turns to send their data to their servers without causing overlaps in their communication. In this paper, we take this approach further and benefiting from the flexibility in data sending schedules, we aim to increase savings in cellular resources by shifting (delaying or performing earlier) the regular traffic patterns of IoT devices slightly. To this end, we consider two different traffic shifting models, namely, consistent and inconsistent shifting. We first solve the optimal aggregation of IoT devices under each model by using Integer Linear Programming (ILP). In order to avoid the high complexity of ILP solution, we then develop a heuristic based solution that runs in polynomial time. Through simulations, we show that heuristic based solution provides close to optimal results in various scenarios and shifting based aggregated communication offers more resource optimization (i.e., smaller number of bearers needed to connect all IoT devices) than the aggregated communication with no shifting.","PeriodicalId":245782,"journal":{"name":"2020 IEEE 45th Conference on Local Computer Networks (LCN)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116100310","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 : 2020-11-16DOI: 10.1109/LCN48667.2020.9314847
Abdulsalam Basabaa, E. Elmallah
In this work, we consider a fundamental wireless sensor network (WSN) problem where the network is deployed to guard against unauthorized traversal along a given path. Nodes are assumed to utilize energy harvesting from the ambient environment, and fluctuations in a node’s energy are assumed to affect its transmission range. In this context, we investigate a problem called the path exposure with range uncertainty (EXPO-RU) problem that asks for the likelihood that the EH-WSN can provide joint detection and reporting of the traversal. The problem models the EH-WSN using a probabilistic graph where each node is associated with multiple possible states. We present algorithms for deriving lower and upper bounds from operating and failed network configurations, respectively. We discuss properties of the presented methods, present numerical results that illustrate their usefulness, and draw remarks on the obtained numerical results.
{"title":"Bounding Path Exposure in Energy Harvesting Wireless Sensor Networks Using Pathsets and Cutsets","authors":"Abdulsalam Basabaa, E. Elmallah","doi":"10.1109/LCN48667.2020.9314847","DOIUrl":"https://doi.org/10.1109/LCN48667.2020.9314847","url":null,"abstract":"In this work, we consider a fundamental wireless sensor network (WSN) problem where the network is deployed to guard against unauthorized traversal along a given path. Nodes are assumed to utilize energy harvesting from the ambient environment, and fluctuations in a node’s energy are assumed to affect its transmission range. In this context, we investigate a problem called the path exposure with range uncertainty (EXPO-RU) problem that asks for the likelihood that the EH-WSN can provide joint detection and reporting of the traversal. The problem models the EH-WSN using a probabilistic graph where each node is associated with multiple possible states. We present algorithms for deriving lower and upper bounds from operating and failed network configurations, respectively. We discuss properties of the presented methods, present numerical results that illustrate their usefulness, and draw remarks on the obtained numerical results.","PeriodicalId":245782,"journal":{"name":"2020 IEEE 45th Conference on Local Computer Networks (LCN)","volume":"187 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126031607","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 : 2020-11-16DOI: 10.1109/LCN48667.2020.9314804
Jonathan Kua, P. Branch, G. Armitage
Dynamic Adaptive Streaming over HTTP (DASH) is a widely adopted standard for delivering high Quality of Experience (QoE) for consumer video streaming applications. The progressive deployment of Active Queue Management (AQM) schemes – such as PIE and FQ-CoDel – at ISP bottlenecks or home gateways means that consumers’ video streams are increasingly impacted by such AQM schemes. However, many existing approaches do not consider adjusting streaming strategies based on the bottleneck queue types. We have previously demonstrated the benefits of AQM schemes for DASH video streams, and proposed adaptive chunklets for an improved streaming performance. In this paper, we demonstrate the problems of queue-agnostic streaming and propose a queue-detection technique during DASH-like streaming. This entirely client-side and application-level technique is capable of detecting likely FIFO, PIE and FQ-CoDel AQM schemes at network bottlenecks.
{"title":"Detecting Bottleneck Use of PIE or FQ-CoDel Active Queue Management During DASH-like Content Streaming","authors":"Jonathan Kua, P. Branch, G. Armitage","doi":"10.1109/LCN48667.2020.9314804","DOIUrl":"https://doi.org/10.1109/LCN48667.2020.9314804","url":null,"abstract":"Dynamic Adaptive Streaming over HTTP (DASH) is a widely adopted standard for delivering high Quality of Experience (QoE) for consumer video streaming applications. The progressive deployment of Active Queue Management (AQM) schemes – such as PIE and FQ-CoDel – at ISP bottlenecks or home gateways means that consumers’ video streams are increasingly impacted by such AQM schemes. However, many existing approaches do not consider adjusting streaming strategies based on the bottleneck queue types. We have previously demonstrated the benefits of AQM schemes for DASH video streams, and proposed adaptive chunklets for an improved streaming performance. In this paper, we demonstrate the problems of queue-agnostic streaming and propose a queue-detection technique during DASH-like streaming. This entirely client-side and application-level technique is capable of detecting likely FIFO, PIE and FQ-CoDel AQM schemes at network bottlenecks.","PeriodicalId":245782,"journal":{"name":"2020 IEEE 45th Conference on Local Computer Networks (LCN)","volume":"106 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128172295","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 : 2020-11-16DOI: 10.1109/LCN48667.2020.9314839
Kashif Naveed, Hui Wu
IoT devices are becoming ubiquitous because of the advent of smart cities and vulnerable to a large number of powerful and sophisticated attacks that can potentially paralyze whole cities. There is a need to develop anomaly detection systems that can work on the same principles as the immune system to continuously learn to detect attacks that are not yet discovered. We present a dynamic framework, Celosia, that is inspired by the immune system offering good accuracy and high performance with minimal human intervention. Celosia employs a continuous learning process to detect abnormal behaviors that are yet to be discovered. It also provides a mechanism to manually define normal and anomalous entities to minimize errors. Celosia provides a layered defence and employs several agents performing their dedicated tasks. Experimental results demonstrate the power and capabilities of this framework, making it an ideal candidate for IoT devices.
{"title":"Celosia: An Immune-Inspired Anomaly Detection Framework for IoT Devices","authors":"Kashif Naveed, Hui Wu","doi":"10.1109/LCN48667.2020.9314839","DOIUrl":"https://doi.org/10.1109/LCN48667.2020.9314839","url":null,"abstract":"IoT devices are becoming ubiquitous because of the advent of smart cities and vulnerable to a large number of powerful and sophisticated attacks that can potentially paralyze whole cities. There is a need to develop anomaly detection systems that can work on the same principles as the immune system to continuously learn to detect attacks that are not yet discovered. We present a dynamic framework, Celosia, that is inspired by the immune system offering good accuracy and high performance with minimal human intervention. Celosia employs a continuous learning process to detect abnormal behaviors that are yet to be discovered. It also provides a mechanism to manually define normal and anomalous entities to minimize errors. Celosia provides a layered defence and employs several agents performing their dedicated tasks. Experimental results demonstrate the power and capabilities of this framework, making it an ideal candidate for IoT devices.","PeriodicalId":245782,"journal":{"name":"2020 IEEE 45th Conference on Local Computer Networks (LCN)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130308069","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：