Masaki Hara, Shinnosuke Nirasawa, A. Nakao, M. Oguchi, Shu Yamamoto, Saneyasu Yamaguchi
{"title":"Service Identification by Packet Inspection Based on N-grams in Multiple Connections","authors":"Masaki Hara, Shinnosuke Nirasawa, A. Nakao, M. Oguchi, Shu Yamamoto, Saneyasu Yamaguchi","doi":"10.1109/CANDAR.2016.0123","DOIUrl":null,"url":null,"abstract":"Identifying the service of traffic by given IP network flows is essential for various purposes, such as management of QoS and avoiding security issues. Typical methods for this are identification based on its IP addresses and port numbers. However, the achieved accuracies of these method are not sufficient, then improving these methods is required. Deep Packet Inspection (DPI) is one of the most effective methods for improving accuracy of identification. In this paper, we explore a method for identifying the service of flow. We propose an identifying method based on DPI which covers multiple connections in a service. Then, we present performance evaluation and demonstrate that our method can suitably identify service from given network flows.","PeriodicalId":322499,"journal":{"name":"2016 Fourth International Symposium on Computing and Networking (CANDAR)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2016-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"5","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2016 Fourth International Symposium on Computing and Networking (CANDAR)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/CANDAR.2016.0123","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 5
Abstract
Identifying the service of traffic by given IP network flows is essential for various purposes, such as management of QoS and avoiding security issues. Typical methods for this are identification based on its IP addresses and port numbers. However, the achieved accuracies of these method are not sufficient, then improving these methods is required. Deep Packet Inspection (DPI) is one of the most effective methods for improving accuracy of identification. In this paper, we explore a method for identifying the service of flow. We propose an identifying method based on DPI which covers multiple connections in a service. Then, we present performance evaluation and demonstrate that our method can suitably identify service from given network flows.