Presentation | 2023-09-22 OLIViS: An OSINT-Based Lightweight Method for Identifying Video Content Services for Capacity Planning in Backbone ISPs Yuki Tamura, Fumio Teraoka, Takao Kondo, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | As of 2022, 66% of Internet traffic is generated by video content services, among which Netflix and YouTube are the dominant players. By predicting the traffic volume of individual video content services, ISPs can make appropriate capital investments and determine appropriate peering policies with CDN (Content Delivery Network) providers. Although DPI (Deep Packet Inspection) is widely used to identify network services, packet-level analysis does not scale to the traffic passing through backbone ISPs and is inapplicable to encrypted packets. This paper proposes OLIViS (OSINT-based Lightweight method for Identifying Video content Services). To achieve scalability, OLIViS adopts flow-level analysis. In the first step, OLIViS extracts elephant flows as anomalies using a CNN-VAE (Convolutional Neural Network - Variational AutoEncoder) trained to detect mice flows. In the second step, OLIViS identifies flows of individual video content services included in the elephant flows by referring to OSINT (Open Source INTelligence) data such as SAN (Subject Alternative Name). OLIViS identifies Netflix and youTube flows with accuracy of over 96% in terms of traffic volume, and OLIViS infers the flow statistics of Netflix and YouTube, which closely resemble those inferred with DPI on non-encrypted traffic in a campus network. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Network Traffic classification / flow-based / unsupervised learning / Netflix / YouTube |
Paper # | IA2023-23 |
Date of Issue | 2023-09-14 (IA) |
Conference Information | |
Committee | IA |
---|---|
Conference Date | 2023/9/21(2days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | Hokkaido Univeristy |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | Internet Operation and Management, Network Architecture, Communication Protocols, IoT, etc. |
Chair | Toyokazu Akiyama(Kyoto Sangyo Univ.) |
Vice Chair | Yusuke Sakumoto(Kwansei Gakuin Univ.) / Toshiki Watanabe(NEC) / Yuichiro Hei(KDDI) |
Secretary | Yusuke Sakumoto(Osaka Univ.) / Toshiki Watanabe(Kogakuin Univ.) / Yuichiro Hei(Kyushu Inst. of Tech.) |
Assistant | Daisuke Kotani(Kyoto Univ.) / Ryo Nakamura(Fukuoka Univ.) / Ryo Nakamura(Univ. of Tokyo) |
Paper Information | |
Registration To | Technical Committee on Internet Architecture |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | OLIViS: An OSINT-Based Lightweight Method for Identifying Video Content Services for Capacity Planning in Backbone ISPs |
Sub Title (in English) | |
Keyword(1) | Network Traffic classification |
Keyword(2) | flow-based |
Keyword(3) | unsupervised learning |
Keyword(4) | Netflix |
Keyword(5) | YouTube |
1st Author's Name | Yuki Tamura |
1st Author's Affiliation | Keio University(Keio Univ.) |
2nd Author's Name | Fumio Teraoka |
2nd Author's Affiliation | Keio University(Keio Univ.) |
3rd Author's Name | Takao Kondo |
3rd Author's Affiliation | Keio University(Keio Univ.) |
Date | 2023-09-22 |
Paper # | IA2023-23 |
Volume (vol) | vol.123 |
Number (no) | IA-193 |
Page | pp.pp.75-82(IA), |
#Pages | 8 |
Date of Issue | 2023-09-14 (IA) |