PPS: A Packets Pattern-based Video Identification in Encrypted Network Traffic

Syed Muhammad Ammar Hassan Bukhari; Muhammad Afaq; Wang Cheol Song

doi:10.1145/3603166.3632243

PPS: A Packets Pattern-based Video Identification in Encrypted Network Traffic

Syed Muhammad Ammar Hassan Bukhari
, Muhammad Afaq
, Wang Cheol Song^*

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

1 Scopus citations

Abstract

Video identification in encrypted network traffic has become a trending field in the research area for user behavior and Quality of Experience (QoE) analysis. However, the traditional methods of video identification have become ineffective with the usage of Hypertext Transfer Protocol Secure (HTTPS). This paper presents a video identification method in encrypted network traffic using the number of packets received at the user's end in a second. For this purpose, video streams are captured, and feature is extracted from the video streams in the form of a series of Packets per Seconds (PPS). This feature is provided as input to a Convolutional Neural Network (CNN), which learns the pattern from the network traffic feature and successfully identifies the video even if the pattern differs from the training sample. The results show that PPS outperforms the other video identification techniques with a high accuracy of 90%. Moreover, the results show that CNN outperforms its counterpart regarding video identification with a 25% performance increase.

Original language	English
Title of host publication	16th IEEE/ACM International Conference on Utility and Cloud Computing, UCC 2023
Publisher	Association for Computing Machinery, Inc
ISBN (Electronic)	9798400702341
DOIs	https://doi.org/10.1145/3603166.3632243
State	Published - 4 Dec 2023
Externally published	Yes
Event	16th IEEE/ACM International Conference on Utility and Cloud Computing, UCC 2023 - Taormina, Italy Duration: 4 Dec 2023 → 7 Dec 2023

Publication series

Name	16th IEEE/ACM International Conference on Utility and Cloud Computing, UCC 2023

Conference

Conference	16th IEEE/ACM International Conference on Utility and Cloud Computing, UCC 2023
Country/Territory	Italy
City	Taormina
Period	4/12/23 → 7/12/23

Bibliographical note

Publisher Copyright:
© 2023 Copyright is held by the owner/author(s). Publication rights licensed to ACM.

Keywords

encrypted network traffic
packets per seconds
video identification
video title classification

ASJC Scopus subject areas

Computer Networks and Communications
Hardware and Architecture

Access to Document

10.1145/3603166.3632243

Cite this

Bukhari, S. M. A. H., Afaq, M., & Song, W. C. (2023). PPS: A Packets Pattern-based Video Identification in Encrypted Network Traffic. In 16th IEEE/ACM International Conference on Utility and Cloud Computing, UCC 2023 Article 35 (16th IEEE/ACM International Conference on Utility and Cloud Computing, UCC 2023). Association for Computing Machinery, Inc. https://doi.org/10.1145/3603166.3632243

@inproceedings{358b93bb580d4383a7f535fa9b46643e,

title = "PPS: A Packets Pattern-based Video Identification in Encrypted Network Traffic",

abstract = "Video identification in encrypted network traffic has become a trending field in the research area for user behavior and Quality of Experience (QoE) analysis. However, the traditional methods of video identification have become ineffective with the usage of Hypertext Transfer Protocol Secure (HTTPS). This paper presents a video identification method in encrypted network traffic using the number of packets received at the user's end in a second. For this purpose, video streams are captured, and feature is extracted from the video streams in the form of a series of Packets per Seconds (PPS). This feature is provided as input to a Convolutional Neural Network (CNN), which learns the pattern from the network traffic feature and successfully identifies the video even if the pattern differs from the training sample. The results show that PPS outperforms the other video identification techniques with a high accuracy of 90\%. Moreover, the results show that CNN outperforms its counterpart regarding video identification with a 25\% performance increase.",

keywords = "encrypted network traffic, packets per seconds, video identification, video title classification",

author = "Bukhari, \{Syed Muhammad Ammar Hassan\} and Muhammad Afaq and Song, \{Wang Cheol\}",

note = "Publisher Copyright: {\textcopyright} 2023 Copyright is held by the owner/author(s). Publication rights licensed to ACM.; 16th IEEE/ACM International Conference on Utility and Cloud Computing, UCC 2023 ; Conference date: 04-12-2023 Through 07-12-2023",

year = "2023",

month = dec,

day = "4",

doi = "10.1145/3603166.3632243",

language = "English",

series = "16th IEEE/ACM International Conference on Utility and Cloud Computing, UCC 2023",

publisher = "Association for Computing Machinery, Inc",

booktitle = "16th IEEE/ACM International Conference on Utility and Cloud Computing, UCC 2023",

}

Bukhari, SMAH, Afaq, M & Song, WC 2023, PPS: A Packets Pattern-based Video Identification in Encrypted Network Traffic. in 16th IEEE/ACM International Conference on Utility and Cloud Computing, UCC 2023., 35, 16th IEEE/ACM International Conference on Utility and Cloud Computing, UCC 2023, Association for Computing Machinery, Inc, 16th IEEE/ACM International Conference on Utility and Cloud Computing, UCC 2023, Taormina, Italy, 4/12/23. https://doi.org/10.1145/3603166.3632243

PPS: A Packets Pattern-based Video Identification in Encrypted Network Traffic. / Bukhari, Syed Muhammad Ammar Hassan; Afaq, Muhammad; Song, Wang Cheol.
16th IEEE/ACM International Conference on Utility and Cloud Computing, UCC 2023. Association for Computing Machinery, Inc, 2023. 35 (16th IEEE/ACM International Conference on Utility and Cloud Computing, UCC 2023).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - PPS

T2 - 16th IEEE/ACM International Conference on Utility and Cloud Computing, UCC 2023

AU - Bukhari, Syed Muhammad Ammar Hassan

AU - Afaq, Muhammad

AU - Song, Wang Cheol

PY - 2023/12/4

Y1 - 2023/12/4

N2 - Video identification in encrypted network traffic has become a trending field in the research area for user behavior and Quality of Experience (QoE) analysis. However, the traditional methods of video identification have become ineffective with the usage of Hypertext Transfer Protocol Secure (HTTPS). This paper presents a video identification method in encrypted network traffic using the number of packets received at the user's end in a second. For this purpose, video streams are captured, and feature is extracted from the video streams in the form of a series of Packets per Seconds (PPS). This feature is provided as input to a Convolutional Neural Network (CNN), which learns the pattern from the network traffic feature and successfully identifies the video even if the pattern differs from the training sample. The results show that PPS outperforms the other video identification techniques with a high accuracy of 90%. Moreover, the results show that CNN outperforms its counterpart regarding video identification with a 25% performance increase.

AB - Video identification in encrypted network traffic has become a trending field in the research area for user behavior and Quality of Experience (QoE) analysis. However, the traditional methods of video identification have become ineffective with the usage of Hypertext Transfer Protocol Secure (HTTPS). This paper presents a video identification method in encrypted network traffic using the number of packets received at the user's end in a second. For this purpose, video streams are captured, and feature is extracted from the video streams in the form of a series of Packets per Seconds (PPS). This feature is provided as input to a Convolutional Neural Network (CNN), which learns the pattern from the network traffic feature and successfully identifies the video even if the pattern differs from the training sample. The results show that PPS outperforms the other video identification techniques with a high accuracy of 90%. Moreover, the results show that CNN outperforms its counterpart regarding video identification with a 25% performance increase.

KW - encrypted network traffic

KW - packets per seconds

KW - video identification

KW - video title classification

UR - https://www.scopus.com/pages/publications/85191663379

U2 - 10.1145/3603166.3632243

DO - 10.1145/3603166.3632243

M3 - Conference contribution

AN - SCOPUS:85191663379

T3 - 16th IEEE/ACM International Conference on Utility and Cloud Computing, UCC 2023

BT - 16th IEEE/ACM International Conference on Utility and Cloud Computing, UCC 2023

PB - Association for Computing Machinery, Inc

Y2 - 4 December 2023 through 7 December 2023

ER -

PPS: A Packets Pattern-based Video Identification in Encrypted Network Traffic

Abstract

Publication series

Conference

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Fingerprint

Cite this