Profiling Users by Modeling Web Transactions

Radek Tomsu; S. Marchal; N. Asokan

doi:10.1109/ICDCS.2017.164

Profiling Users by Modeling Web Transactions

Radek Tomsu
, S. Marchal
, N. Asokan

Department of Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceedings › Scientific › peer-review

6 Citations (Scopus)

Abstract

Users of electronic devices, e.g., laptop, smartphone, etc. have characteristic behaviors while surfing the Web. Profiling this behavior can help identify the person using a given device. In this paper, we introduce a technique to profile users based on their web transactions. We compute several features extracted from a sequence of web transactions and use them with one-class classification techniques to profile a user. We assess the efficacy and speed of our method at differentiating 25 synthetic users on a benchmark dataset (from a major security vendor) representing 6 months of web traffic monitoring from a small enterprise network.

Original language	English
Title of host publication	2017 IEEE 37th International Conference on Distributed Computing Systems (ICDCS)
Editors	Kisung Lee, Ling Liu
Publisher	IEEE
Pages	2399-2404
Number of pages	6
ISBN (Print)	978-1-5386-1791-5
DOIs	https://doi.org/10.1109/ICDCS.2017.164
Publication status	Published - 1 Jun 2017
MoE publication type	A4 Conference publication
Event	International Conference on Distributed Computing Systems - Atlanta, United States Duration: 5 Jun 2017 → 8 Jun 2017 Conference number: 37

Publication series

Name	International Conference on Distributed Computing Systems. Proceedings
Publisher	IEEE Computer Society
Volume	37
ISSN (Print)	1063-6927

Conference

Conference	International Conference on Distributed Computing Systems
Abbreviated title	ICDCS
Country/Territory	United States
City	Atlanta
Period	05/06/2017 → 08/06/2017

Keywords

Internet
behavioural sciences computing
feature extraction
pattern classification
Web traffic monitoring
Web transaction modeling
benchmark dataset
characteristic behaviors
electronic devices
laptop
one-class classification techniques
small enterprise network
smartphone
user profiling
Feature extraction
Kernel
Media
Monitoring
Support vector machines
Uniform resource locators

Access to Document

10.1109/ICDCS.2017.164

https://arxiv.org/abs/1703.09745

Cite this

@inproceedings{ef9a3516f93d44b9afff4b76a5e88671,

title = "Profiling Users by Modeling Web Transactions",

abstract = "Users of electronic devices, e.g., laptop, smartphone, etc. have characteristic behaviors while surfing the Web. Profiling this behavior can help identify the person using a given device. In this paper, we introduce a technique to profile users based on their web transactions. We compute several features extracted from a sequence of web transactions and use them with one-class classification techniques to profile a user. We assess the efficacy and speed of our method at differentiating 25 synthetic users on a benchmark dataset (from a major security vendor) representing 6 months of web traffic monitoring from a small enterprise network.",

keywords = "Internet, behavioural sciences computing, feature extraction, pattern classification, Web traffic monitoring, Web transaction modeling, benchmark dataset, characteristic behaviors, electronic devices, laptop, one-class classification techniques, small enterprise network, smartphone, user profiling, Feature extraction, Kernel, Media, Monitoring, Support vector machines, Uniform resource locators",

author = "Radek Tomsu and S. Marchal and N. Asokan",

year = "2017",

month = jun,

day = "1",

doi = "10.1109/ICDCS.2017.164",

language = "English",

isbn = "978-1-5386-1791-5",

series = "International Conference on Distributed Computing Systems. Proceedings",

publisher = "IEEE",

pages = "2399--2404",

editor = "Kisung Lee and Ling Liu",

booktitle = "2017 IEEE 37th International Conference on Distributed Computing Systems (ICDCS)",

address = "United States",

note = "International Conference on Distributed Computing Systems, ICDCS ; Conference date: 05-06-2017 Through 08-06-2017",

}

Tomsu, R, Marchal, S & Asokan, N 2017, Profiling Users by Modeling Web Transactions. in K Lee & L Liu (eds), 2017 IEEE 37th International Conference on Distributed Computing Systems (ICDCS). International Conference on Distributed Computing Systems. Proceedings, vol. 37, IEEE, pp. 2399-2404, International Conference on Distributed Computing Systems, Atlanta, Georgia, United States, 05/06/2017. https://doi.org/10.1109/ICDCS.2017.164

Profiling Users by Modeling Web Transactions. / Tomsu, Radek; Marchal, S.; Asokan, N.
2017 IEEE 37th International Conference on Distributed Computing Systems (ICDCS). ed. / Kisung Lee; Ling Liu. IEEE, 2017. p. 2399-2404 (International Conference on Distributed Computing Systems. Proceedings; Vol. 37).

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceedings › Scientific › peer-review

TY - GEN

T1 - Profiling Users by Modeling Web Transactions

AU - Tomsu, Radek

AU - Marchal, S.

AU - Asokan, N.

N1 - Conference code: 37

PY - 2017/6/1

Y1 - 2017/6/1

N2 - Users of electronic devices, e.g., laptop, smartphone, etc. have characteristic behaviors while surfing the Web. Profiling this behavior can help identify the person using a given device. In this paper, we introduce a technique to profile users based on their web transactions. We compute several features extracted from a sequence of web transactions and use them with one-class classification techniques to profile a user. We assess the efficacy and speed of our method at differentiating 25 synthetic users on a benchmark dataset (from a major security vendor) representing 6 months of web traffic monitoring from a small enterprise network.

AB - Users of electronic devices, e.g., laptop, smartphone, etc. have characteristic behaviors while surfing the Web. Profiling this behavior can help identify the person using a given device. In this paper, we introduce a technique to profile users based on their web transactions. We compute several features extracted from a sequence of web transactions and use them with one-class classification techniques to profile a user. We assess the efficacy and speed of our method at differentiating 25 synthetic users on a benchmark dataset (from a major security vendor) representing 6 months of web traffic monitoring from a small enterprise network.

KW - Internet

KW - behavioural sciences computing

KW - feature extraction

KW - pattern classification

KW - Web traffic monitoring

KW - Web transaction modeling

KW - benchmark dataset

KW - characteristic behaviors

KW - electronic devices

KW - laptop

KW - one-class classification techniques

KW - small enterprise network

KW - smartphone

KW - user profiling

KW - Feature extraction

KW - Kernel

KW - Media

KW - Monitoring

KW - Support vector machines

KW - Uniform resource locators

U2 - 10.1109/ICDCS.2017.164

DO - 10.1109/ICDCS.2017.164

M3 - Conference article in proceedings

SN - 978-1-5386-1791-5

T3 - International Conference on Distributed Computing Systems. Proceedings

SP - 2399

EP - 2404

BT - 2017 IEEE 37th International Conference on Distributed Computing Systems (ICDCS)

A2 - Lee, Kisung

A2 - Liu, Ling

PB - IEEE

T2 - International Conference on Distributed Computing Systems

Y2 - 5 June 2017 through 8 June 2017

ER -

Profiling Users by Modeling Web Transactions

Abstract

Publication series

Conference

Keywords

Access to Document

Fingerprint

Cite this