Profiling Users by Modeling Web Transactions

Radek Tomsu, S. Marchal, N. Asokan

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

5 Citations (Scopus)


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 languageEnglish
Title of host publication2017 IEEE 37th International Conference on Distributed Computing Systems (ICDCS)
EditorsKisung Lee, Ling Liu
Number of pages6
ISBN (Print)978-1-5386-1791-5
Publication statusPublished - 1 Jun 2017
MoE publication typeA4 Article in a conference publication
EventInternational Conference on Distributed Computing Systems - Atlanta, United States
Duration: 5 Jun 20178 Jun 2017
Conference number: 37

Publication series

NameInternational Conference on Distributed Computing Systems. Proceedings
PublisherIEEE Computer Society
ISSN (Print)1063-6927


ConferenceInternational Conference on Distributed Computing Systems
Abbreviated titleICDCS
Country/TerritoryUnited States


  • 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


Dive into the research topics of 'Profiling Users by Modeling Web Transactions'. Together they form a unique fingerprint.

Cite this