User profiling and re-identification: Case of university-wide network analysis

Warning

This publication doesn't include Institute of Computer Science. It includes Faculty of Informatics. Official publication website can be found on muni.cz.
Authors

KUMPOŠT Marek MATYÁŠ Václav

Year of publication 2009
Type Article in Proceedings
Conference Trust, Privacy and Security in Digital Business, 6th International Conference, TrustBus 2009
MU Faculty or unit

Faculty of Informatics

Citation
Doi http://dx.doi.org/10.1007/978-3-642-03748-1_1
Field Informatics
Keywords user profiling; network analysis; data mining; IDF; similarity searching; cosine similarity
Description In this paper we present our methodology for context information processing, modeling users' behaviour and re-identification. Our primary interest is to what extent a user can be re-identified if we have his "user profile" and how much information is required for a successful re-identification. We operate with ``user profiles'' that reflect user's behaviour in the past. We describe the input date we use for building behavioural characteristics; similarity searching procedure and an evaluation of the re-identification process. We discuss (and provide results of our experiments) how different initial conditions, as well as different approaches used in the similarity searching phase, influence the results and propose the optimal scenario where we obtain the most accurate results. We provide experimental results of re-identification of three protocols (SSH, HTTP and HTTPS).
Related projects:

You are running an old browser version. We recommend updating your browser to its latest version.

More info