Thesis Details

Source Code Authorship Attribution

Bachelor's Thesis Student: Pružina Tomáš Academic Year: 2016/2017 Supervisor: Smrž Pavel, doc. RNDr., Ph.D.
Czech title
Určování autorství zdrojových kódů
Language
English
Abstract

With the rise of the Internet, the trend of source code plagiarism and copyright infringement has been increasing and it has become a problem in both academic and corporate environments. With that in mind, it becomes important to be able to identify author of a source code based on stylomentry techniques to prevent unethical violations of the intelectual property of the author. This thesis summarizes modern approaches to source code authorship attribution and presents a general purpose authorship attribution tool that attempts to detect author of the source code.

Keywords

authorship attribution, machine learning, feature detection, source code authorship verification, code stylometry

Department
Degree Programme
Information Technology
Files
Status
defended, grade C
Date
13 June 2017
Reviewer
Committee
Honzík Jan M., prof. Ing., CSc. (DIFS FIT BUT), předseda
Janoušek Vladimír, doc. Ing., Ph.D. (DITS FIT BUT), člen
Novák Michal, doc. RNDr., Ph.D. (DMAT FEEC BUT), člen
Strnadel Josef, Ing., Ph.D. (DCSY FIT BUT), člen
Szőke Igor, Ing., Ph.D. (DCGM FIT BUT), člen
Citation
PRUŽINA, Tomáš. Source Code Authorship Attribution. Brno, 2017. Bachelor's Thesis. Brno University of Technology, Faculty of Information Technology. 2017-06-13. Supervised by Smrž Pavel. Available from: https://www.fit.vut.cz/study/thesis/17751/
BibTeX
@bachelorsthesis{FITBT17751,
    author = "Tom\'{a}\v{s} Pru\v{z}ina",
    type = "Bachelor's thesis",
    title = "Source Code Authorship Attribution",
    school = "Brno University of Technology, Faculty of Information Technology",
    year = 2017,
    location = "Brno, CZ",
    language = "english",
    url = "https://www.fit.vut.cz/study/thesis/17751/"
}
Back to top