Source Code Author Attribution Using Author’s Programming Style and Code Smells

TL;DR: A machine learning based methodology is described not only to address the question of can code smells are useful for characterizing authors’ signatures but also for designing a system that can improves the authorship attribution.

Abstract: Source code is an intellectual property and using it without author’s permission is a violation of property right. Source code authorship attribution is vital for dealing with software theft, copyright issues and piracies. Characterizing author’s signature for identifying their footprints is the core task of authorship attribution. Different aspects of source code have been considered for characterizing signatures including author’s coding style and programming structure, etc. The objective of this research is to explore another trait of authors’ coding behavior for personifying their footprints. The main question that we want to address is that “can code smells are useful for characterizing authors’ signatures? A machine learning based methodology is described not only to address the question but also for designing a system. Two different aspects of source code are considered for its representation into features: author’s style and code smells. The author’s style related feature representation is used as baseline. Results have shown that code smell can improves the authorship attribution.