Search papers, labs, and topics across Lattice.
This paper presents a systematic literature review of programmer attribution research, analyzing 47 studies published between 2012 and 2025. The review categorizes studies based on authorship tasks, feature categories (stylistic and behavioral), learning approaches, datasets, and evaluation practices, revealing a taxonomy linking feature types to ML techniques. The analysis identifies a research landscape dominated by closed-world attribution using stylometric features and limited benchmark datasets, while highlighting gaps in behavioral signals, authorship verification, and reproducibility.
Programmer attribution research is heavily skewed towards stylometric features and closed-world scenarios, leaving behavioral biometrics and open-world verification largely unexplored.
Programmer attribution seeks to identify or verify the author of a source code artifact using stylistic, structural, or behavioural characteristics. This problem has been studied across software engineering, security, and digital forensics, resulting in a growing and methodologically diverse set of publications. This paper presents a systematic mapping study of programmer attribution research focused on source code analysis. From an initial set of 135 candidate publications, 47 studies published between 2012 and 2025 were selected through a structured screening process. The included works are analysed along several dimensions, including authorship tasks, feature categories, learning and modelling approaches, dataset sources, and evaluation practices. Based on this analysis, we derive a taxonomy that relates stylistic and behavioural feature types to commonly used machine learning techniques and provide a descriptive overview of publication trends, benchmarks, programming languages. A content-level analysis highlights the main thematic clusters in the field. The results indicate a strong focus on closed-world authorship attribution using stylometric features and a heavy reliance on a small number of benchmark datasets, while behavioural signals, authorship verification, and reproducibility remain less explored. The study consolidates existing research into a unified framework and outlines methodological gaps that can guide future work. This manuscript is currently under review. The present version is a preprint.
