Source Code Authorship Attribution: Trends, Techniques, and Challenges
Source code authorship attribution identifies the programmer responsible for a code sample, with applications in plagiarism detection, malware forensics, and software provenance. This systematic review organizes the reviewed source-code attribution studies into a four-stage pipeline: preprocessing, feature extraction, classification, and prediction. The synthesis covers stylometric metrics, n-grams, abstract syntax trees, program graphs, learned embeddings, and watermarking, alongside statistical methods, classical machine learning, neural networks, transformers, and ensembles. Reported results are compared across C, C++, C#, Java, and Python with attention to dataset size and evaluation setting. The synthesis identifies open questions in cross-language and open-set attribution, robustness to transformation and mimicry, AI-assisted and collaborative code, and interpretable forensic evidence.
Authors
- M. Harshvardhan (ORCID: https://orcid.org/0000-0001-8086-544X)
- Bilal I. Al-Ahmad (ORCID: https://orcid.org/0000-0002-1267-1026)
- Dana Dghaym (ORCID: https://orcid.org/0000-0002-2196-2749)
- Murad Magableh
- Sahar Mahmoud (ORCID: https://orcid.org/0009-0000-5770-8585)
- Doaa Altayeb
Institutions
- University of Jordan (JO)
- Alfaisal University (SA)
- University of Khartoum (SD)
- American University of Sharjah (AE)
- Ministry of Higher Education And Scientific Research (SD)
- University of Gezira (SD)
- Irbid National University (JO)
Publication Details
- Journal
- Computers
- Published
- 2026-11-16
- DOI
- https://doi.org/10.3390/computers15110843
- Primary Topic
- Authorship Attribution and Profiling
- Type
- article
- Field-Weighted Citation Impact
- 0.00