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

Institutions

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
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Source Code Authorship Attribution: Trends, Techniques, and Challenges

M. Harshvardhan, Bilal I. Al-Ahmad, Dana Dghaym, Murad Magableh et al.
Computers
Authorship Attribution and Profiling
article

Source Code Authorship Attribution: Trends, Techniques, and Challenges

M. Harshvardhan, Bilal I. Al-Ahmad, Dana Dghaym, Murad Magableh, Sahar Mahmoud, Doaa Altayeb
article en

Abstract

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.

ComputersVol. 15(11)
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)
Authorship Attribution and Profiling
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon