Source Code Authorship Identification Using Deep Neural Networks

Abstract

Many open-source projects are developed by the community and have a common basis. The more source code is open, the more the project is open to contributors. The possibility of accidental or deliberate use of someone else’s source code as a closed functionality in another project (even a commercial) is not excluded. This situation could create copyright disputes. Adding a plagiarism check to the project lifecycle during software engineering solves this problem. However, not all code samples for comparing can be found in the public domain. In this case, the methods of identifying the source code author can be useful. Therefore, identifying the source code author is an important problem in software engineering, and it is also a research area in symmetry. This article discusses the problem of identifying the source code author and modern methods of solving this problem. Based on the experience of researchers in the field of natural language processing (NLP), the authors propose their technique based on a hybrid neural network and demonstrate its results both for simple cases of determining the authorship of the code and for those complicated by obfuscation and using of coding standards. The results show that the author’s technique successfully solves the essential problems of analogs and can be effective even in cases where there are no obvious signs indicating authorship. The average accuracy obtained for all programming languages was 95% in the simple case and exceeded 80% in the complicated ones.

Authorship Attribution of Social Media and Literary Russian-Language Texts Using Machine Learning Methods and Feature Selection

“…There are many studies devoted to establishing authorship of a natural text and source code, the gender and age of the author, determining the sentiment of the text for forensic and social science purposes [5,6]. The early paper [1] provides a detailed review of 2015-2020 studies aimed at determining the author of a text, including approaches based on deep neural networks (NN), classical machine learning (ML) methods, and aspect analysis.…”

“…The hybrid model can work better than separated networks. This article considers combinations of CNN + CNN, LSTM + CNN, and CNN + LSTM, which showed excellent results in the related problem of determining the author of the software source code [5]. It is worth noting that the popular modern architectures CNN with attention and Transformers in the previous study [1] proved to be less accurate and more time-consuming, so they were not considered in this study.…”

“…Even minimal changes in these parameters can have a serious impact on the result. Therefore, the hyperparameters for the experimental models have been selected based on the authors' previous research experience [5].…”

Code Edit Recommendation Using a Recurrent Neural Network

“…For example, "turn your homework" is a 3-g because it consists of three words. In this case, the probability of "homework" that will appear after "turn your" can be found [27]. The probability is calculated as follows:…”

Determining the Age of the Author of the Text Based on Deep Neural Network Models

“…The relevance of research on this topic is associated with the auxiliary function for solving the problems of text mining [1][2][3][4][5][6][7], particularly its attribution [8,9]. The sentiment of the text, as well as the gender and age of the author, are the most informative features used in attribution.…”