# Discriminating Human-authored from ChatGPT-Generated Code Via Discernable Feature Analysis

arXiv: https://arxiv.org/abs/2306.14397 · HTML: https://mlsanity.com/paper/2306.14397/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Jun 2023.

## Built on by (most cited first, 7 of 7)

- [Large Language Models for Software Engineering: A Systematic Literature Review](https://mlsanity.com/paper/2308.10620/) (2023)
- [textttDroid: A Resource Suite for AI-Generated Code Detection](https://mlsanity.com/paper/2507.10583/) (2025)
- [ChatGPT Code Detection: Techniques for Uncovering the Source of Code](https://mlsanity.com/paper/2405.15512/) (2024)
- [Tracing the Data Trail: A Survey of Data Provenance, Transparency and Traceability in LLMs](https://mlsanity.com/paper/2601.14311/) (2026)
- [UID as a Guiding Metric for Automated Authorship Obfuscation](https://mlsanity.com/paper/2312.03709/) (2023)
- [On Developers' Self-Declaration of AI-Generated Code: An Analysis of Practices](https://mlsanity.com/paper/2504.16485/) (2025)
- [What Makes Code Generation Ethically Sourced?](https://mlsanity.com/paper/2507.19743/) (2025)

## Abstract (arXiv)

The ubiquitous adoption of Large Language Generation Models (LLMs) in programming has underscored the importance of differentiating between human-written code and code generated by intelligent models. This paper specifically aims to distinguish code generated by ChatGPT from that authored by humans. Our investigation reveals disparities in programming style, technical level, and readability between these two sources. Consequently, we develop a discriminative feature set for differentiation and evaluate its efficacy through ablation experiments. Additionally, we devise a dataset cleansing technique, which employs temporal and spatial segmentation, to mitigate the dearth of datasets and to secure high-caliber, uncontaminated datasets. To further enrich data resources, we employ "code transformation," "feature transformation," and "feature customization" techniques, generating an extensive dataset comprising 10,000 lines of ChatGPT-generated code. The salient contributions of our research include: proposing a discriminative feature set yielding high accuracy in differentiating ChatGPT-generated code from human-authored code in binary classification tasks; devising methods for generating extensive ChatGPT-generated codes; and introducing a dataset cleansing strategy that extracts immaculate, high-grade code datasets from open-source repositories, thus achieving exceptional accuracy in code authorship attribution tasks.