Towards Robust Plagiarism Detection in Programming Education: Introducing Tolerant Token Matching Techniques to Counter Novel Obfuscation Methods

Creators: Maisch, Robin and Hagel, Nathan and Bartel, Alexander
Title: Towards Robust Plagiarism Detection in Programming Education: Introducing Tolerant Token Matching Techniques to Counter Novel Obfuscation Methods
Item Type: Conference or Workshop Item
Event Title: (Proceedings of the) 6th European Conference on Software Engineering Education (ECSEE)
Event Location: Seeon, Germany
Event Dates: 2.-4. Juni 2025
Projects: TTZ-GZ
Page Range: pp. 11-19
Additional Information: Open Acces: CC BY 4.0
Date: 2025
Divisions: Informationsmanagement
Abstract (ENG): With the rise of AI-generated code, programming courses face new challenges in detecting code plagiarism. Traditional methods struggle against obfuscation techniques that modify code structure through statement insertion and deletion. To address this, we propose a novel approach based on tolerant token matching designed to enhance resilience against such attacks. We evaluate our method through three experiments on a real-life dataset with AI-obfuscated plagiarisms. The results show that our approach increased the median similarity gap between originals and plagiarisms by 1 to 6 percentage points.
Forthcoming: No
Language: English
Link eMedia: Download
Citation:

Maisch, Robin and Hagel, Nathan and Bartel, Alexander (2025) Towards Robust Plagiarism Detection in Programming Education: Introducing Tolerant Token Matching Techniques to Counter Novel Obfuscation Methods. In: (Proceedings of the) 6th European Conference on Software Engineering Education (ECSEE), 2.-4. Juni 2025, Seeon, Germany, pp. 11-19.

Actions for admins (login required)

View Item in edit mode View Item in edit mode