一句话：通过两校学生刻意抄袭并记录修改过程的实证研究，揭示规避代码抄袭检测的常见策略，并发布真实数据集。
学术诚信在高等教育中至关重要，但编程课程中的学生抄袭现象十分普遍。抄袭检测器被广泛使用，然而尚不清楚其检测方式是否与学生实际混淆代码的手法相符；已有评测数据集规模有限、往往不公开，或依赖人工合成的抄袭样例。本文由两所大学合作开展实证研究，要求两校学生对给定解答进行抄袭并记录自己的修改，从而构建真实数据集。基于该数据集，作者分析了学生逃避检测的成功率，归纳出常见的抄袭策略，并为今后学术诚信研究提供了可靠资源。结果显示，只有少数提交成功逃避检测，但参与者采用了大量富有创意的手工与基于 LLM 的混淆策略。
While academic integrity is essential in higher education, plagiarism by students in programming courses is a prevalent challenge. Plagiarism detectors are widely used, yet it is unclear if they match the ways students actually obfuscate copied code. Existing evaluation datasets are limited, often private, or rely on synthetically generated plagiarism instances. In a collaboration between two universities, we conduct an empirical study that challenges students at both institutions to plagiarize given solutions and document their changes. Using this dataset, we analyze their success in evading detection, present common plagiarism strategies, and provide a reliable resource for future research on academic integrity. While only few submissions plagiarize successfully, our participants incorporate a large variety of creative manual and LLM-based strategies.
@inproceedings{MaischSGFNLK26,
title = {Criminal Minds: How First-Year CS Students Plagiarize Code},
author = {Robin Maisch and Larissa Schmid and Richard Glassey and Dominik Fuchß and Nils Niehues and Haoyu Liu and Anne Koziolek},
booktitle = {FSE},
year = {2026},
doi = {10.1145/3803437.3805789}
}