Homoglyph-based Adversarial Perturbation of Introductory Computer Science Theory Problems
For educators, this provides a simple way to protect homework integrity against AI-assisted cheating, though the approach is incremental.
The paper proposes a homoglyph-based adversarial perturbation method to modify introductory computer science theory problems, preventing students from using AI tools to solve them. Experiments show the method effectively perturbs problems without changing semantic meaning.
Different AI tools such as ChatGPT, Gemini, and Claude are becoming very popular. Although they are helpful for many day-to-day tasks, they can be used in unexpected ways. For example, the learning objectives of a course may not be achieved if students use these tools to solve their homework problems. This paper proposes a simple method to address this issue in the lazy student model. The method uses homoglyph-based adversarial perturbation to first modify the question without changing the semantic meaning of the question. Then a few characters are perturbed by their homoglyphs. Our experimental result shows the theoretical problems of introductory computer science courses can be effectively perturbed. We also propose an interactive tool to conveniently use our method.