Homoglyph-based Adversarial Perturbation of Introductory Computer Science Theory Problems
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866909048382685184 |
|---|---|
| author | Alexander, Aidan Juneja, Chitrangada Tontrasathien, Napaluck Vanek, Miro Ahmed, Reyan Debray, Saumya Rahaman, Sazzadur |
| author_facet | Alexander, Aidan Juneja, Chitrangada Tontrasathien, Napaluck Vanek, Miro Ahmed, Reyan Debray, Saumya Rahaman, Sazzadur |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_16286 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Homoglyph-based Adversarial Perturbation of Introductory Computer Science Theory Problems Alexander, Aidan Juneja, Chitrangada Tontrasathien, Napaluck Vanek, Miro Ahmed, Reyan Debray, Saumya Rahaman, Sazzadur Computers and Society Artificial Intelligence 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. |
| title | Homoglyph-based Adversarial Perturbation of Introductory Computer Science Theory Problems |
| topic | Computers and Society Artificial Intelligence |
| url | https://arxiv.org/abs/2605.16286 |