Supporting Students in Navigating LLM-Generated Insecure Code
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908676567072768 |
|---|---|
| author | Park, Jaehwan Lim, Kyungchan Park, Seonhye Kim, Doowon |
| author_facet | Park, Jaehwan Lim, Kyungchan Park, Seonhye Kim, Doowon |
| contents | The advent of Artificial Intelligence (AI), particularly large language models (LLMs), has revolutionized software development by enabling developers to specify tasks in natural language and receive corresponding code, boosting productivity. However, this shift also introduces security risks, as LLMs may generate insecure code that can be exploited by adversaries. Current educational approaches emphasize efficiency while overlooking these risks, leaving students underprepared to identify and mitigate security issues in AI-assisted workflows.
To address this gap, we present Bifröst, an educational framework that cultivates security awareness in AI-augmented development. Bifröst integrates (1) a Visual Studio Code extension simulating realistic environments, (2) adversarially configured LLMs that generate insecure code, and (3) a feedback system highlighting vulnerabilities. By immersing students in tasks with compromised LLMs and providing targeted security analysis, Bifröst cultivates critical evaluation skills; classroom deployments (n=61) show vulnerability to insecure code, while a post-intervention survey (n=21) indicates increased skepticism toward LLM outputs. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_20878 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Supporting Students in Navigating LLM-Generated Insecure Code Park, Jaehwan Lim, Kyungchan Park, Seonhye Kim, Doowon Cryptography and Security The advent of Artificial Intelligence (AI), particularly large language models (LLMs), has revolutionized software development by enabling developers to specify tasks in natural language and receive corresponding code, boosting productivity. However, this shift also introduces security risks, as LLMs may generate insecure code that can be exploited by adversaries. Current educational approaches emphasize efficiency while overlooking these risks, leaving students underprepared to identify and mitigate security issues in AI-assisted workflows. To address this gap, we present Bifröst, an educational framework that cultivates security awareness in AI-augmented development. Bifröst integrates (1) a Visual Studio Code extension simulating realistic environments, (2) adversarially configured LLMs that generate insecure code, and (3) a feedback system highlighting vulnerabilities. By immersing students in tasks with compromised LLMs and providing targeted security analysis, Bifröst cultivates critical evaluation skills; classroom deployments (n=61) show vulnerability to insecure code, while a post-intervention survey (n=21) indicates increased skepticism toward LLM outputs. |
| title | Supporting Students in Navigating LLM-Generated Insecure Code |
| topic | Cryptography and Security |
| url | https://arxiv.org/abs/2511.20878 |