Logo image
Back
Mitigating Insecure Outputs in Large Language Models(LLMs): A Practical Educational Module
Conference proceeding   Peer reviewed

Mitigating Insecure Outputs in Large Language Models(LLMs): A Practical Educational Module

Md Abdul Barek, Md Mostafizur Rahman, Mst Shapna Akter, A. B. M. Kamrul Islam Riad, Md Abdur Rahman, Hossain Shahriar, Akond Rahman and Fan Wu
Proceedings : annual International Computer Software and Applications Conference, pp.2424-2429
IEEE Annual International Computer Software and Applications Conference
Annual Computers, Software, and Applications Conference (COMPSAC), 48th (Osaka, Japan, 07/02/2024–07/04/2024)
08/2024
DOI: https://doi.org/10.1109/COMPSAC61105.2024.00389
Web of Science ID: WOS:001308581200380

Metrics

1 Record Views
9 Times Cited - Web of Science

Abstract

Large Language Models (LLMs) vulnerabilities Artificial Intelligence or Cybernetics Computer Science Cybersecurity
Large Language Models (LLMs) have extensive ability to produce promising output. Nowadays, people are increasingly relying on them due to easy accessibility, rapid and outstanding outcomes. However, the use of these results without appropriate scrutiny poses serious security risks, particularly when they are integrated with other software, APIs, or plugins. This is because the LLM outputs are highly dependent on the prompts they receive. Therefore, it is essential to carefully clean these outputs before using them in additional software environments. This paper is designed to teach students about the potential dangers of contaminated LLM output within the context of web development through prelab, handson, and postlab experiences. Hands-on lab provides practical guidance on how to handle LLM vulnerabilities to make applications safe with some real-world examples in Python. This approach aims to provide students with a deeper understanding of the precautions necessary to ensure software against the vulnerabilities introduced by LLM output.

Details

Logo image