Logo image
Back
Authentic Learning Approach for Data Poisoning Vulnerability in LLMs
Conference proceeding   Peer reviewed

Authentic Learning Approach for Data Poisoning Vulnerability in LLMs

Mst Shapna Akter, Md Abdur Rahman, Md Mostafizur Rahman, Juanjose Rodriguez-Cardenas, Hossain Shahriar, Fan Wu and Muhammad Rahman
Proceedings : annual International Computer Software and Applications Conference, pp.1504-1505
Annual Computers, Software, and Applications Conference (COMPSAC) (Osaka, Japan, 07/02/2024–07/04/2024)
07/02/2024
DOI: https://doi.org/10.1109/COMPSAC61105.2024.00210
Web of Science ID: WOS:001308581200201

Metrics

1 Record Views
5 Times Cited - Web of Science

Abstract

Authentic learning Data Poisoning Attack Privacy Security Large Language Model (LLM) Cybersecurity Education Software
The primary goal of authentic learning is to provide students with an engaging learning environment that offers hands-on experiences in solving real-world security challenges. Each educational theme consists of prelab activities, lab activities, and hands-on lab activities. By implementing authentic learning, we design and build portable lab for data poisoning vulnerability in LLM models on Google Colab. These hands-on labs can be accessed and practiced in real-time without the need for complex installations and configurations. This allows students to focus on learning concepts and increase their hands-on problem-solving skills.

Details

Logo image