GoofyGame_exampleQA.pdf

<p dir="ltr">Large Language Models (LLMs) have advanced capabilities but are still at risk from jailbreak attempts by malicious users. Despite efforts to address this through red teaming, role-playing techniques continue to bypass safeguards effectively. This is especially concerning...

Full description

Saved in:
Bibliographic Details
Main Author: Barbara Puccio (20534147) (author)
Published: 2025
Subjects:
Tags: Add Tag
No Tags, Be the first to tag this record!