← all papers · overview

Vocabulary Attack To Hijack Large Language Model Applications

Abstract

The fast advancements in Large Language Models (LLMs) are driving an increasing number of applications. Together with the growing number of users, we also see an increasing number of attackers who try to outsmart these systems. They want the model to reveal confidential information, specific false information, or offensive behavior. To this end, they manipulate their instructions for the LLM by in

Related papers

Ranked by semantic similarity — how closely each paper's abstract matches this one (100% = near-identical topic).