← all papers · overview

Soft Begging: Modular And Efficient Shielding Of Llms Against Prompt Injection And Jailbreaking Based On Prompt Tuning

Abstract

Prompt injection (both direct and indirect) and jailbreaking are now recognized as significant issues for large language models (LLMs), particularly due to their potential for harm in application-integrated contexts. This extended abstract explores a novel approach to protecting LLMs from such attacks, termed "soft begging." This method involves training soft prompts to counteract the effects of c

Related papers

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