BaThe: Defense against the Jailbreak Attack in Multimodal Large Language Models by Treating Harmful Instruction as Backdoor Trigger

TL;DR

BaThe is a defense mechanism for multimodal large language models that treats harmful instructions as backdoor triggers, effectively mitigating jailbreak attacks with minimal performance impact.

Contribution

It introduces BaThe, a novel backdoor trigger-based defense method that uses virtual rejection prompts embedded in soft text embeddings to defend against jailbreak attacks in MLLMs.

Findings

BaThe effectively mitigates various jailbreak attacks.

It is adaptable to unseen attack types.

Minimal impact on model performance.

Abstract

Multimodal Large Language Models (MLLMs) have showcased impressive performance in a variety of multimodal tasks. On the other hand, the integration of additional image modality may allow the malicious users to inject harmful content inside the images for jailbreaking. Unlike text-based LLMs, where adversaries need to select discrete tokens to conceal their malicious intent using specific algorithms, the continuous nature of image signals provides a direct opportunity for adversaries to inject harmful intentions. In this work, we propose $\textbf{BaThe}$ ($\textbf{Ba}$ckdoor $\textbf{T}$rigger S$\textbf{h}$i$\textbf{e}$ld), a simple yet effective jailbreak defense mechanism. Our work is motivated by recent research on jailbreak backdoor attack and virtual prompt backdoor attack in generative language models. Jailbreak backdoor attack uses harmful instructions combined with manually crafted strings as triggers to make the backdoored model generate prohibited responses. We assume that harmful instructions can function as triggers, and if we alternatively set rejection responses as the triggered response, the backdoored model then can defend against jailbreak attacks. We achieve this by utilizing virtual rejection prompt, similar to the virtual prompt backdoor attack. We embed the virtual rejection prompt into the soft text embeddings, which we call ``wedge''. Our comprehensive experiments demonstrate that BaThe effectively mitigates various types of jailbreak attacks and is adaptable to defend against unseen attacks, with minimal impact on MLLMs' performance.