AutoJailbreak: Exploring Jailbreak Attacks and Defenses through a Dependency Lens

Authors: Lin Lu, Hai Yan, Zenghui Yuan, Jiawen Shi, Wenqi Wei, Pin-Yu Chen, Pan Zhou
Published: 2024-06-06

Source: https://arxiv.org/abs/2406.03805

PDF: https://arxiv.org/pdf/2406.03805

Labels Predicted by AI

防御手法 プロンプトインジェクション LLM性能評価

Please note that these labels were automatically added by AI. Therefore, they may not be entirely accurate.
For more details, please see the About the Literature Database page.

Abstract

Jailbreak attacks in large language models (LLMs) entail inducing the models to generate content that breaches ethical and legal norm through the use of malicious prompts, posing a substantial threat to LLM security. Current strategies for jailbreak attack and defense often focus on optimizing locally within specific algorithmic frameworks, resulting in ineffective optimization and limited scalability. In this paper, we present a systematic analysis of the dependency relationships in jailbreak attack and defense techniques, generalizing them to all possible attack surfaces. We employ directed acyclic graphs (DAGs) to position and analyze existing jailbreak attacks, defenses, and evaluation methodologies, and propose three comprehensive, automated, and logical frameworks. AutoAttack investigates dependencies in two lines of jailbreak optimization strategies: genetic algorithm (GA)-based attacks and adversarial-generation-based attacks, respectively. We then introduce an ensemble jailbreak attack to exploit these dependencies. AutoDefense offers a mixture-of-defenders approach by leveraging the dependency relationships in pre-generative and post-generative defense strategies. AutoEvaluation introduces a novel evaluation method that distinguishes hallucinations, which are often overlooked, from jailbreak attack and defense responses. Through extensive experiments, we demonstrate that the proposed ensemble jailbreak attack and defense framework significantly outperforms existing research.