JULI: Jailbreak Large Language Models by Self-Introspection

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Wang, Jesson, Hu, Zhanhao, Wagner, David
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866910046747623424
author Wang, Jesson
Hu, Zhanhao
Wagner, David
author_facet Wang, Jesson
Hu, Zhanhao
Wagner, David
contents Large Language Models (LLMs) are trained with safety alignment to prevent generating malicious content. Although some attacks have highlighted vulnerabilities in these safety-aligned LLMs, they typically have limitations, such as necessitating access to the model weights or the generation process. Since proprietary models through API-calling do not grant users such permissions, these attacks find it challenging to compromise them. In this paper, we propose Jailbreaking Using LLM Introspection (JULI), which jailbreaks LLMs by manipulating the token log probabilities, using a tiny plug-in block, BiasNet. JULI relies solely on the knowledge of the target LLM's predicted token log probabilities. It can effectively jailbreak API-calling LLMs under a black-box setting and knowing only top-$5$ token log probabilities. Our approach demonstrates superior effectiveness, outperforming existing state-of-the-art (SOTA) approaches across multiple metrics.
format Preprint
id arxiv_https___arxiv_org_abs_2505_11790
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle JULI: Jailbreak Large Language Models by Self-Introspection
Wang, Jesson
Hu, Zhanhao
Wagner, David
Machine Learning
Cryptography and Security
Large Language Models (LLMs) are trained with safety alignment to prevent generating malicious content. Although some attacks have highlighted vulnerabilities in these safety-aligned LLMs, they typically have limitations, such as necessitating access to the model weights or the generation process. Since proprietary models through API-calling do not grant users such permissions, these attacks find it challenging to compromise them. In this paper, we propose Jailbreaking Using LLM Introspection (JULI), which jailbreaks LLMs by manipulating the token log probabilities, using a tiny plug-in block, BiasNet. JULI relies solely on the knowledge of the target LLM's predicted token log probabilities. It can effectively jailbreak API-calling LLMs under a black-box setting and knowing only top-$5$ token log probabilities. Our approach demonstrates superior effectiveness, outperforming existing state-of-the-art (SOTA) approaches across multiple metrics.
title JULI: Jailbreak Large Language Models by Self-Introspection
topic Machine Learning
Cryptography and Security
url https://arxiv.org/abs/2505.11790