Saved in:
Bibliographic Details
Main Authors: Ha, Junwoo, Kim, Hyunjun, Yu, Sangyoon, Park, Haon, Yousefpour, Ashkan, Park, Yuna, Kim, Suhyun
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2503.04856
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918114948546560
author Ha, Junwoo
Kim, Hyunjun
Yu, Sangyoon
Park, Haon
Yousefpour, Ashkan
Park, Yuna
Kim, Suhyun
author_facet Ha, Junwoo
Kim, Hyunjun
Yu, Sangyoon
Park, Haon
Yousefpour, Ashkan
Park, Yuna
Kim, Suhyun
contents We introduce a novel framework for consolidating multi-turn adversarial ``jailbreak'' prompts into single-turn queries, significantly reducing the manual overhead required for adversarial testing of large language models (LLMs). While multi-turn human jailbreaks have been shown to yield high attack success rates, they demand considerable human effort and time. Our multi-turn-to-single-turn (M2S) methods -- Hyphenize, Numberize, and Pythonize -- systematically reformat multi-turn dialogues into structured single-turn prompts. Despite removing iterative back-and-forth interactions, these prompts preserve and often enhance adversarial potency: in extensive evaluations on the Multi-turn Human Jailbreak (MHJ) dataset, M2S methods achieve attack success rates from 70.6 percent to 95.9 percent across several state-of-the-art LLMs. Remarkably, the single-turn prompts outperform the original multi-turn attacks by as much as 17.5 percentage points while cutting token usage by more than half on average. Further analysis shows that embedding malicious requests in enumerated or code-like structures exploits ``contextual blindness'', bypassing both native guardrails and external input-output filters. By converting multi-turn conversations into concise single-turn prompts, the M2S framework provides a scalable tool for large-scale red teaming and reveals critical weaknesses in contemporary LLM defenses.
format Preprint
id arxiv_https___arxiv_org_abs_2503_04856
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle M2S: Multi-turn to Single-turn jailbreak in Red Teaming for LLMs
Ha, Junwoo
Kim, Hyunjun
Yu, Sangyoon
Park, Haon
Yousefpour, Ashkan
Park, Yuna
Kim, Suhyun
Computation and Language
Artificial Intelligence
We introduce a novel framework for consolidating multi-turn adversarial ``jailbreak'' prompts into single-turn queries, significantly reducing the manual overhead required for adversarial testing of large language models (LLMs). While multi-turn human jailbreaks have been shown to yield high attack success rates, they demand considerable human effort and time. Our multi-turn-to-single-turn (M2S) methods -- Hyphenize, Numberize, and Pythonize -- systematically reformat multi-turn dialogues into structured single-turn prompts. Despite removing iterative back-and-forth interactions, these prompts preserve and often enhance adversarial potency: in extensive evaluations on the Multi-turn Human Jailbreak (MHJ) dataset, M2S methods achieve attack success rates from 70.6 percent to 95.9 percent across several state-of-the-art LLMs. Remarkably, the single-turn prompts outperform the original multi-turn attacks by as much as 17.5 percentage points while cutting token usage by more than half on average. Further analysis shows that embedding malicious requests in enumerated or code-like structures exploits ``contextual blindness'', bypassing both native guardrails and external input-output filters. By converting multi-turn conversations into concise single-turn prompts, the M2S framework provides a scalable tool for large-scale red teaming and reveals critical weaknesses in contemporary LLM defenses.
title M2S: Multi-turn to Single-turn jailbreak in Red Teaming for LLMs
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2503.04856