Metraipolis › archive › dc_f0baaa2c88e7

$M^3$: A Multi-LLM System for Multi-Turn Jailbreaking as a Markov Decision Process — arXiv:2610.31937

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.31937
License (as archived)
CC0-1.0
Archived
2026-10-26T19:47:37.335Z
SHA-256 of the archived text
e4b7d203acfdbb5b6fe15880b146b78ab560eaf076eec8f597e332dffd7659f9
Stable URL of this page
https://metraipolis.com/documento/dc_f0baaa2c88e7

How to cite

$M^3$: A Multi-LLM System for Multi-Turn Jailbreaking as a Markov Decision Process — arXiv:2610.31937 — arXiv (en), https://arxiv.org/abs/2610.31937 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f0baaa2c88e7 (Metraipolis archive dc_f0baaa2c88e7, sha256 e4b7d203acfdbb5b6fe15880b146b78ab560eaf076eec8f597e332dffd7659f9)
BibTeX
@misc{dcf0baaa2c88e7,
  title = {$M^3$: A Multi-LLM System for Multi-Turn Jailbreaking as a Markov Decision Process — arXiv:2610.31937},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.31937},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f0baaa2c88e7; sha256 e4b7d203acfdbb5b6fe15880b146b78ab560eaf076eec8f597e332dffd7659f9},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.31937. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Modern Large Language Models (LLMs) remain vulnerable to carefully orchestrated multi-turn interactions that progressively bypass safety mechanisms. However, many existing red-teaming approaches rely on heuristics or impose strong assumptions that limit their applicability in fully black box settings. We address this gap by introducing $M^3$, an automated red-teaming framework that formalizes multi-turn jailbreaking as a finite-horizon Markov Decision Process (MDP). In $M^3$, an attacker LLM interacts with a target LLM while operating over a compact internal state produced by a state LLM. Across two benchmarks and six target models, $M^3$ consistently outperforms state-of-the-art multi-turn red-teaming methods in Attack Success Rates (ASR), achieving improvements of up to 53% in ASR@5. Even with lightweight attacker, $M^3$ attains gains up to 26% in ASR@1 and 34% in ASR@5, compared to baselines that use higher capacity attackers. Beyond improved effectiveness, $M^3$ exhibits steeper risk escalation over conversational turns and achieves more consistent performance across risk categories (up to 4.82 improvement in Gini index) without relying on predefined risk taxonomy, providing a scalable and principled framework for multi-turn red-teaming and safety evaluation.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.31937 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-26T19:45:33.271Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).