Metraipolis › archive › dc_9ddfc2f0f642
BrainwashedLLM: Jailbreaking via Automated Adversarial Chain of Thoughts Discovery — arXiv:2611.04717
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.04717
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-04T21:49:43.282Z
- SHA-256 of the archived text
c0d9240cad778223cbf7b4876e2f6c708880731cad5d84b54ff9d3993b819044- Stable URL of this page
https://metraipolis.com/documento/dc_9ddfc2f0f642
How to cite
BrainwashedLLM: Jailbreaking via Automated Adversarial Chain of Thoughts Discovery — arXiv:2611.04717 — arXiv (en), https://arxiv.org/abs/2611.04717 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_9ddfc2f0f642 (Metraipolis archive dc_9ddfc2f0f642, sha256 c0d9240cad778223cbf7b4876e2f6c708880731cad5d84b54ff9d3993b819044)
BibTeX
@misc{dc9ddfc2f0f642,
title = {BrainwashedLLM: Jailbreaking via Automated Adversarial Chain of Thoughts Discovery — arXiv:2611.04717},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.04717},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_9ddfc2f0f642; sha256 c0d9240cad778223cbf7b4876e2f6c708880731cad5d84b54ff9d3993b819044},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.04717. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Large Reasoning Models (LRMs) achieve strong performance on complex tasks by generating explicit Chain-of-Thought (CoT) reasoning, but the safety implications of this intermediate reasoning surface remain underexplored. We demonstrate that the reasoning trace itself is a powerful attack vector. Safety alignment in large models is substantially less robust to malicious reasoning embedded in the context than to direct imperative prompts. We introduce BrainwashedLLM, a weak-to-strong adversarial framework that automates the discovery of reasoning-based jailbreaks. First, we use Group Relative Policy Optimization (GRPO), a Reinforcement Learning (RL) algorithm, with a multi-objective rule-based reward to fine-tune a small, white-box source model to generate adversarial reasoning traces. Crucially, the reward is computed entirely over the source's own reasoning trace. Second, we show that these traces transfer in a zero-shot manner. When traces are injected as input prefixes, they steer larger black-box LRMs to continue the adversarial reasoning and produce harmful outputs, without requiring prompt optimization, gradient access, or any form of output feedback from the target model. Across four state-of-the-art LRMs that span distinct architectures, BrainwashedLLM achieves ASR@5 between 0.74 and 0.98 across targets, within 16 points of query-based baselines, without querying the target during attack construction. To our knowledge, this is the first framework to use RL to directly optimize the CoT of LRMs as an attack surface without any target feedback, and the first to demonstrate zero-shot weak-to-strong transfer of reasoning traces. Our results suggest that exposed CoT is a vulnerability in LRMs and motivate architectural defenses that isolate the reasoning buffer. Warning: This paper contains potentially offensive and harmful text. Tema degli esploratori: fiducia digitale e crittografia (elenco arXiv cs.CR, nuovi lavori del giorno). Categorie arXiv: Cryptography and Security (cs.CR). Pagina del lavoro: https://arxiv.org/abs/2611.04717 — 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 2026-11-04T21:38:19.530Z dalla pagina https://arxiv.org/list/cs.CR/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).