ARMOR: Aligning Secure and Safe Large Language Models via Meticulous Reasoning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhao, Zhengyue, Ma, Yingzi, Jha, Somesh, Pavone, Marco, McDaniel, Patrick, Xiao, Chaowei
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909855662473216
author Zhao, Zhengyue
Ma, Yingzi
Jha, Somesh
Pavone, Marco
McDaniel, Patrick
Xiao, Chaowei
author_facet Zhao, Zhengyue
Ma, Yingzi
Jha, Somesh
Pavone, Marco
McDaniel, Patrick
Xiao, Chaowei
contents Large Language Models have shown impressive generative capabilities across diverse tasks, but their safety remains a critical concern. Existing post-training alignment methods, such as SFT and RLHF, reduce harmful outputs yet leave LLMs vulnerable to jailbreak attacks, especially advanced optimization-based ones. Recent system-2 approaches enhance safety by adding inference-time reasoning, where models assess potential risks before producing responses. However, we find these methods fail against powerful out-of-distribution jailbreaks, such as AutoDAN-Turbo and Adversarial Reasoning, which conceal malicious goals behind seemingly benign prompts. We observe that all jailbreaks ultimately aim to embed a core malicious intent, suggesting that extracting this intent is key to defense. To this end, we propose ARMOR, which introduces a structured three-step reasoning pipeline: (1) analyze jailbreak strategies from an external, updatable strategy library, (2) extract the core intent, and (3) apply policy-based safety verification. We further develop ARMOR-Think, which decouples safety reasoning from general reasoning to improve both robustness and utility. Evaluations on advanced optimization-based jailbreaks and safety benchmarks show that ARMOR achieves state-of-the-art safety performance, with an average harmful rate of 0.002 and an attack success rate of 0.06 against advanced optimization-based jailbreaks, far below other reasoning-based models. Moreover, ARMOR demonstrates strong generalization to unseen jailbreak strategies, reducing their success rate to zero. These highlight ARMOR's effectiveness in defending against OOD jailbreak attacks, offering a practical path toward secure and reliable LLMs.
format Preprint
id arxiv_https___arxiv_org_abs_2507_11500
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle ARMOR: Aligning Secure and Safe Large Language Models via Meticulous Reasoning
Zhao, Zhengyue
Ma, Yingzi
Jha, Somesh
Pavone, Marco
McDaniel, Patrick
Xiao, Chaowei
Cryptography and Security
Large Language Models have shown impressive generative capabilities across diverse tasks, but their safety remains a critical concern. Existing post-training alignment methods, such as SFT and RLHF, reduce harmful outputs yet leave LLMs vulnerable to jailbreak attacks, especially advanced optimization-based ones. Recent system-2 approaches enhance safety by adding inference-time reasoning, where models assess potential risks before producing responses. However, we find these methods fail against powerful out-of-distribution jailbreaks, such as AutoDAN-Turbo and Adversarial Reasoning, which conceal malicious goals behind seemingly benign prompts. We observe that all jailbreaks ultimately aim to embed a core malicious intent, suggesting that extracting this intent is key to defense. To this end, we propose ARMOR, which introduces a structured three-step reasoning pipeline: (1) analyze jailbreak strategies from an external, updatable strategy library, (2) extract the core intent, and (3) apply policy-based safety verification. We further develop ARMOR-Think, which decouples safety reasoning from general reasoning to improve both robustness and utility. Evaluations on advanced optimization-based jailbreaks and safety benchmarks show that ARMOR achieves state-of-the-art safety performance, with an average harmful rate of 0.002 and an attack success rate of 0.06 against advanced optimization-based jailbreaks, far below other reasoning-based models. Moreover, ARMOR demonstrates strong generalization to unseen jailbreak strategies, reducing their success rate to zero. These highlight ARMOR's effectiveness in defending against OOD jailbreak attacks, offering a practical path toward secure and reliable LLMs.
title ARMOR: Aligning Secure and Safe Large Language Models via Meticulous Reasoning
topic Cryptography and Security
url https://arxiv.org/abs/2507.11500