# LMSM：借鉴 Linux 安全模块的 LLM 安全框架

- 来源：HuggingFace Daily Papers（社区热门论文）
- 发布时间：2026-08-26 08:00
- AIHOT 分数：45
- AIHOT 链接：https://aihot.virxact.com/items/cmtgmdkaf0301rochys9pt7hs
- 原文链接：https://arxiv.org/abs/2608.25697

## AI 摘要

LMSM 将 Linux Security Modules 的分离设计引入 LLM 服务，通过安全后端、版本化策略与独立门控分离调解正确性与策略有效性，支持在不重建请求处理的情况下更换后端、规则或调度。

## 正文

Large language models (LLMs) are increasingly deployed with layered defenses, yet malicious prompts can still bypass them. Interpretability methods can expose model-internal signals along the generation path that could inform enforcement, but these signals are not security controls by themselves. Deployments that adapt them for safety typically couple each signal to its own calibration, policy logic, and intervention code, so each new artifact creates integration work instead of strengthening a shared defense. We present Language Model Security Modules (LMSM), a security framework that adapts the separation behind Linux Security Modules (LSM) to LLM serving. In LMSM, a selected security backend exposes calibrated evidence, a versioned policy evaluates active rules over trusted per-request context, and a separate gate authorizes buffered output release. This design separates mediation correctness from policy effectiveness, and it allows backend, rule, or schedule changes without rebuilding request handling or enforcement. Our prototype shows the separation working in practice: with Hugging Face Transformers and continuously batched vLLM, the same substrate hosts artifact-backed sparse autoencoder (SAE) and transcoder deployments and task-fitted dense probes, preserves request-specific decisions under scheduler churn, and selectively enforces and composes multiple rules per request. On Qwen3-4B, LMSM-Checkpoint reduces HarmBench attack success rate from 39.20% to 3.32%, with XSTest false refusals rising from 2.40% to 4.40%, while retaining 98.14% of the throughput of a matched serving path that performs no monitoring work at 32 active sequences. LMSM gives advances in interpretability and model-internal analysis a common path to runtime enforcement.