跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2608.25697 · v2

Language Model Security Modules: Turning LLM Interpretability into Runtime Defense

首次提交 2026-08-26 20:13
版本更新 2026-11-18 22:43
雷达观测 2026-11-19 15:04
arXiv ↗PDF ↗

摘要

Large language models (LLMs) are served behind layered defenses such as alignment and guardrail models, yet jailbreaks still get through. Interpretability research looks inside the model, where methods such as probes and sparse autoencoders expose signals of harmful content during generation. A signal alone, however, is not a defense. To become one, the serving system must tie each signal to the right request, apply the policy as declared, and release output only when the policy allows. Today, defenses built on such signals handle these duties on their own, so every new detector needs its own integration. Yet none of these duties depends on how a signal is computed. We present Language Model Security Modules (LMSM), which adapts the design of Linux Security Modules to LLM serving and carries out these duties once in a shared mediation path. The path hosts pluggable backends that turn model internals into evidence and policies that decide what that evidence allows. Each policy declares the evidence and evaluations it needs, and LMSM provides exactly these for each request and verifies that they took place, so a failure is never mistaken for permission. Protection therefore remains cheap and correct under common serving optimizations. We evaluate LMSM in vLLM, with both eager and compiled execution, on Qwen3-4B and Gemma-3-4B with fitted probes, a released transcoder, and a released sparse autoencoder. With vLLM's default optimizations on, every backend keeps at least 96% of native throughput, and all of them share the same mediation path. On Qwen3-4B, a representative probe-based policy cuts HarmBench attack success from 39.4% to 3.3% while XSTest false refusals rise from 0.8% to 3.1%. LMSM lets existing and future interpretability methods become runtime defenses without rebuilding the serving path.

作者备注:17 pages, 7 figures, 6 tables. Code: https://github.com/xiuyuz/LMSM

AI 论文解读

基于摘要 · 非全文审阅

此版本尚未生成 AI 解读。解读由后台任务生成并按论文版本保存,登录后共享已有结果。

版本差异

本站首次收录为 v2,暂无更早版本可对照。

观测到的版本

相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。

v2 · 2026-11-18 22:43 · 最新观测版本

Language Model Security Modules: Turning LLM Interpretability into Runtime Defense

Large language models (LLMs) are served behind layered defenses such as alignment and guardrail models, yet jailbreaks still get through. Interpretability research looks inside the model, where methods such as probes and sparse autoencoders expose signals of harmful content during generation. A signal alone, however, is not a defense. To become one, the serving system must tie each signal to the right request, apply the policy as declared, and release output only when the policy allows. Today, defenses built on such signals handle these duties on their own, so every new detector needs its own integration. Yet none of these duties depends on how a signal is computed. We present Language Model Security Modules (LMSM), which adapts the design of Linux Security Modules to LLM serving and carries out these duties once in a shared mediation path. The path hosts pluggable backends that turn model internals into evidence and policies that decide what that evidence allows. Each policy declares the evidence and evaluations it needs, and LMSM provides exactly these for each request and verifies that they took place, so a failure is never mistaken for permission. Protection therefore remains cheap and correct under common serving optimizations. We evaluate LMSM in vLLM, with both eager and compiled execution, on Qwen3-4B and Gemma-3-4B with fitted probes, a released transcoder, and a released sparse autoencoder. With vLLM's default optimizations on, every backend keeps at least 96% of native throughput, and all of them share the same mediation path. On Qwen3-4B, a representative probe-based policy cuts HarmBench attack success from 39.4% to 3.3% while XSTest false refusals rise from 0.8% to 3.1%. LMSM lets existing and future interpretability methods become runtime defenses without rebuilding the serving path.

查看此版本解读 →查看此版本原文 ↗