跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2603.17673 · v3

Towards Reliable Local Security Agents: Verifiable Post-Training for Linux Privilege Escalation

首次提交 2026-03-18 20:52
版本更新 2026-11-17 08:30
雷达观测 2026-11-18 19:43
arXiv ↗PDF ↗

摘要

LLM agents are increasingly important in security, yet leading systems are typically closed-source and cloud-hosted, limiting reproducibility and their use with sensitive data. This creates a need for small, local models that can perform security tasks under strict resource constraints, though effective methods for developing them remain underexplored. In this paper, we address this gap by proposing a two-stage post-training recipe that turns a small local language model into a security agent. To this end, we focus on Linux privilege escalation as a representative setting to systematically study the training of local models, as the task is automatically verifiable and requires multi-step interactive reasoning. Using an experimental setup that mitigates benchmark leakage, we post-train a small 4B model in two stages: supervised fine-tuning on traces from procedural privilege-escalation environments, followed by reinforcement learning with verifiable rewards. On a held-out benchmark of 12 Linux privilege-escalation scenarios, supervised fine-tuning nearly doubles the baseline success rate under a tight budget of 20 interaction rounds, and subsequent reinforcement learning improves our model, PrivEsc-LLM 4B, to 93.3% success, ahead of all other evaluated models that fit a single consumer GPU. At the same time, its expected inference cost per successful escalation is more than 80x lower than that of Claude Opus 4.7. Our findings show that small local models can be adapted to complex security tasks. We document the challenges involved and offer guidance for transferring this recipe to other settings.

作者备注:Accepted at the 42nd Annual Computer Security Applications Conference (ACSAC 2026). Artifacts Available, Functional, and Reproduced

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 v3,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。

v3 · 2026-11-17 08:30 · 最新观测版本

Towards Reliable Local Security Agents: Verifiable Post-Training for Linux Privilege Escalation

LLM agents are increasingly important in security, yet leading systems are typically closed-source and cloud-hosted, limiting reproducibility and their use with sensitive data. This creates a need for small, local models that can perform security tasks under strict resource constraints, though effective methods for developing them remain underexplored. In this paper, we address this gap by proposing a two-stage post-training recipe that turns a small local language model into a security agent. To this end, we focus on Linux privilege escalation as a representative setting to systematically study the training of local models, as the task is automatically verifiable and requires multi-step interactive reasoning. Using an experimental setup that mitigates benchmark leakage, we post-train a small 4B model in two stages: supervised fine-tuning on traces from procedural privilege-escalation environments, followed by reinforcement learning with verifiable rewards. On a held-out benchmark of 12 Linux privilege-escalation scenarios, supervised fine-tuning nearly doubles the baseline success rate under a tight budget of 20 interaction rounds, and subsequent reinforcement learning improves our model, PrivEsc-LLM 4B, to 93.3% success, ahead of all other evaluated models that fit a single consumer GPU. At the same time, its expected inference cost per successful escalation is more than 80x lower than that of Claude Opus 4.7. Our findings show that small local models can be adapted to complex security tasks. We document the challenges involved and offer guidance for transferring this recipe to other settings.

查看此版本解读 →查看此版本原文 ↗