跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2607.27951 · v2

LLM Misuse Safeguards Rely on Untrusted Input: A Widespread, High-Risk Vulnerability

首次提交 2026-07-30 17:59
版本更新 2026-11-18 00:34
雷达观测 2026-11-18 16:38
arXiv ↗PDF ↗

摘要

Large language models now help professionals in fields such as cybersecurity and biology, yet the same answers would help an attacker. Deployers rely on misuse safeguards to keep such answers from attackers. We find that these safeguards share a high-risk vulnerability: they decide whether to release an answer from what users write, including the professional identity or purpose they claim, and anyone can write such a claim. Threat reports from model vendors and security firms show that attackers who fabricate a professional identity or purpose already exploit this vulnerability to cause serious harm. The vulnerability is also widespread across the state of the art: every defense proposed in 129 papers from the latest editions of 12 top venues has it. Safeguard research studies the wrong object: it treats harm as a property of the text of a request, although the same text can come from a professional or an attacker. Current safeguard benchmarks therefore cannot reveal the vulnerability: a safeguard can score high on them and still give dangerous answers to attackers. Because the vulnerability lies in what users write, no improvement in how safeguards judge that writing can close it. Under the patch we propose, large language models can help professionals without giving dangerous capabilities to anyone who merely claims to be one.

作者备注:13 pages, 4 tables. This work has been submitted to the IEEE for possible publication. Copyright may be transferred without notice, after which this version may no longer be accessible

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 00:34 · 最新观测版本

LLM Misuse Safeguards Rely on Untrusted Input: A Widespread, High-Risk Vulnerability

Large language models now help professionals in fields such as cybersecurity and biology, yet the same answers would help an attacker. Deployers rely on misuse safeguards to keep such answers from attackers. We find that these safeguards share a high-risk vulnerability: they decide whether to release an answer from what users write, including the professional identity or purpose they claim, and anyone can write such a claim. Threat reports from model vendors and security firms show that attackers who fabricate a professional identity or purpose already exploit this vulnerability to cause serious harm. The vulnerability is also widespread across the state of the art: every defense proposed in 129 papers from the latest editions of 12 top venues has it. Safeguard research studies the wrong object: it treats harm as a property of the text of a request, although the same text can come from a professional or an attacker. Current safeguard benchmarks therefore cannot reveal the vulnerability: a safeguard can score high on them and still give dangerous answers to attackers. Because the vulnerability lies in what users write, no improvement in how safeguards judge that writing can close it. Under the patch we propose, large language models can help professionals without giving dangerous capabilities to anyone who merely claims to be one.

查看此版本解读 →查看此版本原文 ↗