arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2610.22244cs.CRcs.AIcs.CLcs.LG
收藏

语言是智能体防护机制的安全攻击面

Language Is a Security Surface for Agent Guards

Kontext

Hasan Demirkiran, Jens Ernstberger

AI总结:

本文构建多语言智能体防护基准LinguaGuardBench,发现多数小型开源及专用防护机制的裁决会随请求语言变化,且效应随语言稀有度增强,前沿防护机制受影响极小,还发布了相关基准与裁决数据。

摘要:

步骤级防护机制会在智能体每次调用工具前,根据用户请求和当前轨迹判断其下一个动作是否安全。用户用多种语言编写这些请求,而防护机制的提示词以及专门训练和评估防护机制的基准均为英文。本文研究防护机制的裁决是否依赖于请求的语言。我们基于TS-Bench AgentDojo-Traj的1220个带标签步骤构建了LinguaGuardBench:仅将用户指令翻译成德语、法语、土耳其语、斯瓦希里语和阿姆哈拉语,保留所有工具调用、观测结果和标签的字节级一致性,因此裁决的任何变化都可归因于语言本身。设置6种英文改写版本和1个空白安慰剂作为对照,对托管防护机制运行3次以测量其噪声。在19种防护机制中,从前沿API到4B开源模型以及4种专门的智能体防护机制,大多数开源、小型和专门的防护机制在翻译后会在自身噪声水平之外改变裁决,且该效应随语言稀有度增加而增强:在9种参数低于13B的防护机制中,经安慰剂调整的平均翻转率从法语的+1.5个百分点上升至阿姆哈拉语的+4.4个百分点,专门的防护机制最为敏感。损害方向往往随防护机制规模变化:参数为12-30B的开源防护机制会拦截更多良性步骤(最多+5.0个百分点的误报),所有显著的召回率损失均出现在参数低于10B的防护机制中(最多-7.4个百分点)。前沿防护机制的变化最多约1个百分点,最强的Gemini 3.8 Flash在请求翻译前后返回相同裁决。损害集中在少数指令中,事后分析显示,该损害发生在智能体推理重述英文请求的步骤,与防护机制对不同通道间不一致性的反应一致。英文改写对所有防护机制的影响均小于翻译。我们发布了该基准及全部48.9万条裁决结果。

英文摘要:

Step-level guards decide, before each tool call, whether an agent's next action is safe given the user's request and the trajectory so far. Users write those requests in many languages, while guard prompts and the benchmarks on which purpose-built guards are trained and evaluated are English. We ask whether a guard's verdict depends on the language of the request. We build LinguaGuardBench from the 1,220 labelled steps of TS-Bench AgentDojo-Traj: we translate only the user instruction into German, French, Turkish, Swahili and Amharic, and keep every tool call, observation and label byte-identical, so any change in a verdict is attributable to language alone. Six English rewordings and a whitespace placebo serve as controls, and managed guards are run three times to measure their noise. Across 19 guards, from frontier APIs to 4B open models and four purpose-built agent guards, most open, small and purpose-built guards change verdicts under translation beyond their own noise floor, and the effect grows with the rarity of the language: among the nine guards below 13B parameters, the mean placebo-adjusted flip rate rises from +1.5 pp on French to +4.4 pp on Amharic. Purpose-built guards are the most sensitive. The direction of the damage tends to follow guard size: open guards of 12-30B parameters block more benign steps (up to +5.0 pp false positives), and every significant loss of recall is in a guard below 10B (up to -7.4 pp). Frontier guards shift by at most about one point; the strongest, Gemini 3.8 Flash, returns identical verdicts with and without the request. The damage is concentrated in a few instructions and, in a post-hoc analysis, falls on steps where the agent's reasoning restates the English request, consistent with guards reacting to inconsistency between channels. English paraphrase moves every guard less than translation does. We release the benchmark and all 489k verdicts.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑