English(EN) APEX-Harm: Evaluating Agent Safety in Shared Professional Workspaces

新的APEX-Harm基准测试AI代理对注入攻击的安全性

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-09 00:00

一个名为APEX-Harm的新基准已被开发出来，用于评估AI代理在共享专业工作空间中的安全性，特别是针对注入攻击。该基准模拟了涉及金融、咨询和法律任务的现实场景，包含大量文件和工具。测试显示，即使是Opus 5和Sonnet 5等模型，虽然总体攻击成功率较低，但也容易受到特定任务脚本替换和通用脚本攻击的攻击，这表明正确完成任务并不保证行为安全。 AI

影响突出了当前AI代理的关键漏洞，表明除了完成任务之外，还需要加强安全措施。

排序理由该集群描述了一篇介绍AI安全基准的新学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 Hugging Face Daily Papers 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 0 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群描述了一篇介绍AI安全基准的新学术论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, safety; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: 8 days old; Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

报道来源 [1]

Hugging Face Daily Papers TIER_1 English(EN) · 2026-10-09 00:00

APEX-Harm: 评估共享专业工作空间中的代理安全

APEX-Harm evaluates long-horizon agent vulnerabilities to injection attacks across large multi-tool workspaces, revealing high success rates for script-based attacks despite correct task outputs.

本文如何被排名

报道来源 [1]

APEX-Harm: 评估共享专业工作空间中的代理安全

相关实体

相关话题