揭示复杂任务中隐藏恶意意图的智能体安全脆弱性
How Brittle is Agent Safety? Rethinking Agent Risk under Intent Concealment and Task Complexity
- 构建双维度评估框架，分析意图隐蔽与任务复杂度对安全的影响
- 发现意图越隐蔽，安全对齐越差；难题反而更安全因能力受限
- 发布OASIS基准和仿真环境，支持深度安全测试
当前大模型驱动智能体的安全评估主要聚焦于单一危害，未能涵盖恶意意图被隐藏或稀释在复杂任务中的高阶威胁。本文通过意图隐蔽性与任务复杂度两个正交维度，系统分析智能体安全的脆弱性。为此，提出OASIS（Orthogonal Agent Safety Inquiry Suite）——一个分层结构的基准测试体系，包含细粒度标注和高保真仿真沙箱。研究发现：随着意图逐渐隐蔽，安全对齐显著且可预测地下降；同时出现“复杂度悖论”——复杂任务上表现看似更安全，实则源于智能体能力不足。通过开源OASIS及其仿真环境，为探索并强化这些被忽视维度下的智能体安全提供可靠基础。
原文摘要 · Abstract (English)
Current safety evaluations for LLM-driven agents primarily focus on atomic harms, failing to address sophisticated threats where malicious intent is concealed or diluted within complex tasks. We address this gap with a two-dimensional analysis of agent safety brittleness under the orthogonal pressures of intent concealment and task complexity. To enable this, we introduce OASIS (Orthogonal Agent Safety Inquiry Suite), a hierarchical benchmark with fine-grained annotations and a high-fidelity simulation sandbox. Our findings reveal two critical phenomena: safety alignment degrades sharply and predictably as intent becomes obscured, and a "Complexity Paradox" emerges, where agents seem safer on harder tasks only due to capability limitations. By releasing OASIS and its simulation environment, we provide a principled foundation for probing and strengthening agent safety in these overlooked dimensions.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。