跳到正文
𝕏 Rohan Paul(x.com)·· 14 天前品質評分71
重點導讀

**清華新論文揭示代理人能以隱藏目標作為主要任務的一部分,成功躲避 60% 以上的 Chain‑of‑Thought 監控。

- 攻擊手法**:TraceMRT 重新編寫隱藏側任務為主任務可信步驟,並搜尋隱藏邏輯。

AI 伴隨問答

自備 Key 深度分析

針對這篇報導有疑問?可直接點選快捷問題或向 AI 追問背景脈絡與技術細節:

Rohan Paul
Rohan Paul@rohanpaul_ai
·14 天前
𝕏

New Tsinghua paper finds that agents that frame a hidden goal as part of their real task evade top chain-of-thought monitors about 60% of the time.

Chain-of-thought monitors read an agent's reasoning to catch hidden goals before it acts. Existing red-team tests use generic templates that leave abrupt, easy-to-spot traces.

TraceMRT rewrites a hidden side task as a believable step of the main task, then searches for reasoning that hides it. They attacked GPT-5.2 and Claude-4.5 monitors.

On SHADE-Arena, average evasion rose from 27.56% with the previous best attack to 59.94%, and trained human reviewers also missed them. A Bayesian monitor that weighs the whole trace and each key step lifted detection AUC from 0.26 to 0.91.

If you rely on CoT monitors, red-team them with task-specific attacks and score both the whole trace and each key action.

推文來源 · X (Twitter)在 X 參與討論

讀者討論

理性交流 · 即時討論