ExploitGym：AI 代理在受控環境下的漏洞利用能力與邊界
ExploitGym 以 898 個真實漏洞測試 AI 代理的攻擊轉換能力。Claude Mythos Preview 與 GPT-5.5 在解除防禦下分別達成 157 與 120 次成功，但啟用 ASLR 等防護後成功率大幅下降。本文解析其機制、邊界與風險管理準則。
AI Agents
ExploitGym: AI Agents’ Exploitation Capabilities and Boundaries in Controlled Environments
ExploitGym tests AI agents’ ability to turn 898 real vulnerabilities into attacks. With defenses disabled, Claude Mythos Preview and GPT-5.5 achieved 157 and 120 successes respectively, but success rates dropped sharply after protections such as ASLR were enabled. This article examines its mechanisms, boundaries, and risk-management principles.
GDM AI Control Roadmap：為假設性的 AI 威脅建立防禦藍圖
當 AI Agent 逐漸具備自主能力，我們該如何防範尚未發生的風險？DeepMind 最新研究提出 TRAIT&R 分類法，搭配 D1–D4 偵測與 R1–R3 回應的分層防禦機制，為企業提供一套在威脅真正成形之前就能先行部署、並逐層驗證成效的安全藍圖。
GDM AI Control Roadmap: A Defensive Blueprint for Hypothetical AI Threats
As AI agents gain autonomy, how do you defend against risks that have not happened yet? DeepMind’s TRAIT&R taxonomy maps D1–D4 detection onto R1–R3 response.