GLM模型如何帮助OpenAI安全团队识别后门，了解AI安全事件的防御策略。
ClementDelangue回应了关于OpenAI安全事件的讨论。GLM模型帮助团队识别了后门，支持了安全防御工作。安全团队采用了检测、理解、控制和修复的防御策略，而非实时对抗。OpenAI事件结束后，攻击者仍在尝试探测系统，凸显了持续防御的重要性。
https://t.co/kPNpih2lnD
x.com/ClementDelangu… clem 🤗 @ClementDelangue Great blogpost! On the paragraph below, not sure what you mean by 'real-time defense'. Nobody fights attackers in a live sword-fight; defense is detect, understand, contain, remediate in different timeframes depending on the criticality of the issue. Here it was deemed by the team not super critical (and rightly so) so this is why it took a few days rather than a few minutes or hours. We did the initial cut the old-fashioned way, Monday, over a week before OAI even realized there was even a problem. GLM then helped us identify the backdoors they'd planted so we could cut them, which is defense, not archaeology. And the die-off at OpenAI didn't end anything; agents were still probing us after we closed the doors, which is why containment mattered. Detection and understanding are most of the game in cyber-security, and open models are what let us do that part without asking anyone's permission and without sharing our most important confidential data which is the point most people have been making I feel like. 🔗 View Quoted Tweet 💬 1 🔄 0 ❤️ 1 👀 1020 📊 1 ⚡