OpenAI Security Response GLM
https://t.co/kPNpih2lnD
OpenAI's response shows how open-source models enable security detection without sharing confidential data, contrasting with proprietary alternatives.
OpenAI security team responded to a breach on Monday, over a week before OpenAI realized the problem. GLM helped identify backdoors planted by attackers, allowing containment. The team followed a detect, understand, contain, remediate approach based on issue criticality. Agents continued probing after the breach was closed.
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 ⚡
