Loading the catalog…
Loading the catalog…
AI新創Anthropic周二(9/29)警告,中國AI業者智譜(Z.ai)的GLM-5.3模型已具備自主開發端到端漏洞利用程式的能力,表現接近Anthropic今年推出的資安模型Claude Mythos Preview,但GLM-5.3的安全防護可透過簡單方法繞過,在模擬攻擊測試中的突破率最高達100%。
What RADAR observed and classified to build this opportunity. It is what the source published, not a verification that the offer is still active.
Anthropic警告智譜GLM-5.3具自主漏洞攻擊能力,安全防護容易遭繞過. AI新創Anthropic周二(9/29)警告,中國AI業者智譜(Z.ai)的GLM-5.3模型已具備自主開發端到端漏洞利用程式的能力,表現接近Anthropic今年推出的資安模型Claude Mythos Preview,但GLM-5.3的安全防護可透過簡單方法繞過,在模擬攻擊測試中的突破率最高達100%。
Open sourceThe catalog shows persisted RADAR opportunities. Storage availability does not mean sources are verified or offers are active.