Vals AI测试智能体自主入侵企业网络
AI 总结
Vals AI的CyberOffense基准用于测试AI智能体能否独立攻破逼真的模拟企业网络，所有操作均由外部记录并自动评分。据The Decoder报道，智能体可从Web应用推进至Windows服务器及管理员权限，更难的Lighthouse测试还涉及对第二家公司的横向入侵。报告的Nova领先者与得分存在矛盾，而Lighthouse结果据称由GPT-6 Sol Daybreak领先Deepseek V4.1 Flash 1017。
深度见解
该基准显示多种模型能在无人协助下执行多步骤网络入侵，但现有报道的Nova得分及领先者说法并不一致。
The gap between open and closed AI models in cyber capabilities keeps shrinking
Matthias Bastian View the LinkedIn Profile of Matthias Bastian
Nov 7, 2026
Nano Banana Pro prompted by THE DECODER
AI agents can break into realistic corporate networks on their own, Vals AI finds
#Vals AI#CyberOffense benchmark#GPT-6 Sol Daybreak#Deepseek V4.1 Flash 1017#Kimi K3.1 Pro#Meta Wonder#Grok 4.7#Kimi K3#GLM 5.3 Flash#OpenAI#AI Security Institute#Anthropic