去年12月下旬OpenAI公布新的AI模型o3、o3-mini预览版本，并引入新的安全功能“审议一致（Deliberative Alignment）”，借由这项机制，OpenAI号称AI模型将高度遵守他们的安全策略，改善原有模型容易被越狱的情况。但在1月底o3-mini正式推出不久，有研究人员指出，他们成功突破这项防护，让该AI模型指导如何对Windows组件本机安全认证子系统服务（lsass.e ...

from Endpoint Detection and Response (EDR) logs, focusing on specific command-line ...

Expand Energy Corporation operates as an independent exploration and production company in the United States. It engages in acquisition, exploration, and development of properties to produce oil ...

During red team operations, stealth is a critical component. We spend a great deal of time ensuring our payloads will evade ...

Microsoft is publishing for the first time our research into a subgroup within the Russian state actor Seashell Blizzard and ...

We read every piece of feedback, and take your input very seriously.