Artemis Security 发布 Orion-1
面向企业网络攻防调查与响应的专用安全模型。
为什么重要
为安全团队提供比通用模型更贴近攻防调查的专用 AI 方案。
阅读原文the-decoder.com
AI 解读（根据原文生成）
Artemis Security 发布 Orion-1，用于自主调查和响应企业网络攻击。模型处理来自认证服务、云环境、终端、SaaS 应用和网络设备的日志，把分散信号关联到单一攻击者，并给出置信度、结论及响应建议或执行处置。公司称其基于自身安全运营任务微调，未使用客户数据训练，并提出 DGR 基准评估安全决策可信度。Orion-1 目前在 Artemis 平台面向部分客户私人预览。
要点（AI 据原文整理，数字均已与原文核对）
- Orion-1 processes log data from auth services, cloud setups, corporate endpoints, SaaS apps, and network gear.
- No customer data was used during training, the company says.
- Artemis developed a benchmark called "Decision-Grade Readiness" (DGR) for the comparison.
- The thousands of tasks all have known outcomes, and some contain no attack at all or include benign data designed to look malicious.
- In attack reconstruction, Orion-1 scored 80.8 compared to 58.3 for the next-best model.
- Orion-1 is live in a private preview for select customers on the Artemis platform.
