首页> 外国专利> SYSTEM AND METHOD FOR SECURITY MANAGEMENT BASED ARTIFICIAL INTELLIGENCE USING FEDERATED LEARNING

SYSTEM AND METHOD FOR SECURITY MANAGEMENT BASED ARTIFICIAL INTELLIGENCE USING FEDERATED LEARNING

机译:基于安全管理的人工智能使用联合学习的系统和方法

摘要

An artificial intelligence-based security control method through federated learning according to the present invention comprises the steps of (a) generating an initial detection model using cyber threat data possessed by the upper control system; (b) distributing, by the upper level control system, parameter information of the initial detection model to a plurality of lower level control systems; c) detecting, by the subordinate control system, the cyber threat data that is continuously collected in real time by generating an initial detection model with the parameter information and then operating it; (d) generating a new threat detection model after the subordinate control system learns an initial detection model using cyber threat data; (e) distributing, by the upper level control system, a new detection model generated with the parameters of the new threat detection model; and (f) the lower level control system detects a cyber threat with the new detection model. .
机译:根据本发明的联合学习的基于人工智能的安全控制方法包括使用上控制系统所拥有的网络威胁数据生成初始检测模型的步骤; (b)通过上层控制系统分配初始检测模型的参数信息到多个下层控制系统; c)通过从属控制系统检测,通过使用参数信息生成初始检测模型并操作它来实时地实时收集网络威胁数据; (d)在从属控制系统使用网络威胁数据学习初始检测模型后生成新的威胁检测模型; (e)通过上层控制系统分发,使用新的威胁检测模型的参数产生的新检测模型; (f)较低级别的控制系统检测到具有新检测模型的网络威胁。 。

著录项

相似文献

  • 专利
  • 外文文献
  • 中文文献
获取专利

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号