• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>Accelerating Space Commerce, Exploration, and New Discocery Conference >Building cyber resilience in space assets with real-time autonomous Graph Database Anomaly Detection Algorithms
【24h】

Building cyber resilience in space assets with real-time autonomous Graph Database Anomaly Detection Algorithms

机译：使用实时自主图数据库异常检测算法在空间资产中建设网络弹性

获取原文
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Advances and interconnected satellite communications (SATCOM) and navigation systems, and the development of smaller satellite technologies, mean that the international challenge at the intersection of space and cybersecurity could now be regarded as a strategic opportunity to enhance mission assurance for space assets. In this paper we describe cutting edge novel research in building cyber resilience in space assets with real-time autonomous Graph Database Anomaly Detection Algorithms. Anomaly detection algorithms with realtime Graph Database models provide autonomous, proactive, and intelligent cyber defense for space assets. Global, time differential, community, and neighbor anomalies are detected with iForest, DNODA (Direct Neighbor Outlier Detection Algorithms), CNA machine learning and AI methods to detect cyber security anomalies and classify them based on threat vector levels. Onboard Spacecraft and Ground based SIEM infrastructure is enhanced to recognize and eliminate threat vectors preemptively. The algorithms enhance preventive, detective, operational, countermeasure, and recovery controls.
机译：卫星通信（SATCOM）和导航系统以及较小卫星技术的发展意味着空间和网络安全交叉口的国际挑战现在可以被视为加强特派团保证空间资产的战略机会。本文介绍了利用实时自主图数据库异常检测算法在空间资产中建立网络恢复力的尖端新颖研究。具有实时图数据库模型的异常检测算法为空间资产提供自主，主动和智能的网络防御。使用IFOREST，DNODA（直接邻居异常检测算法），CNA机学习和AI方法来检测全局，时间差异，社区和邻居异常，以检测网络安全异常并根据威胁矢量水平对其进行分类。船上航天器和基于地面的SIEM基础设施得到了增强，以识别和消除威胁矢量。该算法增强了预防，侦探，操作，对策和恢复控制。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

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