首页> 外国专利> CREATION AND VERIFICATION OF BEHAVIORAL BASELINES FOR THE DETECTION OF CYBERSECURITY ANOMALIES USING MACHINE LEARNING TECHNIQUES

CREATION AND VERIFICATION OF BEHAVIORAL BASELINES FOR THE DETECTION OF CYBERSECURITY ANOMALIES USING MACHINE LEARNING TECHNIQUES

机译:采用机器学习技术检测网络安全异常的行为基线的创建和验证

摘要

A system (10) for the creation and verification of behavioral baselines, comprising a central processing device (12) which comprises a control unit (14) and enriched data storage means (22) and which is connected to and communicates with a plurality of target apparatuses (36) and with an Identity & Access Management (IAM) apparatus (38). The central processing device (12) comprises: - an IAM state collection module (18) configured to generate a real-time synchronized copy of data on the IAM state which are recorded by the IAM apparatus (38), minimizing the overhead on said IAM apparatus (38); - a data enrichment module (20) configured to identify an entity in real time; - a Markovian module (24), configured to build a Markov transition matrix adapted to track the transition from a first activity to a second, temporally subsequent activity; - a baseline module (26), configured to calculate a plurality of individual score values, one for each individual activity/entity pair, and a plurality of collective score values, one for each individual activity/time window pair; - a log anomaly verification module (28) configured to assess the presence of a behavioral anomaly of the entity with respect to an individual space, on the basis of the plurality of individual score values; - a peer anomaly verification module (30), configured to assess behaviors of similar peer entities; and - a noise reduction module (32), configured to reduce the number of false positives on the basis of the assessment of the behavior of the similar peer entities.
机译:用于创建和验证行为基线的系统(10),包括中央处理设备(12),其包括控制单元(14)和富集的数据存储装置(22)并且连接到并与多个目标通信装置(36)和身份和访问管理(IAM)装置(38)。中央处理设备(12)包括: - IAM状态集合模块(18),被配置为在IAM装置(38)记录的IAM状态上生成数据的实时同步副本,从而最小化所述IAM上的开销装置(38); - 数据丰富模块(20),用于实时识别实体; - Markovian模块(24),配置为构建Markov转换矩阵,适于将从第一活动的转换跟踪到第二次时间后的活动; - 基线模块(26),被配置为计算多个单独的刻度值,一个用于每个单独的活动/实体对,以及用于每个单独的活动/时间窗对的多个集合分数值; - 基于多个单独的分数值,日志异常验证模块(28)被配置为评估各个空间对单个空间的行为异常的存在; - 对等异常验证模块(30),配置为评估类似同行实体的行为; - 降噪模块(32),用于基于对类似对等实体的行为的评估来减少误报的数量。

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