发明授权
US08544087B1 Methods of unsupervised anomaly detection using a geometric framework
有权
使用几何框架进行无监督异常检测的方法
- 专利标题： Methods of unsupervised anomaly detection using a geometric framework
- 专利标题（中）： 使用几何框架进行无监督异常检测的方法
-
申请号： US12022425申请日： 2008-01-30
-
公开(公告)号： US08544087B1公开(公告)日： 2013-09-24
- 发明人: Eleazar Eskin , Andrew Oliver Arnold , Michael Prerau , Leonid Portnoy , Salvatore J. Stolfo
- 申请人： Eleazar Eskin , Andrew Oliver Arnold , Michael Prerau , Leonid Portnoy , Salvatore J. Stolfo
- 申请人地址： US NY New York
- 专利权人： The Trustess of Columbia University in the City of New York
- 当前专利权人： The Trustess of Columbia University in the City of New York
- 当前专利权人地址： US NY New York
- 代理机构： Baker Botts, L.L.P.
- 主分类号： G06F12/14
- IPC分类号： G06F12/14 ; G06F12/16
摘要：
A method for unsupervised anomaly detection, which are algorithms that are designed to process unlabeled data. Data elements are mapped to a feature space which is typically a vector space . Anomalies are detected by determining which points lies in sparse regions of the feature space. Two feature maps are used for mapping data elements to a feature apace. A first map is a data-dependent normalization feature map which we apply to network connections. A second feature map is a spectrum kernel which we apply to system call traces.
信息查询
