Identifying exceptional web documents

摘要: Techniques are provided through which “suspicious” websites may be identified automatically. A suspicious website is one that associated with many changes or an inconsistent number of in web registry information over time. Registry received when to the occur. The referred as a transaction. transaction comprised plurality values each correspond characteristic. characteristic property website, such website's contact information. count particular characteristic-value pair updated time value high indicates lot changes. Therefore, suspicious. Other factors used for identifying include how often and much