Identify Malicious Software

专利名称：Identify Malicious Software发明人：Richard Cannings,Sai Deep Tetali,Mo

Yu,Salvador Mandujano

申请号：US17057639申请日：20180521

公开号：US20210200872A1公开日：20210701

专利附图：

摘要：A method () for identifying malicious software includes receiving and executing asoftware application (), identifying a plurality of uniform resource identifiers () thesoftware application interacts with during execution of the software application, and

generating a vector representation () for the software application using a feed-forwardneural network () configured to receive the plurality of uniform resource identifiers asfeature inputs. The method also includes determining similarity scores () for a pool oftraining applications, each similarity score associated with a corresponding trainingapplication and indicating a level of similarity between the vector representation for thesoftware application and a respective vector representation for the correspondingtraining application. The method also includes flagging the software application asbelonging to a potentially harmful application category () when one or more of thetraining applications have similarity scores that satisfy a similarity threshold and include apotentially harmful application label.

申请人：Google LLC

地址：Mountain View CA US

国籍：US

更多信息请下载全文后查看