公开(公告)号：US20200380123A1

公开(公告)日：2020-12-03

申请号：US16887623

申请日：2020-05-29

Applicant: General Electric Company

Inventor： Johann REIMANN ,  Nurali VIRANI ,  Naresh IYER ,  Zhaoyuan YANG

IPC: G06F21/56 ,  G06N7/00 ,  G06N20/10 ,  G06N3/08 ,  G06K9/62

Abstract: A system and method including receiving a set of deep neural networks (DNN) including DNNs trained with an embedded trojan and DNNs trained without any embedded trojan, each of the trained DNNs being represented by a mathematical formulation learned by the DNNs and expressing a relationship between an input of the DNNs and an output of the DNNs; extracting at least one characteristic feature from the mathematical formulation of each of the trained DNNs; statistically analyzing the at least one characteristic feature to determine whether there is a difference between the DNNs trained with the embedded trojan and the DNNs trained without any embedded trojan; generating, in response to the determination indicating there is a difference, a detector model to execute the statistical analyzing on deep neural networks; and storing a file including the generated detector model in a memory device.