公开(公告)号：US10984105B2

公开(公告)日：2021-04-20

申请号：US16193822

申请日：2018-11-16

Applicant: Avast Software s.r.o.

Inventor： Petr Gronat ,  Rajarshi Gupta ,  Filip Havlicek ,  Michal Wojcik

IPC: G06F21/56 ,  G06N5/04 ,  G06N20/00

Abstract: Minimizing the latency of on-device detection of malicious executable files, without sacrificing accuracy, by applying a machine learning model to an executable file in quantized steps. Allowing a threshold confidence level to be set to different values enables controlling the tradeoff between accuracy and latency in generating a confidence level indicative of whether the executable file includes malware.

公开(公告)号：US20190156037A1

公开(公告)日：2019-05-23

申请号：US16193822

申请日：2018-11-16

Applicant: Avast Software s.r.o.

Inventor： Petr Gronat ,  Rajarshi Gupta ,  Filip Havlícek ,  Michal Wojcik

IPC: G06F21/56 ,  G06N5/04

Abstract: Minimizing the latency of on-device detection of malicious executable files, without sacrificing accuracy, by applying a machine learning model to an executable file in quantized steps. Allowing a threshold confidence level to be set to different values enables controlling the tradeoff between accuracy and latency in generating a confidence level indicative of whether the executable file includes malware.