公开(公告)号：US20180278635A1

公开(公告)日：2018-09-27

申请号：US15811248

申请日：2017-11-13

Applicant: Korea Advanced Institute of Science and Technology

Inventor： Seungwon Shin ,  Chanhee Lee ,  Changhoon Yoon ,  Sang Kil Cha

IPC: H04L29/06 ,  G06F9/54 ,  G06N99/00

CPC classification number: H04L63/1425 ,  G06F9/547 ,  G06N20/00 ,  H04L45/38 ,  H04L45/42 ,  H04L45/64 ,  H04L63/145

Abstract: Disclosed are an apparatus, a method, and a computer program by which it is determined whether a target network program generated in a software defined network is malicious by extracting a feature of a behavior graph of the target network program and applying machine learning to the behavior graph. Accordingly, a security and safety of a software defined network may be improved by detecting whether a computer program is malicious before the malware is installed.