公开(公告)号：US20160337218A1

公开(公告)日：2016-11-17

申请号：US15145870

申请日：2016-05-04

Applicant: AJOU UNIVERSITY INDUSTRY-ACADEMIC COOPERATION FOUNDATION

Inventor： Tae Shik SHON ,  Yong Min PARK ,  Hyung Uk YOO

IPC: H04L12/26 ,  H04L29/08 ,  H04L29/06

CPC classification number: H04L63/1425 ,  H04L43/062 ,  H04L43/12 ,  H04L69/08 ,  H04L69/40

Abstract: Provided are a method of monitoring a network driving apparatus provided in a network and a system thereof.The present invention provides a network monitoring method that performs monitoring which does not hinder existing network availability through a means for detouring a path of a packet transferred to a monitoring target apparatus by using one or more servers and clients connected to a network and further, provides extensibility which can be applied to the network using various communication protocols through a protocol converting means that detours the path of the packet after converting the existing protocol into a TCP/IP protocol.

Abstract translation: 本发明提供了一种网络监视方法，其通过使用连接到网络的一个或多个服务器和客户端，通过用于迂回传送到监视目标设备的分组的路径的装置来阻止现有的网络可用性，并进一步提供 可以通过协议转换装置使用各种通信协议应用于网络的可扩展性，其在将现有协议转换为TCP / IP协议之后绕过分组的路径。

公开(公告)号：US20180240016A1

公开(公告)日：2018-08-23

申请号：US15687773

申请日：2017-08-28

Applicant: AJOU UNIVERSITY INDUSTRY-ACADEMIC COOPERATION FOUNDATION

Inventor： Tae Shik SHON ,  Seok Jun LEE ,  Seok Cheol LEE ,  Hyung Uk YOO

IPC: G06N3/08 ,  G06F7/523

CPC classification number: G06N3/08 ,  G06F7/523 ,  G06N20/00

Abstract: Provided is a method for generating a one class model based on a data frequency. The method for generating a one class model based on a data frequency includes: generating, by a machine learning apparatus, a plurality of spatial coordinates by arranging a plurality of learning data in corresponding coordinates in a feature space; classifying, by the machine learning apparatus, the plurality of spatial coordinates into a plurality of internal coordinates PI and a plurality of external coordinates PO based on a frequency of the learning data arranged in the respective spatial coordinates which belong to the plurality of spatial coordinates; and generating, by the machine learning apparatus, a one class model based on the plurality of internal coordinates PI based on mutual spatial distances of the plurality of external coordinates PO and the plurality of internal coordinates PI.

公开(公告)号：US20170124333A1

公开(公告)日：2017-05-04

申请号：US15200051

申请日：2016-07-01

Applicant: AJOU UNIVERSITY INDUSTRY-ACADEMIC COOPERATION FOUNDATION

Inventor： Tae Shik SHON ,  Hyung Uk YOO

IPC: G06F21/57 ,  G06F11/36

CPC classification number: G06F21/577 ,  G06F11/3676 ,  G06F11/3684 ,  G06F2221/033

Abstract: According to an aspect of the inventive concept, there is provided a system for detecting vulnerabilities of communication protocol software, including: a field selection module selecting message fields of a communication protocol of an industrial control system; a value set configuration module configuring first value sets with respect to the respective message fields selected by the field selection module; a test case generation module generating first test cases by Cartesian product of the first value sets; a test module generating first code coverage data by testing the communication protocol software of the industrial control system based on the first test cases; and a code coverage analysis module analyzing the first code coverage data, wherein the field selection module selects concentration message fields which influence the first code coverage data among the message fields according to an analysis result of the code coverage analysis module.