METHOD APPARATUS COMPUTER-READABLE STORAGE MEDIUM AND COMPUTER PROGRAM FOR DETECTING ATTACK DATA

An attack data detection method performed by an attack data detection device according to an embodiment includes the steps of: performing data preprocessing corresponding to the type of data input from the outside; calculating a value output by passing the preprocessed data in a previously learned d...

Full description

Saved in:
Bibliographic Details
Main Authors MIN BYEONG JUN, KIM SANG SOO, KOO SUNG MO, KIM YI HYEONG, YOO JI HOON, SHIN DONG KYOO
Format Patent
LanguageEnglish
Korean
Published 30.12.2022
Subjects
Online AccessGet full text

Cover

Loading…
More Information
Summary:An attack data detection method performed by an attack data detection device according to an embodiment includes the steps of: performing data preprocessing corresponding to the type of data input from the outside; calculating a value output by passing the preprocessed data in a previously learned deep learning model and calculating a loss value between the preprocessed data; and checking whether the data is attack data based on a comparison between the calculated loss value and a threshold value. The threshold value may be a percentage value of a plurality of loss values calculated in a learning process of the previously learned deep learning model. 일 실시예에 따른 공격 데이터 탐지 장치에 의해 수행되는 공격 데이터 탐지 방법은, 외부로부터 입력 받은 데이터의 유형에 대응되는 데이터 전처리를 수행하는 단계와, 기 학습된 딥러닝 모델에 상기 전처리된 데이터를 통과시켜 출력된 값과 상기 전처리된 데이터간의 손실값을 산출하는 단계와, 상기 산출된 손실값과 임계값의 비교에 기초하여 상기 데이터가 공격 데이터인지 유무를 확인하는 단계를 포함하고, 상기 임계값은, 상기 기 학습된 딥러닝 모델의 학습 과정에서 산출된 복수의 손실값에 대한 백분율 값일 수 있다.
Bibliography:Application Number: KR20210081856