메뉴 건너뛰기
.. 내서재 .. 알림
소속 기관/학교 인증
인증하면 논문, 학술자료 등을  무료로 열람할 수 있어요.
한국대학교, 누리자동차, 시립도서관 등 나의 기관을 확인해보세요
(국내 대학 90% 이상 구독 중)
로그인 회원가입 고객센터 ENG
주제분류

추천
검색
질문

논문 기본 정보

자료유형
학술대회자료
저자정보
Liaq Ridda (Jeju National University) Flor Gutierrez De la Cruz (Jeju National University)
저널정보
대한산업공학회 대한산업공학회 춘계공동학술대회 논문집 2023년 대한산업공학회 춘계공동학술대회 논문집 [2개 학회 공동주최]
발행연도
2023.5
수록면
4,018 - 4,026 (9page)

이용수

표지
📌
연구주제
📖
연구배경
🔬
연구방법
🏆
연구결과
AI에게 요청하기
추천
검색
질문

이 논문의 연구 히스토리 (2)

초록· 키워드

오류제보하기
Recommendation systems are trending nowadays, and with the vast deployment of these systems, data protection is required. This paper focuses on the security efforts in a recommendation system for a dataset. In some domains (e.g., the medical, or financial sector), data security and the impact of data manipulation on a system are more relevant than others. The work’s primary goal is to focus on data security effects on recommendation systems and how to protect our dataset from intruders if any data is changed. In this project, the data set was attacked by an intruder, which changed the dataset which was correctly, and as a result, the output that was predicted was wrong, and as an effect of that, the user failed to proceed and complete the task on time, and the project failed.

We apply classification using a convolutional neural network (CNN) on two different datasets separately. We measure the effect of the data manipulation over these networks. We compare the result of a neural network trained on the original dataset with the one trained with the modified dataset. We consider a dataset containing ten different cases. We modify the dataset by changing the output values of one use case. Once the values are modified, we train a separate neural network based on this new dataset. The recommendation system was trained and tested on the modified data, and the results were wrongly calculated due to the data set differing from the original data set. When we apply a similar training and testing process on both Neural Networks, the modified dataset has incorrect results for 10 percent of the dataset.

목차

등록된 정보가 없습니다.

참고문헌 (0)

참고문헌 신청

함께 읽어보면 좋을 논문

논문 유사도에 따라 DBpia 가 추천하는 논문입니다. 함께 보면 좋을 연관 논문을 확인해보세요!

이 논문의 저자 정보

최근 본 자료

전체보기

댓글(0)

0