현재 위치
Home
High Representation based GAN defense for Adversarial Attack
-
- 발행기관
- 국제인공지능학회(구 한국인터넷방송통신학회) 바로가기
-
- 간행물
- The International Journal of Advanced Smart Convergence KCI 등재 바로가기
-
- 통권
- Volume 8 Number 1 (2019.03)바로가기
-
- 페이지
- pp.141-146
-
- 저자
-
- 언어
- 영어(ENG)
-
- URL
- https://www.earticle.net/Article/A351892
※ 원문제공기관과의 협약기간이 종료되어 열람이 제한될 수 있습니다.
원문정보
초록
- 영어
- These days, there are many applications using neural networks as parts of their system. On the other hand, adversarial examples have become an important issue concerining the security of neural networks. A classifier in neural networks can be fooled and make it miss-classified by adversarial examples. There are many research to encounter adversarial examples by using denoising methods. Some of them using GAN (Generative Adversarial Network) in order to remove adversarial noise from input images. By producing an image from generator network that is close enough to the original clean image, the adversarial examples effects can be reduced. However, there is a chance when adversarial noise can survive the approximation process because it is not like a normal noise. In this chance, we propose a research that utilizes high-level representation in the classifier by combining GAN network with a trained U-Net network. This approach focuses on minimizing the loss function on high representation terms, in order to minimize the difference between the high representation level of the clean data and the approximated output of the noisy data in the training dataset. Furthermore, the generated output is checked whether it shows minimum error compared to true label or not. U-Net network is trained with true label to make sure the generated output gives minimum error in the end. At last, the remaining adversarial noise that still exist after low-level approximation can be removed with the U-Net, because of the minimization on high representation terms.
목차
Abstract
1. Introduction
2. Method
3. Experiments
4. Results and Discussion
5. Conclusion
Acknowledgement
References
키워드
Neural networks Adversarial examples Generative adversarial network Adversarial attack Adversarial defense.저자
간행물 정보
발행기관
-
- 발행기관명
- 국제인공지능학회(구 한국인터넷방송통신학회) [The International Association for Artificial Intelligence]
- 설립연도
- 2000
- 분야
- 공학>전자/정보통신공학
- 소개
- 인터넷방송, 인터넷 TV , 방송 통신 네트워크 및 관련 분야에 대한 국내는 물론 국제적인 학술, 기술의 진흥발전에 공헌하고 지식 정보화 사회에 기여하고자 한다.
간행물
-
- 간행물명
- The International Journal of Advanced Smart Convergence
- 간기
- 계간
- pISSN
- 2288-2847
- eISSN
- 2288-2855
- 수록기간
- 2012~2025
- 십진분류
- KDC 326 DDC 380
이 권호 내 다른 논문 / The International Journal of Advanced Smart Convergence Volume 8 Number 1
피인용수 : 0건 (자료제공 : 네이버학술정보)
함께 이용한 논문 이 논문을 다운로드한 분들이 이용한 다른 논문입니다.
출처 : 네이버학술정보
0개의 논문이 장바구니에 담겼습니다.