December 2020
Beginner to intermediate
256 pages
5h 15m
Korean
Content preview from 안전한 인공지능 시스템을 위한 심층 신경망 강화
Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
O’Reilly covers everything we've got, with content to help us build a world-class technology community, upgrade the capabilities and competencies of our teams, and improve overall team performance as well as their engagement.I wanted to learn C and C++, but it didn't click for me until I picked up an O'Reilly book. When I went on the O’Reilly platform, I was astonished to find all the books there, plus live events and sandboxes so you could play around with the technology.I’ve been on the O’Reilly platform for more than eight years. I use a couple of learning platforms, but I'm on O'Reilly more than anybody else. When you're there, you start learning. I'm never disappointed.I'm always learning. So when I got on to O'Reilly, I was like a kid in a candy store. There are playlists. There are answers. There's on-demand training. It's worth its weight in gold, in terms of what it allows me to do.
106
2
부
적대적 입력 생성하기
실제로 훈련 데이터가 예측 지도와 같은 실제 이미지를 표현한다면 많은
OoD
입력은 자연스럽게 발생하지
않는 데이터에 해당합니다. 임의의 픽셀 이미지나 이상한 조작을 가한 이미지는
OoD
입니다. 대개 이런 입
력은 결정을 내리지 못하는 모델 예측을 초래할 것이며, 이것은 우리가 예상할 수 있는 일입니다. 그러나 때
로는 모델이
OoD
입력에 대해 확신 있게 잘못된 예측을 합니다.
OoD
데이터를 인식하는 것은 매우 어렵습니다. 적대적 공격을 방어하는 방법은
10
장에서 살펴보겠습니다.
5.1.2
OoD
데이터 실험
DNN
분류기에 무질서하거나 비현실적인 이미지를 입력하면 어떤 결과를 보여주는지 실험해
보는 것도 흥미롭습니다. [그림
5
-
4
]는
Fashion
-
MNIST
와
ResNet50
모델에 임의의 이미지
를 입력한 예측 결과입니다.
그림
5-4
임의로 생성한 이미지에 대한 분류기의 예측
Fashion-MNIST
예측:
가방
0
.
850
스웨터
0
.
080
셔츠
0
.
054
ResNet50
예측:
테니스공
0
.
223
체인
0
.
108
철책선
0
.
081
Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.
Read now
Unlock full access
More than 5,000 organizations count on O’Reilly
O’Reilly covers everything we've got, with content to help us build a world-class technology community, upgrade the capabilities and competencies of our teams, and improve overall team performance as well as their engagement.Julian F.
I wanted to learn C and C++, but it didn't click for me until I picked up an O'Reilly book. When I went on the O’Reilly platform, I was astonished to find all the books there, plus live events and sandboxes so you could play around with the technology.Addison B.
I’ve been on the O’Reilly platform for more than eight years. I use a couple of learning platforms, but I'm on O'Reilly more than anybody else. When you're there, you start learning. I'm never disappointed.Amir M.
I'm always learning. So when I got on to O'Reilly, I was like a kid in a candy store. There are playlists. There are answers. There's on-demand training. It's worth its weight in gold, in terms of what it allows me to do.