2019.11.15 note (1)

2019.11.15 note (1)

EXPLAINING AND HARNESSING ADVERSARIAL EXAMPLES

FGSM (Fast Gradient Sign Method)

在这里插入图片描述


Adversarial examples in the physical world


Another version:

Towards Deep Learning Models Resistant to Adversarial Attacks

2019.11.15 note (1)_第1张图片

Another version (L2 norm instead of L-inf norm):

你可能感兴趣的:(Paper,Reading)