[论文阅读笔记]One pixel attack for foo

论文题目：One pixel attack for fooling deep neural networks
论文地址：https://arxiv.org/abs/1710.08864

One-pixel

The goal of adversaries in the case of targeted attacks is to find the optimized solution for the following question:

where

• , n-dimensional inputs
• , the target image classifier
• , the probability of belonging to the class
• , an additive adversarial perturbation according to
• , the target class
• , the limitation of maximum modification

In our approach, the equation is slightly different:

where is a small number. In the case of one-pixel attack .
note: 0范数表示向量中非零元素的个数。

参考

One pixel 对抗攻击_学习笔记
修改一个像素，就能让神经网络识别图像出错
论文阅读笔记三十：One pixel attack for fooling deep neural networks（CVPR2017）