Proj CDeepFuzz Paper Reading: The limitations of deep learning in adversarial settings

Abstract

本文：
Task: formalize the space of adversaries against DNNs and then introduce an adversarial testing

实验：
方法：defining a hardness measure
效果：

1. 能以97%的成功率生成adversarial examples(人工核查DNN的错误）,平均修改每个samples中4.02%input features
2. 评估不同类别对扰动的敏感度
3. 对已有Defenses进行了评估