TL;DR本文提出了一种 Deep Decision boundary Instance Generation(DeepDIG)的方法,在决策边界附近通过生成样本来深入理解深度神经网络的工作机制和决策行为多方面特征。在多个数据集上进行了实验和测试。
Abstract
deep neural networks and in particular, deep neural classifiers have become
an integral part of many modern applications. Despite their practical success,
we still have limited knowledge of how they work and the demand for such an
understanding is evergrowing. In this regard, one cruci