Adversarial-Playground: A Visualization Suite Showing How Adversarial Examples Fool Deep Learning

1 Aug 2017Andrew P. Norton • Yanjun Qi

Due to the complex nature of deep learning, it is challenging to understand how deep models can be fooled by adversarial examples. (2) It can help security experts explore more vulnerability of deep learning as a software module. (3) Building an interactive visualization is challenging in this domain due to the large feature space of image classification (generating adversarial examples is slow in general and visualizing images are costly).

Full paper

Evaluation


No evaluation results yet. Help compare this paper to other papers by submitting the tasks and evaluation metrics from the paper.