Deep learning-based visual sensing has achieved attractive accuracy but is shown
vulnerable to adversarial attacks. Specifically, once the attackers obtain the deep model …

DeepMTD: Moving Target Defense for Deep Visual Sensing against Adversarial Examples
1: 3 on several datasets, the adversarial examples can mislead the new deep models with a …

DeepMTD: Moving Target Defense for Deep Visual Sensing against Adversarial Examples
1: 3 on several datasets, the adversarial examples can mislead the new deep models with a …