Join or Log in
Abstract: Recent research has revealed that the output of Deep neural networks(DNN) is not continuous and very sensitive to tiny perturbation on the input vectors and accordingly several methods have been proposed for crafting effective perturbation against the networks. In this paper, we propose a novel method for optically calculating extremely small adversarial perturbation (few-pixels attack), based on differential evolution.
[1710.08864] One pixel attack for fooling deep neural networks 
Added 9 months ago by Francis Tseng
Show info
[1710.08864] One pixel attack for fooling deep neural networks 
Info
Abstract: Recent research has revealed that the output of Deep neural networks(DNN) is not continuous and very sensitive to tiny perturbation on the input vectors and accordingly several methods have been proposed for crafting effective perturbation against the networks. In this paper, we propose a novel method for optically calculating extremely small adversarial perturbation (few-pixels attack), based on differential evolution.
1 Connection