Non-informative noise-enhanced stochastic neural networks for improving adversarial robustness

Hao Yang, Min Wang, Qi Wang, Zhengfei Yu, Guangyin Jin, Chunlai Zhou, Yun Zhou

Abstract: Highlights•Introduce a novel stochastic neural network.•Extend beyond Gaussian by placing an arbitrary distribution over a non-informative prior.•Augment model uncertainty through network training.•The proposed method as an implicit regularization for robustness.•SOTA performance without the need for adversarial training.