Bronya Roni Chernyak

Constant Random Perturbations Provide Adversarial Robustness with Minimal Effect on Accuracy

2021 · arXiv (Cornell University)

This paper proposes an attack-independent (non-adversarial training) technique for improving adversarial robustness of neural network models, with minimal loss of standard accuracy. We suggest creating a neighborhood around each training example, such that the label …