Random Projections for Improved Adversarial Robustness

We propose two training techniques for improving the robustness of Neural Networks to adversarial attacks, i.e. manipulations of the inputs that are maliciously crafted to fool networks into incorrect predictions. Both methods are independent of the chosen attack and leverage random projections of the original inputs, with the purpose of exploiting both dimensionality reduction and some characteristic geometrical properties of adversarial perturbations. The first technique is called RP-Ensemble and consists of an ensemble of networks trained on multiple projected versions of the original inputs. The second one, named RP-Regularizer, adds instead a regularization term to the training objective.

Automated summary

In this study, two training techniques, namely RP-Ensemble and RP-Regularizer, are proposed to enhance the robustness of Neural Networks against adversarial attacks. Both methods leverage random projections to exploit dimensionality reduction and geometric properties of adversarial perturbations, aiming to improve the network's resistance to input manipulations.