parameter-space evolution

GRAPE: New Training Method Boosts Adversarial Robustness with 21% Fewer Parameters

A new training framework called GRAPE (Guided Parameter-Space Evolution) improves adversarial robustness in neural networks by progressively exposing parameters, achieving 56.94% robust accuracy on CIFAR-10 with 21.4% fewer parameters than standard adversarial training, according to an arXiv paper.