AINeutralarXiv – CS AI · Jun 26/10
🧠
SORA: Free Second-Order Attacks in Fast Adversarial Training
Researchers introduce SORA, a new adversarial training method that addresses catastrophic overfitting in fast neural network defense systems. By leveraging perturbation variability and a novel gradient alignment metric, SORA achieves state-of-the-art robustness against adversarial attacks while maintaining higher clean accuracy with improved computational efficiency.