Neural prediction decorrelation reveals that adversarial robustness substantially improves DNN prediction accuracy across the entire human auditory cortex
David Skrill, Jenelle Feather, Sam Norman-Haignere
Sounds synthesized to decorrelate model predictions across human auditory cortex show an adversarially robust CochResNet50 predicts fMRI responses far better than its standard counterpart, a gap hidden with natural sounds.
bioRxiv · Oct 11, 2026 · PreprintNeuroscience✦ In-depth digest