Dissociating spatial frequency reliance from adversarial robustness advantages in neurally guided deep convolutional neural networks

ArXi:2605.04443v1 Announce Type: cross Deep convolutional neural networks (DCNNs) have rivaled humans on many visual tasks, yet they remain vulnerable to near-imperceptible perturbations generated by adversarial attacks. Recent work shows that aligning DCNN representations with human visual cortex activity improves adversarial robustness, but the mechanisms driving this advantage are unclear. One hypothesis suggests that neural alignment confers robustness by biasing models away from brittle high-frequency details and towards the low spatial frequencies.