Zhenan Shao

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

2026 · PubMed

Deep convolutional neural networks (DCNNs) have approached and even surpassed human-level performance on many visual recognition tasks, yet they remain strikingly vulnerable to near-imperceptible perturbations generated by adversarial attacks. Recent research demonstrates that aligning DCNN …