Dissociable Neural Representations of Adversarially Perturbed Images in Convolutional Neural Networks and the Human Brain.

ABSTRACT: Despite the remarkable similarities between convolutional neural networks (CNN) and the human brain, CNNs still fall behind humans in many visual tasks, indicating that there still exist considerable differences between the two systems. Here, we leverage adversarial noise (AN) and adversarial interference (AI) images to quantify the consistency between neural representations and perceptual outcomes in the two systems. Humans can successfully recognize AI images as the same categories as their corresponding regular images but perceive AN images as meaningless noise. In contrast, CNNs can recognize AN images similar as corresponding regular images but classify AI images into wrong categories with surprisingly high confidence. We use functional magnetic resonance imaging to measure brain acti

SUBMITTER: Zhang C 

PROVIDER: S-EPMC8375771 | biostudies-literature | 2021

REPOSITORIES: biostudies-literature