Adversarially trained neural representations may already be as robust as corresponding biological neural representations

TitleAdversarially trained neural representations may already be as robust as corresponding biological neural representations
Publication TypeJournal Article
Year of Publication2022
AuthorsGuo, C, Lee, MJ, Leclerc, G, Dapello, J, Rao, Y, Madry, A, DiCarlo, JJ
JournalarXiv
Date Published06/2022
Abstract

Visual systems of primates are the gold standard of robust perception. There is thus a general belief that mimicking the neural representations that underlie those systems will yield artificial visual systems that are adversarially robust. In this work, we develop a method for performing adversarial visual attacks directly on primate brain activity. We then leverage this method to demonstrate that the above-mentioned belief might not be well founded. Specifically, we report that the biological neurons that make up visual systems of primates exhibit susceptibility to adversarial perturbations that is comparable in magnitude to existing (robustly trained) artificial neural networks.

Associated Module: 

CBMM Relationship: 

  • CBMM Related