The A ConvNet for the 2020s paper from Facebook (Meta?) AI Research proposed a new architecture called ConvNeXt that is built out of standard convolutional blocks and seems to outperform the Vision Transformer (ViT). I wanted to know if it suffers from adversarial examples so I wrote a Colab that loads up a pretrained version of the ConvNeXt model, runs a quick loop of the Fast Gradient Sign Method, and demonstrates that it’s easy to find adversaries to this new model. This is not surprising, but I thought it might be valuable to demonstrate it explicitly as well as to create a Colab that others can run and modify for their own experiments.

Writing the Colab was made particularly fast by the Keras CV Attention Models repository that allows for an easy loading of the pretrained ConvNeXt model.

Stanislav Fort (Twitter, Scholar and GitHub)