Code + Data from the paper "Finding Biological Plausibility for Adversarially Robust Features via Metameric Tasks" by Anne Harrington + Arturo Deza published as a Spotlight in ICLR 2022. Link to paper: https://openreview.net/forum?id=yeP_zx9vqNm

All the participant data with respect to the experiments below are available in the psychophysics folder.

All the code wrt to the computational experiments in the paper can be seen in the Machine folder (to be uploaded).

The Visual Stimuli used in our experiments can be downloaded here: https://www.kaggle.com/neurosurfer/peripheral-stimuli

Our paper was also recently featured at MIT News: https://news.mit.edu/2022/machine-peripheral-vision-0302

If you have found this documentation, code, data and research useful for your current research please consider citing:

@inproceedings{
harrington2022finding,
title={Finding Biological Plausibility for Adversarially Robust Features via Metameric Tasks},
author={Anne Harrington and Arturo Deza},
booktitle={Published at The Tenth International Conference on Learning Representations},
year={2022},
url={https://openreview.net/forum?id=yeP_zx9vqNm},
}